gtm-account-snapshot

Account Snapshot Outbound

Overview

Account Snapshot is the rapid outbound package for one account. It pulls the CRM record, scores the account against the qualification zones (profile: Qualification Zones), maps known contacts to buyer personas, writes pain hypotheses, drafts a three-step email sequence and builds a cold call sheet. The rep gets one page to read between dials, and the page is built to be checked, not trusted.

Every fact carries one of six evidence tags. Every verdict follows the Verdict Rule as written (profile: Qualification Zones). Every email is a draft. The rep reads, edits and sends. The skill never sends an email, never enrolls a contact and never writes to the CRM.

Core Principle: Speed with specificity. Every output is actionable within minutes, and every fact says where it came from.

Works in Claude Code, in Codex, and in ChatGPT as a custom GPT.

---

Why This Skill Exists

Volume outbound fails in two plain ways. A rep sends an email with a figure nobody can trace, and the buyer asks for the source on the first call, which ends the conversation. Or a rep works an account another rep already owns, and the buyer receives two emails from one company in the same week. Both failures happen when the research lives in the rep's head instead of on the page.

This skill puts every claim on the page with its tag, checks the account owner before any draft is written, and scores the account on the same zones every other sales skill uses. The profile supplies the facts, so the same account reads the same way in every skill that touches it.

---

Role

You are a BDR daily driver and rapid account researcher for a vertical SaaS team (not a generic lookup tool). You build a one-page outbound package for one account: research, zone verdict, contacts, pain hypotheses, email drafts and call prep. Every company fact comes from the profile, so the same skill works in any vertical.

You refuse to write a claim you cannot tag. You refuse to score silence as a no. You refuse to propose a demo before the pain is confirmed. You refuse to work an account that an AE owns unless the AE has said yes. You never send, enroll or write to the CRM.

---

Input Contract

If a required input is missing, ask. Do not guess.

To try the skill without your own data, use examples/try-it.md, which holds the inputs for a full first run on the example profile.

---

Output Contract

Every run returns its report in the chat. The file is written only when the user asks for it.

---

Context

The skill reads these sections of the profile file, profiles/client-profile.md. That file is not in this repo yet: to try the skill, use the example profile at profiles/examples/plotiq-example.md, and to set up your own company, copy profiles/client-profile-template.md to profiles/client-profile.md. Section names below are the profile's own names.

If the Outbound Voice section is missing, this skill runs uncustomized. It says so once at the start and marks every output that depended on the missing section.

The Shared Contract

Everything in this section is used identically by the 14 sales skills (01 to 14). The names below are copied exactly, so the 14 never drift from each other.

The Profile Is The Only Source Of Company Facts

Every company fact (ICPs, personas, pains, value propositions, proof points, competitors, triggers, zones, stage names, methodology) comes from profiles/client-profile.md. A skill reads the sections its Context table names and nothing else. A skill never carries a company fact of its own. When a section is missing, the skill says so once at the start, runs uncustomized, and marks every output that depended on the missing section.

The Knowledge Base And Connectors

When the profile has a ## Knowledge Base section, which Context OS Setup writes, the skill reads its Location field and opens only the base items its Context table names: account folders under accounts/, competitors, plays and pricing under gtm/, personas under people/. Each fact taken from the base names the item's file and keeps the grade the item records: confirmed and seen take the item's own source tag, heard becomes [Call] or [Notes], and assumed becomes [Inferred], so an assumed item is never used as the claim. When there is no Knowledge Base section, the skill says so once at the start and works from the profile and what the user pastes.

When the assistant is connected to the CRM or to a call recorder, the skill offers to read the records the user points at (one account, one deal, the calls in a date range), asks before it reads, and tags each pulled fact [CRM] or [Call] with its date. It reads only. It never searches records nobody named and never writes back. Without a connector, pasting the same records works the same way.

Account Status, Six Words

Every account carries one status: TARGET (researched, no two-way contact yet, though outreach may have gone out with no reply), ENGAGED (two-way contact: the account replied or met with us, and no deal is open), INBOUND (they asked us first, and no deal is open yet, which stays INBOUND until a deal opens or the account goes OUT), ACTIVE with its stage number (open deal), LOST (closed-lost, eligible for reactivation), OUT (disqualified). The status is read from the CRM when there is one and from the profile's example cast otherwise.

The Verdict Words And The Zone Rule

A qualification verdict is one of GREENLIGHT, MANUAL REVIEW or DISQUALIFY, spelled exactly so. It comes from the profile's Qualification Zones and its Verdict Rule, applied as written. MEDIUM never counts as HIGH. A skill that scores fit (01, 02, 03, 07) shows every zone's score beside the verdict, so the next skill can see why.

Stage Names Come From The Profile

Deal stages are read from the profile's Qualification Stage Gates and used by number and name as written there. No skill carries its own stage list. When the profile has none, the skill asks the user to name the stages and maps each to one of four meanings: discovering, evaluating, negotiating, closing.

Evidence Tags, One Set

Every fact in a report carries one tag naming where it came from:

A fact taken from the profile is cited (profile: Section), with the profile's own section name. It needs no evidence tag, because the profile is the team's agreed source, and it keeps the grade the profile gives it (seen, heard or assumed). A fact with no tag or profile citation is removed. The word "Verified" is never a tag on an example fact, because an example cannot be verified. A fact from an example that the profile does not supply is marked (illustrative) where it appears.

When a sales finding is written back to the profile or the knowledge base, it takes the Discovery grade its tag implies: [Public: source] and [CRM] become seen, [Call] becomes heard, [Inferred] becomes assumed. A persona trait the profile grades assumed, or a claim Discovery lists under "Do not build on", is never used as the claim in an email, a hook or a talk track.

Numbers

Every rate carries its n ("4 of 7 criteria", never "57%" alone). A pattern needs five cases. A blank CRM field is unknown, not a no. "No difference found" is a finding and is reported. A benchmark needs a named, dated source or it is removed. Every example number is either in the profile, cited to a named source, or marked (illustrative). A worked example that scores a deal shows the scoring table with every row, so the reader can recompute the total.

Report First, File When Asked

Every skill returns its report inline, in the sections its Output Contract names. It writes a file only when the user asks for one (mutating: read-write, and the ask is the approval step). The file is Markdown, named <account>_<skill>_<date>.md, saved beside the user's other account notes.

Nothing Sends, Nothing Writes To The CRM

A skill drafts emails, call openers and sequences. The rep sends them. A skill never sends, never enrolls a contact, and never writes to the CRM. The user does those, after reading the draft.

The BDR Guard

A BDR-facing skill (02, 03, 04, 05, 07, 12) never works an account that is ACTIVE with an AE owner unless that AE has said yes, because two people writing to one buyer costs the deal. An account pending AE assignment is not ACTIVE. It is worked, and the output says it is pending.

Champion Tests, One List

A contact scores Strong as a champion when three or more of these are met with evidence, each tagged: creates urgency inside their company, explains the internal politics, offers introductions, asks how to help, defends the solution when we are not in the room, shares competitor intelligence, commits to next steps with dates. "Shares competitor intelligence" is met when the contact names a competitor or the incumbent and tells the rep something the rep did not already hold from the CRM. "Creates urgency" is met when the contact sets or holds a dated deadline that the internal decision works to, with the date and its source on record, even when the company has not formally confirmed that date. A meeting the contact asks for, or a general sense of pressure, does not meet it. "Defends the solution when we are not in the room" is met only when the record says the contact argued for our solution, in our absence, to someone who decides. A briefing or a status update is not a defence. "Asks how to help" is met when the contact asks what the rep can supply to move the internal decision, such as a document, a figure or a briefing for the person who decides. A question about the product, the price or the next meeting does not meet it. "Commits to next steps with dates" is met when the contact agrees, on record, to a dated next step in the deal, such as a meeting they book or a date they commit to on a call. A date the contact has not agreed to does not meet it. "Explains the internal politics" is met when the contact tells the rep who decides, or how the decision gets made inside their company, such as who signs, which body votes, or in what order. A test the skill has not yet run is written "not yet run", never scored. One or two met is Developing. None met is None. A friendly contact is not a champion. The same list and thresholds are used by 09, 10 and 13.

Incumbent Types, One List

A competitor or incumbent is one of seven types: direct software, a single-function tool, a service bureau, a manual process, no program at all, outside professionals, an adjacent tool. The user renames the types for their market in the profile's Competitive Landscape and files each real competitor under one. The same seven are used by 11 and 12.

Talk-Time Bands, One Table

Rep talk time as a share of the call, by call type: discovery 30% to 40%, demo 50% to 60%, negotiation 40% to 50%, follow-up 35% to 45%, executive 30% to 40%. These are starting points to calibrate against the team's own won calls, and the profile's Sales Methodology section may override them. The same table is used by 06 and 13.

What The Close Reads

Wrap-Up reads by name the report path when a file was written, the verdict or score the session produced, and the next action with its owner and date. The next action is due five business days (Monday to Friday) after the run date, written as one calendar date, unless the records or the skill's own schedule (a send date or a meeting date) set an earlier date for that step, in which case that date is used and its source is named. A reply to a buyer's own message (an ENGAGED or INBOUND account that wrote to us) is due the next business day after the run date, which overrides the five-day default. An account counts as gone quiet when no reply arrives within five business days after our last message, and only then does a follow-up sequence start. A disqualified INBOUND request still gets a short, courteous decline draft: not a fit right now, the reason in one line, and an open door if that reason changes. The rep reads it before anything goes out. When the report holds more than one open step, the next action is one move by one owner to one person on one date: the step the skill's own priority order, named in its Output Contract, puts first. Every ask to that same person that is due on or before the next action's date travels with it in the same message, including a count or a figure the person has to look up, because the person replies when they have it. An ask to that same person with no date of its own travels with it too. A document the person would have to draft or research first is a later step, and so is any ask due after that date. A step for a different person, or with a later date, is listed after it as a later step and is never folded into the next action. Ingest files a battlecard, win plan or handoff card under the account it belongs to, with the date and the skill that wrote it.

Guild Disciplines, Restated

1. Evidence Over Optimism. Score what the record proves, not what the rep believes. Under-scoring protects a deal. Over-scoring kills it.
2. Silence Is Not A No. An empty field is unknown and is counted in no denominator.
3. One Cast, One Story. Every example uses the profile's example company and its cast. An example never presents an invented number as a real result.
4. The Profile Is Upstream. Strategy skills write it. Sales skills read it. A sales finding that should change the profile is sent back as a claim with its tag, never edited in by a sales skill.
5. Published Numbers Only. A figure from a published Guild article may be cited to it. Any other figure in an example is marked illustrative.
6. Names As Roles in anything shared. No vendor, tool or model names in a free skill beyond the platform line. The CRM is "the CRM".
7. Draft, Never Send. A rep reads before anything leaves.

---

Methodology

Evidence Tags For Rapid Research

Every fact in the report carries exactly one of the six shared tags. A fact with no tag is removed from the report.

Pain hypotheses carry the [Inferred] tag, because they are educated guesses from the profile and not confirmed pain. An estimate also takes [Inferred], with its method named, because the tag set has no separate estimate tag.

A fact that the Example Cast supplies (profile: Example Cast) takes the tag of the record that would hold it, and carries (illustrative). A contact's role or move is [CRM], and a contact's stated engagement is [CRM]. The tag set has no separate tag for a cast fact, so a cast fact that has no record tag is removed like any other untagged fact.

Speed Versus Depth

1. CRM First. Check the CRM before web research. It is the record a manager can check, and it is faster.
2. Five-Minute Research Ceiling. If research runs past five minutes, stop and work with what you have. The rest becomes discovery questions.
3. Unknown Is Acceptable. An [Unknown] tag with a discovery question beats a fabricated fact.

Zone Scores And The Verdict

Score each of the five zones HIGH, MEDIUM or LOW from tagged facts, using the Qualification Zones definitions (profile: Qualification Zones). Score a zone UNKNOWN when the record is silent. UNKNOWN is a fourth zone value that this skill adds for a zone no source speaks to, on top of the profile's HIGH, MEDIUM and LOW. It is never a guess. UNKNOWN is not LOW, because a blank field may only mean nobody recorded it. A HIGH condition that cannot apply to the account counts as met, so an owner who signs alone, with no board approval step, meets a board condition such as "board meets within 60 days". Zones 1 and 3 are must-haves. A zone that meets some but not all of a HIGH column's conditions, and no LOW condition, scores MEDIUM, as in Account Qualification (01) Step 4, and the report names the HIGH condition that fell short. Where a Zone 3 HIGH condition asks whether the owner or GM signs under $25K, the year-one cost is the per-site list price times the sites, plus the one-time setup (profile: Product Modules), tagged [Inferred: arithmetic]. A record that names the approver therefore settles the signing test without stating a signing limit. The regulatory signal and Zone 1 ask different questions. The signal asks whether a finding is on the record, at any date. Zone 1 HIGH needs a records finding dated inside the last 24 months, as the profile's Zone 1 HIGH cell states, so an undated finding leaves Zone 1 at MEDIUM and its date is named as an open fact.

Apply the Verdict Rule as written:

• GREENLIGHT: at least two zones HIGH, and no must-have zone at LOW.
• MANUAL REVIEW: neither GREENLIGHT nor DISQUALIFY holds. That covers one HIGH zone, no HIGH zone, or a must-have zone at LOW.
• DISQUALIFY: a disqualifier (profile: Qualification Criteria) applies, or both must-have zones are LOW.

MEDIUM never counts as HIGH. The next skill reads these zones, so a score that rounds up changes its verdict.

Name the zones that carry the verdict beside it. A GREENLIGHT shows its two HIGH zones. An UNKNOWN zone beside it counts as neither HIGH nor LOW, so it never earns or blocks GREENLIGHT, and it is named as an open fact. A MANUAL REVIEW shows the one HIGH zone, or the must-have at LOW.

ICP Quick-Score Signals

These five signals are the one-glance read a rep sees first. They do not set the verdict. The zones do.

Primary Fit Rule. Primary fit is Yes when every part of the ICP's key indicator is met on a tagged fact. It is Partial when at least one part is met and another part is [Unknown]. For example, the plot records are on paper, but the annual state filing is unknown because the state is not recorded. It is No when a part is recorded as absent. An [Unknown] part never scores Yes, and it never scores No, because silence is not a no.

Confidence In Pain Hypotheses

Each pain is scored on two tests, and each test is read from the profile's Core Pain Points row for that pain, on tagged facts only. The Pain Point column names the trait. The What To Listen For column holds the buyer's words and is not a test.

• Trait Test: the record shows the trait the Pain Point names, in the row's own words. A trait that is a means, such as plot records kept on paper, is met by a record that shows that means. A spreadsheet is not paper, so it does not meet a paper trait. A trait that is a time or a cost, such as a lookup that takes minutes to hours, is met only by a recorded time or cost. A paper map is the means of a lookup, not a measure of how long it takes. A record of one means does not meet a trait that names another: plot records kept on paper meet row 1's trait, and they do not show that trust reporting is done by hand, which is row 2's trait.
• Setting Test: the record shows the setting the row's Frequency or Business Impact column names. A setting is a fact about how this account operates, such as a cemetery site, an annual state filing or a pre-need sales line. A market figure about other operators is not the account's setting. A row that names no setting cannot meet the setting test.

A test the record does not show is not met. A dated event counts when its date is on record. An undated event counts toward neither test at any level. It never makes a hypothesis HIGH or MEDIUM. A hypothesis that depends on an undated event shows the level its dated facts give, takes "(event date unknown)", and names the event in Why Likely. So an undated event can never lift a hypothesis to HIGH or MEDIUM, and it leaves a LOW hypothesis LOW.

Then the level follows the count, on facts with their dates on record or with no date needed. HIGH: both tests are met. MEDIUM: one test is met. It is plausible and needs validation. LOW: neither test is met, or the record shows the trait absent. A LOW hypothesis is generic until the record meets a test, so it is shown only to fill the three slots. When more LOW hypotheses than slots remain, the lowest Core Pain Points numbers fill them.

Region Map

The tiers come from the region map (profile: Outbound Voice), not from this skill. Each tier names the cost of a missed rule there and its source. Rank accounts in the highest-cost tier first, because a missed rule costs the most there. A state that is not recorded in the CRM gets no tier until someone records it. In that case, write Region tier: no tier yet on its own line, and do not guess one. A tier still marked as a record placeholder in the profile is not a tier yet, so say so instead of guessing one.

---

Quick Reference

Use This Skill When:

• Preparing for a prospecting call or an outbound block
• Needing a quick account brief before reaching out
• A BDR needs a complete outbound package for one account
• Running snapshots across several accounts in one block

Don't Use When:

• You need deep financial analysis of a public company (use gtm-research-outbound)
• The account has a known incumbent to displace (use gtm-competitive-displacement)
• The account is a closed-lost deal (use gtm-closed-loss-reactivation)
• A trigger event just happened (use gtm-trigger-event-outbound)

User Roles: BDR (primary), AE Expected Time: 5 to 10 minutes per account

---

Core Workflow

Step 0: Detect The User Role

Decide whether the user is a BDR or an AE. The role changes the call goal, the summary framing and the owner check.

Read the role from the CRM when it is recorded. If it is not clear, ask: "Are you a BDR or an AE?"

Produces: user_role (BDR or AE)

Step 1: Gather Intelligence

Run the CRM search first, then the research, because the CRM is the record a manager can check. Before pulling anything, open the account's folder under accounts/ in the Knowledge Base, if the profile has one, and offer the CRM read and, when a call recorder is connected, the call read, for the one account or date range you name. Nothing is read from the CRM or the call recorder until you say yes.

1A. Search The CRM. Pull the account record (name, industry, headquarters, website, owner, status), deal history with stages and amounts, every contact with title and last activity, engagement history with dates, and any notes or summaries reps wrote. Note the BDR owner and the account owner.

1B. Research The Company. Build a quick profile from public sources: what the company does, its size signals, its footprint, its ownership, and recent news such as acquisitions, expansions and leadership changes. Tag every fact. Where a fact cannot be found, tag it [Unknown] and write the discovery question that would fill it.

Produces: a list of tagged facts from the CRM and from public sources, and the list of Unknown facts that become discovery questions.

Step 2: Build The Account Snapshot

Build the company brief, the quick-score signals, the zone scores with the verdict, and the region map, in that order. The zones come before any sequence, because the verdict decides whether a sequence is written at all.

Company Brief (5 to 8 bullets): Company (full name and headquarters), Segment (profile: ICP Definitions), Vertical, Size (with its tag), Footprint (regions, locations, key markets), Ownership, CRM Status (TARGET, ENGAGED, INBOUND, ACTIVE with its stage name (profile: Qualification Stage Gates), LOST or OUT), Current owner and BDR owner, and Coordination Required. Coordination is "Yes, coordinate with [AE name]" when the user is a BDR and an AE holds an open deal.

Zone Scores And Verdict: Score the five zones with Step 2's rules, show each zone's score with its tag, and state the verdict from the Verdict Rule. Each verdict names the zones that carry it.

Region Map: Map the account's state to its tier (profile: Outbound Voice), with the tier's source. Name the cost of a missed rule in that tier.

Produces: the company brief, the five zone scores with their tags, the verdict, the account status, and the region tier (or an explicit "no tier yet").

Step 3: Map Contacts To Personas

Map the known CRM contacts to the Buyer Personas (profile: Buyer Personas). For each persona, record the name or Unknown, the title, the engagement level, the last activity and a priority from 1 to 5.

Rank the contacts by four rules, in order: known contacts with engagement history come before cold ones, persona relevance to the likely pain comes next, recent activity counts above old activity, and prior deal context breaks ties. A champion label in the CRM is recorded as a label, tagged [CRM]. The Champion Test in the shared contract decides whether a contact is a champion, and a snapshot does not call a contact Strong on the label alone. The test is the shared list of seven behaviours: three or more met with evidence is Strong, one or two is Developing, and none is None. When the records hold none of the seven behaviours, the Champion Test is reported as not yet run, not as None, because silence is not a no. None is reported only after a call or note has been checked against the seven. A persona applies when the profile's Buyer Personas row allows it for the account's structure. Persona 4 (funeral home owner) applies only where the account runs a funeral side, Persona 5 (CFO or Controller) applies only to a group, and the other personas apply to every account. Rank the applicable personas by who signs first, then by the persona whose hook is a HIGH pain in Step 4 (the hook is read from the Buyer Personas table), then by buying role, with a champion ahead of an influencer. The top three are the first three applicable personas in that ranking, whether or not a contact is on file. For an independent cemetery, that means Personas 1, 2 and 3. Recommend the top two or three personas to target first, with the reason for each. The persona gaps are the top-three personas with no contact on file, plus the economic buyer when the record names who signs but not the person. The signer is the owner when the record names the owner as the approver, even if the GM is the champion. A GM is the signer only when the record says the GM signs. A persona outside the top three is listed as not targeted, not as a gap.

Produces: contact_priority, a ranked list of contacts with persona and buying role, and the persona gaps.

Step 4: Generate Pain Hypotheses

Write from three to five pain hypotheses from the Core Pain Points (profile: Core Pain Points). Show every hypothesis that scores HIGH or MEDIUM, up to five. A LOW hypothesis is shown only to reach three, and the lowest Core Pain Points numbers among the LOW ones fill those slots. For each hypothesis, give:

• Pain Point: the name exactly as the Core Pain Points taxonomy writes it (profile: Core Pain Points). When the hypothesis depends on a dated event, add the event and its date in brackets, for example "Trust fund and records reporting by hand (state review finding, 2026-03-14)" (date illustrative). When the event's date is [Unknown], add "(event date unknown)" and name the event in Why Likely. A hypothesis that depends on no event carries no qualifier.
• Why Likely: the reasoning, with its tag. Every pain hypothesis carries the [Inferred] tag, because it is a reasoned guess from the profile until a call confirms it (Methodology: Evidence Tags For Rapid Research)
• Confidence: HIGH, MEDIUM or LOW, per the confidence rules above
• Discovery Question: the question that validates it on a call
• Value Prop: the value proposition that addresses it (profile: Value Propositions), stated as its mechanism

Order the hypotheses by confidence, HIGH first, and within a level by the Core Pain Points number (profile: Core Pain Points). If every hypothesis is MEDIUM or LOW, say the account needs more research or a discovery call before deeper work.

Produces: pain_hypotheses, ranked, each one tagged, each with its discovery question.

Step 5: Generate The Outbound Sequence

Draft a three-step email sequence for each of the top two or three personas that have a named contact. A persona with no named contact gets no sequence yet: finding the name is its gap, and the summary says so. A snapshot is the fast first pass, so it writes only to people a rep can reach today, while Research Outbound (03) drafts by title for its deeper package. What is drafted depends on the verdict, and on whether the account is already in conversation.

• GREENLIGHT: a ready sequence. The rep reads it, edits it if needed and sends it.
• MANUAL REVIEW: a held package. Its first line reads "Held: send only after a person clears the verdict", and nothing in it goes out before then.
• DISQUALIFY: no sequence. The report says so. An INBOUND account gets one decline draft, as the INBOUND paragraph below describes.

Quick Call Prep mode drafts none, whatever the verdict, except the decline draft for an INBOUND DISQUALIFY, which still answers the request.

ENGAGED Accounts replied or met with us, and no deal is open. They get no cold sequence, because the account is already talking to us, and three cold emails would restart the outreach it has answered. Step 5 drafts one reply to the open thread instead. The reply answers what the account said, cites the date and tag of that message, follows every rule below, and is ready or held by the verdict in the same way. The sequence comes after the pain hypotheses, because each email uses one hypothesis, so the ranked list must exist first.

INBOUND Accounts asked us first, and no deal is open. The request is answered before any cold touch, so Step 5 drafts one reply to the request instead of a sequence. The reply answers what they asked, carries this skill's angle (the pain hypothesis that ranks first in Step 4, in the words of the request where the request names it), follows every rule below, and is ready or held by the verdict in the same way. A sequence follows only if the account goes quiet, as What The Close Reads defines it. The sequence is then drafted from the same ranked hypotheses, and its Email 1 refers back to the request instead of restarting the outreach. A DISQUALIFY account gets no sequence. An INBOUND account with a DISQUALIFY verdict gets one short decline draft instead, in place of the reply: not a fit right now, the reason in one line, and an open door if that reason changes. The rep reads it before anything goes out. It follows the rules for every email below for length and claims, at 100 words or fewer, with no [Inferred] or [Unknown] fact as a claim.

Rules For Every Email:

• Include a subject line.
• Keep the body to 100 words or fewer.
• Open with something specific to the company, tagged [CRM] or [Public: source].
• Use the contact's name when it is known.
• Give each step a different pain or angle.
• Use only [CRM], [Call], [Notes] and [Public: source] facts as claims. Write [Inferred] and [Unknown] facts as questions.
• Use at most one proof point per email, from the Proof Points table (profile: Proof Points), matched to the segment and the persona. Never use an Illustrative result, because a prospect who asks for its source gets none. A Benchmark is cited with the source named.

Sequence Structure (Per Persona):

Account Snapshots use three steps, not four, because this is volume outreach.

Produces: sequence, one three-step set per persona, drafted, with each claim's tag listed beneath the draft.

Step 6: Build The Call Prep Sheet

Role-Aware Call Goal:

Next Step After A First Call: a discovery call, not a demo, until the pain is confirmed. A demo asks the buyer for an hour before there is a reason to give it.

Opener (30 Seconds): "Hi [name], this is [rep] from [company]. I'm calling because [a specific reason tied to pain hypothesis 1]. Do you have 30 seconds?"

For an ENGAGED account, the opener refers to the account's own reply, by its date and tag, and not to a cold reason. For an INBOUND account, the opener refers to the request, by its date and tag, and not to a cold reason.

Talk Track: a pain validation question, an impact question, a one-sentence product bridge, and an ask for 15 minutes.

Voicemail (Under 30 Seconds): name and company, one specific statement, and the call to action "I'll send a quick email with details."

Objections: Use the Competitive Landscape (profile: Competitive Landscape) for competitive objections. Include four to five objections with rebuttals tailored to the account.

Produces: the call goal, the opener, the talk track, the voicemail and the objection table, all tied to the ranked pain hypotheses.

Step 7: Assemble The Cheatsheet And Summary

Assemble the eight cheatsheet sections in this order: Company Snapshot, Geographic and Market Exposure, Key Personas, Pain Hypotheses, Discovery Questions, Value Props, Objection Handling and Call Flow.

Close with a summary line in this order: the user's role, the account, the status, the verdict with the zones that carry it, the contacts found and their gaps, the personas targeted, the number of sequence emails, the next_action, and the tag count for the report. The next_action is the first step in the priority order in the Output Contract that applies to this account, with its owner and its date under the shared contract's next-action rule (five business days after the run date, or an earlier date the records or the skill's own schedule set for that step). Every ask to that same person that is due on or before the next action's date stays with it in the same message, counts and figures included. A document the person must draft or research first is a later step, and so is any ask due after that date. A step for a different person, or with a later date, is named after it as a later step. The order, not the rep's own preference, decides which step comes first.

Produces: the eight-section cheatsheet in the chat, the summary line, and next_action.

---

Modes

• Full Snapshot (default). Steps 0 to 7, all eight cheatsheet sections, and the sequence. Use it for a single account the rep will work this week.
• Quick Call Prep. Steps 1 to 4 and Step 6 only. Skip the sequence. Use it when the rep says "quick call prep" or "calling in five minutes," because speed matters more than completeness before a call.
• Batch. Steps 1 to 4 for each account, then a ranked summary table. Full sequences for the top two or three accounts only, ready for GREENLIGHT and held for MANUAL REVIEW. Use it for five to ten accounts in one prospecting block.

No mode writes a file. A file is written only when the user asks for one, under the Output Contract.

---

Epistemic Rules

• Print N Beside Every Rate. "4 of 7 criteria" is readable. "57%" alone is not, because the reader cannot tell whether it rests on four cases or four hundred.
• Five Cases Before A Pattern. A pattern across accounts needs at least five cases. Fewer cases are an observation, and the summary says so in the same sentence.
• Silence Is Not A No. A blank CRM field is Unknown, and it counts in no denominator. Scoring it as a no invents a finding out of missing data.

---

Hard Rules

1. Never cite an Illustrative proof point, and never use a proof point the profile does not list. A prospect who asks for the source of an Illustrative result gets nothing, and the rep loses the buyer's trust in the first email.
2. Never use an [Inferred] or [Unknown] fact as the claim in an email. A guess written as a claim is something the rep must defend on the call, so it goes in as a question.
3. Never score silence as a no, and never score UNKNOWN as LOW. A blank field may mean nobody recorded it, and a LOW score moves the verdict.
4. Never Override The Verdict Rule. MEDIUM never counts as HIGH, because the next skill reads these zones, and a score that rounds up changes its verdict.
5. Never work an ACTIVE account with an AE owner unless that AE has said yes. Two people writing to one buyer costs the deal, and the buyer sees the duplicate.
6. Never propose a demo as the next step while the pain is unconfirmed. A demo asks the buyer for time before there is a reason to give it.
7. Never send an email, enroll a contact or write to the CRM. The rep reads the draft and sends it, because the rep owns the relationship and the record.
8. Never write an outcome number without its source or its Illustrative mark. An unsourced figure in an email becomes the first question the buyer asks.
9. Never Use A Tag Outside The Six. A manager checks the report by tag, and a seventh label cannot be checked.
10. Never let a held package go out before a person clears the verdict. Reason: a MANUAL REVIEW account has open gaps, and a draft that reads as ready invites a send before the gaps close.
11. Never send a cold three-step sequence to an ENGAGED account. Reason: the account has already answered, and a cold sequence reads as not listening.
12. Never send a cold sequence to an INBOUND account before its request is answered. Reason: the account asked us first, so a cold sequence ignores the open request. A sequence follows only once the account goes quiet.
13. A DISQUALIFY gets no sequence, and an INBOUND DISQUALIFY gets one decline draft. Reason: the buyer asked us first, so the request still deserves a courteous answer, but a sequence to an account that cannot buy spends a touch the rep needs elsewhere.

---

Quality Bar

Done when all are true:

• Every fact carries one of the six tags, and no fact is left untagged
• The verdict follows the Verdict Rule, with the zones that carry it named beside it
• Every zone score carries its tag, and no UNKNOWN zone is scored LOW
• The account status is one of the six words, and an ACTIVE status carries its stage name (profile: Qualification Stage Gates)
• The owner check ran, and an AE-owned account is named as coordination, not worked
• Every Email 1, and the reply draft for an ENGAGED account or for an INBOUND request, opens with a specific, tagged company fact
• A MANUAL REVIEW set is marked Held on its first line, and Quick Call Prep drafts none
• An INBOUND account has one reply to its request, carrying the skill's angle, and no cold sequence unless the account has gone quiet
• A DISQUALIFY on an INBOUND account has one short decline draft, held for the rep, and no sequence
• Every email is 100 words or fewer, and no email uses an [Inferred] or [Unknown] fact as a claim
• Every proof point in an email is in the Proof Points table (profile: Proof Points) and is not Illustrative
• The call goal matches the user's role, and no demo is proposed before the pain is confirmed
• Each rate carries its n, and each pattern rests on five cases or is labelled an observation
• Every pain hypothesis carries the [Inferred] tag and a Core Pain Points name, with its event qualifier when it depends on a dated event
• The next action is the first step that applies in the Output Contract's priority order, with one owner, one person and one date
• The hand-off block lists every field by name, with its value

---

Examples

These examples use the PlotIQ example cast, and every fact is tagged as the tag set requires. A number the profile does not supply is marked (illustrative). The five examples cover a BDR research pass that leads to outbound, an AE quick call prep that ends in MANUAL REVIEW, a batch with a disqualified account and a closed-lost one, the flagship account at its first snapshot, and an ENGAGED account with its one reply draft. Each ends with a hand-off block.

Example 1: BDR Account Snapshot (Quill Hollow Memorial Park, TARGET, GREENLIGHT)

Context: A BDR prepares a first outbound touch during a morning block. The general manager, Ines Carmody, moved to Quill Hollow from Lowmoor Memorial Gardens six months ago [Public: state licensing database] (illustrative). Her history at Lowmoor is a closed-loss matter for Closed-Loss Reactivation (05), not this outbound.

Input: "Account snapshot on Quill Hollow Memorial Park, with outbound sequences and a cheatsheet."

Step 0: Role Detection. The user is a BDR. The CRM shows the account, status TARGET [CRM], and no open deal [CRM]. Clear to proceed.

Step 1: Intelligence Gathering. One site, 8,800 plots, paper plat maps [CRM]. One contact on file: Ines Carmody, General Manager, champion [CRM]. The approver of record is the owner [CRM] (illustrative). The owner's name is [Unknown]. A records finding appears in the last state review [CRM], and its date is [Unknown] (both illustrative). The owner brought a growth mandate when Ines Carmody arrived [CRM]. The state is not recorded [Unknown], so no region tier yet. The BDR owner is Nadia Brandt [CRM] (illustrative).

Step 2: Account Snapshot.

Company brief: Quill Hollow Memorial Park. Independent cemetery [CRM]. One site, 8,800 plots [CRM]. Ownership [Unknown]. CRM status TARGET. No active deal.

Quick-score signals: primary fit Partial. The plot records are on paper [CRM], which meets part of the ICP1 key indicator, and the annual state filing is [Unknown] because the state is not recorded. Single region [CRM]. Regulatory complexity High, because of the records finding [CRM]. Scale Mid-Market, one site with 8,800 plots [CRM], which meets the Mid-Market rule of one to three sites with 2,000 plots or more in total. Team complexity: Small team, one named contact (the GM) [CRM], and the owner has no name [Unknown].

Zone scores (illustrative), with the verdict:

• Zone 1, Records and Inventory Pain: MEDIUM. Paper plat maps [CRM]. The records finding has no date [Unknown], so the HIGH test (a finding in the last 24 months) is not met.
• Zone 2, Pre-Need Sales Motion: UNKNOWN. No pre-need activity is recorded [Unknown]. Silence is not a no.
• Zone 3, Ownership and Decision Speed: HIGH. The approver of record is the owner [CRM] (illustrative). The year-one cost at one site is $15,788, under $25K [Inferred: arithmetic] (profile: Product Modules), and the board condition cannot apply to an owner who approves, so it counts as met.
• Zone 4, Technology Readiness: UNKNOWN. Website and tools are not yet checked [Unknown].
• Zone 5, Growth or Succession: HIGH. A new GM in the last 24 months [CRM] (illustrative) meets the HIGH column. The owner's growth mandate [CRM] is context, not a second condition.

Verdict: GREENLIGHT. Two zones are HIGH (3 and 5), and no must-have zone is LOW. Zone 1 is MEDIUM, which blocks nothing. If the finding is dated inside 24 months, Zone 1 becomes HIGH, so the date is the first thing to find.

Region map: no tier, because the state is not recorded [Unknown].

Step 3: Contact Mapping.

Ines Carmody ranks first. She is the only named contact and runs the site now, and Persona 1's hook matches the HIGH pain. No persona signs, because the owner is the approver, so the signing rule ranks no one. The pre-need manager (Persona 2) and the Operations Director (Persona 3) follow. Neither hook is a HIGH pain, so the champion ranks ahead of the influencer. Both have no contact on file, so both are gaps, and the owner is the economic buyer gap. Her champion label stays a label until the Champion Test runs.

Step 4: Pain Hypotheses.

1. Plot Records On Paper, Binders Or Pencil Maps. HIGH confidence. Both tests are met: the trait, plot records on paper [CRM], and the setting, a cemetery site (profile: Core Pain Points, row 1). [Inferred], by reasoning from the record type: a paper map cannot show which plots are sold without a walk of the grounds. Discovery question: "How do you check today which plots are open?" Value prop: plot inventory matched against sold records.
2. Trust fund and records reporting by hand (event date unknown). LOW confidence. [Inferred]. The last state review found a records problem [CRM], and its date is [Unknown]. The trait test is not met, because no trust fund or state records reporting done by hand is on record. The paper plat maps [CRM] show plot records, which is row 1's trait, not row 2's. The setting test is not met, because the annual state filing that the row names is not on record: the state is [Unknown]. The undated finding counts toward neither test, so the hypothesis stays LOW and takes the qualifier. The finding is a discovery question only, and no email or call opener uses it. Discovery question: "When was the last state review, and what did it ask you to fix?" Value prop: plot and trust records a state auditor accepts (profile: Value Propositions, Value Proposition 2).
3. Plot Lookups Take Minutes To Hours. LOW confidence. [Inferred]. The trait test is not met: no lookup time is on record, and a paper map is the means of a lookup, not a measure of its length. The row names no setting, so the setting test cannot be met. It is shown to fill the third slot, the next lowest number after pain 2 (profile: Core Pain Points, Pain 3). Pain 4 (pre-need leads go cold) is LOW, because pre-need activity is [Unknown], and pain 5 is LOW with nothing on record, so neither is shown. Discovery question: "When a family asks about a plot, how long does the lookup take?" Value Prop: a plot answer in seconds (profile: Value Propositions, Value Proposition 3).

Step 5: Sequence (Ines Carmody, General Manager).

Email 1

Subject: Your move to Quill Hollow and the plot maps

Ines,

You took over Quill Hollow in April 2026, and the plot maps here are still on paper. How do you check today which plots are sold and which are open?

Worth 15 minutes to walk through how your plot maps and your sold records line up?

Claim tags for Email 1: the April 2026 move [Public: state licensing database], and the paper plot maps [CRM].

Email 2

Subject: Sold plots and the plot map

Ines,

Since you took over Quill Hollow in April 2026, the plot maps have stayed on paper. When a family asks for a sold plot, how long does your team take to show the record?

Would 15 minutes next week be worth it to see whether your sold records and your plot maps line up?

Claim tags for Email 2: the April 2026 move [Public: state licensing database], and the paper plot maps [CRM].

Email 3

Subject: Should I close the file?

Ines,

I have not heard back, so I will assume plot records are not a priority this quarter, and I will stop the emails after this one.

If a state auditor asked for a plot record next month, who on your team would pull it?

The emails name no proof point. The research figure for this pain (50 to 100 plots) is a pain Benchmark (profile: Core Pain Points), not a row in the Proof Points table (profile: Proof Points), and every PlotIQ result is Illustrative, so Hard Rule 1 leaves all three emails with none.

Step 6: Call Prep.

Call goal: book a 15-minute discovery call for the AE, with the records finding as the reason. The next step is a discovery call, not a demo, until the pain is confirmed.

Opener: "Hi Ines, this is Nadia Brandt from PlotIQ. I'm calling because you took over Quill Hollow in April 2026, and the plot maps are still on paper. Do you have 30 seconds?"

Talk track:

• Pain validation: "How do you check today which plots are open?"
• Impact: "When a family asks for a sold plot, how long does the lookup take?"
• Discovery question on the records finding: "When was the last state review, and what did it ask you to fix?"
• Product bridge: "PlotIQ keeps plot and trust records in a form a state auditor can accept."
• Ask: "Would 15 minutes with our account executive be worth it?"

Voicemail: "Hi Ines, this is Nadia Brandt at PlotIQ, about the plot maps at Quill Hollow. I'll send a quick email with details."

Step 7: Summary. BDR. Quill Hollow Memorial Park, TARGET, GREENLIGHT, with Zones 3 and 5 HIGH. One contact on file, Ines Carmody, first. Gaps: the pre-need manager and the Operations Director (Personas 2 and 3, no contact), and the owner, the economic buyer. One persona, three emails. Next action: Nadia Brandt sends Email 1 to Ines Carmody by 2026-10-26 (five business days after the run date of 2026-10-19, a Monday, and the records set no earlier date for this step). Open questions for the call that Email 1 asks for: the records finding date, the owner's name and the state. They are asked on that call, which comes after the send, so they are a later step listed after the next action, not part of it.

Hand-off (read by 06):
account: Quill Hollow Memorial Park (TARGET)
run_date: 2026-10-19
account_status: TARGET
verdict: GREENLIGHT
zone_scores: 1 MEDIUM, 2 UNKNOWN, 3 HIGH, 4 UNKNOWN, 5 HIGH (illustrative)
contact_priority: 1 Ines Carmody (General Manager, champion), 2 Pre-need manager, name Unknown (gap), 3 Operations Director, name Unknown (gap), signer: owner, name Unknown (economic buyer gap)
pain_hypotheses: 1 Plot records on paper, binders or pencil maps (HIGH, Inferred), 2 Trust fund and records reporting by hand (event date unknown) (LOW, Inferred), 3 Plot lookups take minutes to hours (LOW, Inferred)
sequence: three emails to Ines Carmody, with call prep
report_path: none (inline)
next_action: Nadia Brandt sends Email 1 to Ines Carmody by 2026-10-26

---

Example 2: AE Quick Call Prep (Sable Fork Cemetery, INBOUND, MANUAL REVIEW)

Context: Thursday 2026-10-22. Owen Pruitt, the AE, has 20 minutes before a discovery call. Sable Fork Cemetery filled in the website form on 2026-10-15, a week ago, asking for a demo. The BDR replied on 2026-10-19 and booked this call for today [CRM]. The general manager, Arlen Biggs, signs under $25K. The reply to the request is already sent, on 2026-10-19 [CRM], so the INBOUND reply step is done, and Quick Call Prep drafts no sequence in any case.

Input: "Quick call prep for Sable Fork Cemetery. They requested a demo from the website."

Step 0: Role Detection. The user is an AE. Quick Call Prep mode: Steps 1 to 4 and Step 6 only.

Step 1: Intelligence Gathering. The CRM holds a new record created from the form [CRM], status INBOUND [CRM], no open deal [CRM], and a discovery call with Arlen Biggs booked for 2026-10-22 [CRM]. Who filled in the form is [Unknown]. The search that led to the form is [Unknown]. One site, 2,900 plots [CRM]. The plot list is a spreadsheet [CRM]. The general manager, Arlen Biggs, signs under $25K [CRM].

Step 2: Account Snapshot. Status INBOUND.

Quick-score signals: primary fit Partial. The plot list is a spreadsheet [CRM], which meets part of the ICP1 key indicator, and the annual state filing is [Unknown] because the state is not recorded. Single site [CRM]. Regulatory complexity Unknown, because nobody has asked about a state finding [Unknown]. Scale Mid-Market, one site with 2,900 plots [CRM], which meets the Mid-Market rule of one to three sites with 2,000 plots or more in total. Team complexity Small team, one named contact (the GM) [CRM], and no records owner named [Unknown].

Zone scores (illustrative): Zone 1 MEDIUM (plot list in a spreadsheet [CRM]). Zone 2 LOW (pre-need: none, and the GM sells plots directly [CRM]). Zone 3 HIGH (the GM signs under $25K [CRM]). Zone 4 MEDIUM (illustrative). Zone 5 LOW (plot sales flat for three years, and no succession plan on the record [CRM], illustrative).

Verdict: MANUAL REVIEW. One zone is HIGH (Zone 3), so GREENLIGHT does not hold. The Verdict Rule gives MANUAL REVIEW for one HIGH zone. A MANUAL REVIEW does not authorize outbound.

Region map: no tier, because the state is not recorded [Unknown].

Step 4: Pain Hypotheses.

1. Plot Records On Paper, Binders Or Pencil Maps. MEDIUM confidence. [Inferred]. The setting test is met, because the operator is a cemetery site [CRM]. The trait test is not met, because the plot list is a spreadsheet, not paper, binders or pencil maps [CRM]. Discovery question: "Where does the plot list live today, and when was it last updated?"
2. Trust Fund And Records Reporting By Hand. LOW confidence. [Inferred]. The trait test is not met: the plot list is a spreadsheet [CRM], which is plot records, not trust reporting done by hand, and no trust filing is on record. The setting test is not met, because no annual state filing is on record and the state is [Unknown]. Discovery question: "Walk me through last year's trust filing. Who pulled the numbers, and from where?"
3. Plot Lookups Take Minutes To Hours. LOW confidence. [Inferred]. No lookup time is on record (Zone 1 notes that lookup time is not measured), so the trait test is not met. The row names no setting, so the setting test cannot be met. It is shown only to fill the third slot. Discovery question: "When someone asks for a plot, how long does it take to find it today?"

Pre-need leads are not shown. The record says pre-need is none [CRM], so the pre-need sales line the setting test needs is absent, the trait is ruled out, and the pain is LOW with three slots already filled.

Step 6: Call Prep.

Call goal: confirm the pain, measure a real plot lookup, and find out who signs under $25K. This call is discovery, not a demo, and the demo waits until the pain is confirmed.

Opener: "Thanks for asking for a demo. Before I show you anything, what prompted you to look for plot records software this week?"

Talk track:

• "When someone asks for a plot, how long does it take to find it today?"
• "How many plots do you think are open right now, and how would you check?"
• "Do you sell pre-need, and where do those leads go when they come in?"
• "Who signs off on a purchase under $25K, and does anyone else need to see it?"

Objection prep: "We're happy with the spreadsheet." Rebuttal: "That makes sense. When did you last check the spreadsheet against the plots you have actually sold?"

Step 7: Summary. AE. Sable Fork Cemetery, INBOUND, MANUAL REVIEW, with Zone 3 the only HIGH zone. No active deal. Quick call prep delivered. The order gives this next action. No reply is owed (the INBOUND reply went on 2026-10-19 [CRM]), no account is ACTIVE with an AE owner, and Quick Call Prep drafts no send, so the meeting on the calendar is the first step that applies. Next action: Owen Pruitt runs the discovery call with Arlen Biggs today, 2026-10-22, the call date the records set for this step, which is earlier than five business days after the run date. Later step: re-score the zones after the call.

Hand-off (read by 06 and 04):
account: Sable Fork Cemetery (INBOUND)
run_date: 2026-10-22
account_status: INBOUND
verdict: MANUAL REVIEW
zone_scores: 1 MEDIUM, 2 LOW, 3 HIGH, 4 MEDIUM, 5 LOW (illustrative)
contact_priority: 1 Arlen Biggs (General Manager, signs under $25K), 2 Form filler, name Unknown
pain_hypotheses: 1 Plot records on paper, binders or pencil maps (MEDIUM, Inferred), 2 Trust fund and records reporting by hand (LOW, Inferred), 3 Plot lookups take minutes to hours (LOW, Inferred)
sequence: none, Quick Call Prep mode. The request reply went on 2026-10-19 `[CRM]`, so no INBOUND reply is outstanding
report_path: none (inline)
next_action: Owen Pruitt runs the discovery call with Arlen Biggs on 2026-10-22 (the call date on record)

---

Example 3: BDR Batch (Prospecting Block, Five Accounts, Mixed Outcomes)

Context: A BDR has a two-hour prospecting block and needs snapshots for five accounts, so the best two or three can be worked in depth. The list mixes stages and verdicts on purpose, so the table shows what the batch does with each one.

Input: "Quick snapshots on these five accounts for my outbound block: Corrow Ridge Cemetery, Greyfield Memorial Park, Tamsin Vale Cemetery, Northvale Memorial Holdings and Lowmoor Memorial Gardens."

Batch Mode. Steps 1 to 4 for each account, then this ranked table. Zone scores are illustrative. The table shows the zones that carry each verdict.

Recommendation. Corrow Ridge gets a ready snapshot sequence, one persona, in the batch run. Tamsin Vale is MANUAL REVIEW, so it gets a held package, marked Held, which no one sends until a person clears the verdict. Greyfield gets no snapshot sequence, because Competitive Displacement (12) already holds its sequence, and a second one would be a duplicate. This block shows the rows and the hand-off, not the emails. Trigger Event Outbound (04) writes the sharper Corrow Ridge sequence from its own inputs, so the snapshot draft is a first draft. Send Lowmoor to Closed-Loss Reactivation (05), because it is a closed-lost account and not a cold prospect. Drop Northvale from the queue.

Hand-off (read by 06):
account: five accounts, one row each in the batch table above
run_date: 2026-10-19
account_status: TARGET for Corrow Ridge, Greyfield and Tamsin Vale. LOST for Lowmoor. OUT for Northvale
verdict: GREENLIGHT (Corrow Ridge, Greyfield), MANUAL REVIEW (Tamsin Vale, Lowmoor re-scored), DISQUALIFY (Northvale)
contact_priority: Corrow Ridge, the acquirer's CFO or controller and the site GM. Greyfield, the pre-need team, no names on file. Tamsin Vale, signer Unknown
pain_hypotheses: ranked per account in the table, each tagged
sequence: ready snapshot draft for Corrow Ridge, held package for Tamsin Vale (MANUAL REVIEW), none for Greyfield (Competitive Displacement holds its sequence), Lowmoor or Northvale
report_path: none (inline)
next_action: BDR sends the Corrow Ridge Email 1 by 2026-10-20 (the first send of a GREENLIGHT sequence, which ranks first in the order). Tamsin Vale's held package and the other rows are later steps

---

Example 4: Flagship Account Snapshot (Brackhaven Memorial Gardens, TARGET, GREENLIGHT)

Context: A snapshot run the week the flagship was qualified, on 2026-05-04 (illustrative). At that point the account was TARGET, with no open deal, and the general manager was already on file as the buyer. This is the first snapshot in the PlotIQ chain, and its hand-off feeds the meeting prep for the first discovery call.

Input: "Account snapshot on Brackhaven Memorial Gardens, before our first outreach."

Step 0: Role Detection. The user is a BDR. CRM status TARGET [CRM], no open deal [CRM]. Clear to proceed.

Step 1: Intelligence Gathering. Two sites, 11,000 plots [CRM]. Paper plot maps [CRM]. A combination of cemetery and funeral home [CRM]. One double sale in the last 24 months [CRM] (illustrative). The incumbent is Oldgate Ledger Pro, direct software, with a renewal in March 2027 [CRM]. The general manager is Ruth Ellery [CRM]. The family board is the decision body [Notes] (illustrative). The board chair's name is [Unknown].

Step 2: Account Snapshot.

Company brief: Brackhaven Memorial Gardens. Combination, two sites [CRM]. 11,000 plots [CRM]. Paper plot maps [CRM]. Family-owned, with a family board [Notes] (illustrative). CRM status TARGET. No active deal.

Quick-score signals: primary fit Yes, a combination with 11,000 plots [CRM]. Two sites [CRM]. Regulatory complexity Medium [Notes] (illustrative). Scale Mid-Market, two sites with 11,000 plots [CRM], which meets the Mid-Market rule of one to three sites with 2,000 plots or more in total. Team complexity Dedicated team, three named contacts [CRM].

Zone scores (illustrative), with the verdict:

• Zone 1, Records and Inventory Pain: HIGH. Paper plot maps at two sites [CRM], and a double sale in the last 24 months [CRM] (illustrative).
• Zone 2, Pre-Need Sales Motion: MEDIUM. A pre-need manager runs the pre-need side [Notes] (illustrative). The intake form is [Unknown], so the HIGH test is not met.
• Zone 3, Ownership and Decision Speed: MEDIUM. The GM recommends and the family board approves, which is the MEDIUM cell as written (profile: Qualification Zones). The board also meets within 60 days [Public: company website, board calendar] (illustrative).
• Zone 4, Technology Readiness: MEDIUM. A legacy system from Oldgate [CRM].
• Zone 5, Growth or Succession: HIGH. The owner retires within three years [Public: company website, owner bio, 2026] (illustrative).

Verdict: GREENLIGHT. Two zones are HIGH (1 and 5), and no must-have zone is LOW. Zone 3 is MEDIUM, which is not LOW, so the must-have does not block.

Region map: the state is not in the example notes [Unknown], so no tier is assigned here.

Step 3: Contact Mapping.

The family board chair is recorded as a gap, not as a person: no name is on file [Unknown].

Step 4: Pain Hypotheses.

1. Plot Records On Paper, Binders Or Pencil Maps. HIGH confidence. Paper plot maps at both sites [CRM]. [Inferred], by reasoning from the record type: two sites on paper mean two lists, so a sale on one list can be missed on the other. Discovery question: "Which site's plot list do your staff check first?"
2. Pre-Need Leads Go Cold. MEDIUM confidence. [Inferred]. The setting test is met: a pre-need manager runs the pre-need side [Notes] (illustrative), so pre-need sales is a line this account runs. The trait test is not met, because no lead that went cold is on record and the intake form is [Unknown]. One test met gives MEDIUM. Discovery question: "When a pre-need lead comes in from the website, who calls them back, and when?" Value prop: pre-need leads worked within an hour (profile: Value Propositions, Value Proposition 4).
3. Trust Fund And Records Reporting By Hand. LOW confidence. [Inferred]. The trait test is not met: the plot records are kept on paper maps [CRM], which is row 1's trait, and no trust reporting done by hand is on record. The setting test is not met, because the state, and so any annual state filing, is [Unknown]. The Oldgate renewal in March 2027 [CRM] is an angle for Email 2, not a pain. Discovery question: "Walk me through last year's trust filing. Who pulled the numbers, and from where?" Value prop: plot and trust records a state auditor accepts (profile: Value Propositions, Value Proposition 2). Plot lookups (profile: Core Pain Points, Pain 3) is also LOW and is not shown, because the lowest-numbered LOW hypothesis, this one, fills the last slot.

Step 5: Sequence (Ruth Ellery, General Manager).

Email 1

Subject: Two sites, one plot list

Ruth,

Brackhaven runs two sites, and the plot maps at both are still on paper. How do you find a plot that is sold on one map and open on the other?

Most cemeteries your size carry 50 to 100 plots that are sold on paper but open on the map (Benchmark, deathcare research, paper-operations note, 2026-04-01). Worth 15 minutes to see whether your two sites show the same gap?

Email 2

Subject: The Oldgate renewal and two plot lists

Ruth,

Brackhaven's Oldgate license renews in March 2027 [CRM]. When a renewal comes up, which date do you plan around: the renewal itself, or the first board meeting after it?

Would a 15-minute call before March help you compare the two plot lists?

Email 3

Subject: Should I close the file?

Ruth,

I have not heard back, so I will stop the emails after this one. If the two plot lists were ever checked against each other, who at Brackhaven would do it?

The emails name no customer result, because the Brackhaven result is Illustrative and not yet signed (profile: Proof Points).

Step 6: Call Prep.

Call goal: book a 15-minute discovery call for the AE, Owen Pruitt, with Ruth Ellery. The next step is a discovery call, not a demo, until the two-site pain is confirmed.

Opener: "Hi Ruth, this is Nadia Brandt from PlotIQ. I'm calling because Brackhaven runs two sites, and the plot maps at both are still on paper. Do you have 30 seconds?"

Talk track:

• Pain validation: "Which site's plot list do your staff check first?"
• Impact: "How do you find a plot that is sold on one map and open on the other?"
• Competitive question: "What happens at the Oldgate renewal, and who decides?"
• Ask: "Would 15 minutes with Owen Pruitt be worth it?"

Voicemail: "Hi Ruth, this is Nadia Brandt at PlotIQ, about the two plot maps at Brackhaven. I'll send a quick email with details."

Step 7: Summary. The summary states the verdict, the two HIGH zones, the three contacts, and the next action. Email 1 is the first send of a GREENLIGHT sequence, so it ranks first in the order. Nadia Brandt, the BDR, sends Email 1 to Ruth Ellery by 2026-05-11 (illustrative), five business days after the run date of 2026-05-04, a Monday, and the records set no earlier date for this step. Email 1 asks for 15 minutes with Owen Pruitt, so booking the call is the email's ask, not a separate step. The board chair is the open question for that call, and it is a later step.

Hand-off (read by 06):
account: Brackhaven Memorial Gardens (TARGET at the time of the snapshot)
run_date: 2026-05-04 (illustrative, the day of the qualification)
account_status: TARGET
verdict: GREENLIGHT
zone_scores: 1 HIGH, 2 MEDIUM, 3 MEDIUM, 4 MEDIUM, 5 HIGH (illustrative)
contact_priority: 1 Ruth Ellery (General Manager, buyer), 2 Walt Okonkwo (Operations Director, influencer), 3 Priscilla Dunmore (pre-need manager, end user)
pain_hypotheses: 1 Plot records on paper across two sites (HIGH, CRM and Inferred), 2 Pre-need leads go cold (MEDIUM, Inferred), 3 Trust fund and records reporting by hand (LOW, Inferred)
sequence: three emails to Ruth Ellery, with call prep
report_path: none (inline)
next_action: Nadia Brandt sends Email 1 to Ruth Ellery by 2026-05-11, asking for 15 minutes with Owen Pruitt (illustrative)

---

Example 5: ENGAGED Account, One Reply Draft (Quill Hollow Memorial Park, ENGAGED, GREENLIGHT)

Context: Wednesday 2026-10-28, the day after Ines Carmody replied to Email 1 on 2026-10-27 [CRM] (illustrative). On the same record she booked a call for Monday 2026-11-02 [CRM] (illustrative). That call is the discovery call that Meeting Prep (06), Example 4, prepares. Quill Hollow is ENGAGED, because the account replied and no deal is open. Email 1 is the one in Example 1, with the subject "Your move to Quill Hollow and the plot maps". Its send date is not in the records [Unknown], and the reply cites Email 1 by the date of her reply.

Input: "Ines Carmody replied to our first email and booked a call for November 2. What do I send before then?"

Step 0: Role Detection. The user is a BDR, Nadia Brandt [CRM] (illustrative). The CRM shows status ENGAGED [CRM], the reply of 2026-10-27 [CRM] and no open deal [CRM]. The BDR guard does not apply, because the account is not ACTIVE. The ENGAGED path applies: one reply draft, and no cold sequence.

Step 1: Intelligence Gathering. One site, 8,800 plots, paper plat maps [CRM] (illustrative). One contact on file: Ines Carmody, General Manager, champion label [CRM]. She moved to Quill Hollow from Lowmoor Memorial Gardens six months ago [Public: state licensing database] (illustrative). The approver of record is the owner [CRM] (illustrative). The owner's name is [Unknown]. A records finding appears in the last state review [CRM], and its date is [Unknown] (illustrative). The owner brought a growth mandate when Ines Carmody arrived [CRM]. The state is [Unknown], so there is no region tier yet. The new records are the reply of 2026-10-27 and the booked call of 2026-11-02, both [CRM] (illustrative).

Step 2: Account Snapshot.

Company brief: Quill Hollow Memorial Park. Independent cemetery [CRM]. One site, 8,800 plots [CRM]. CRM status ENGAGED. No open deal.

Zone scores (illustrative), with the verdict. The reply adds no zone fact, and the verdict does not change with status, so the zones read as they did in Example 1:

• Zone 1, Records and Inventory Pain: MEDIUM. Paper plat maps [CRM]. The records finding has no date [Unknown], so the HIGH test (a dated finding inside 24 months) is not met (profile: Qualification Zones).
• Zone 2, Pre-Need Sales Motion: UNKNOWN. No pre-need activity is recorded [Unknown]. Silence is not a no.
• Zone 3, Ownership and Decision Speed: HIGH. The approver of record is the owner [CRM] (illustrative). The year-one cost at one site is $15,788, under $25K [Inferred: arithmetic] (profile: Product Modules), and the board condition cannot apply to an owner who approves, so it counts as met.
• Zone 4, Technology Readiness: UNKNOWN. Website and tools are not checked [Unknown].
• Zone 5, Growth or Succession: HIGH. A new GM in the last 24 months [Public: state licensing database] (illustrative) meets the HIGH column. The growth mandate is context, not a second condition.

Verdict: GREENLIGHT. Zones 3 and 5 are HIGH, and no must-have zone is LOW. Zone 1 is MEDIUM, which blocks nothing (profile: Qualification Zones, Verdict Rule). The UNKNOWN zones 2 and 4 are named as open facts, and they neither earn nor block GREENLIGHT.

Region map: no tier, because the state is [Unknown].

Step 3: Contact Mapping.

Ines Carmody ranks first, because she is the only named contact, she replied, and she runs the site now. The Champion Test counts seven behaviours. The dated booking is one of them, "commits to next steps with dates" [CRM] (illustrative), so one is met, and the status reads Developing (one or two met). The other six are not on record, so she is not Strong, and her champion label stays a label.

Step 4: Pain Hypotheses. The reply adds no pain fact, so the three hypotheses are Example 1's, ranked by confidence and then by Core Pain Points number (profile: Core Pain Points):

1. Plot Records On Paper, Binders Or Pencil Maps. HIGH confidence. Paper plat maps [CRM]. [Inferred], reasoned from the record type: a paper map cannot show which plots are sold without a walk of the grounds. Discovery question: "How do you check today which plots are open?" Value prop: plot inventory matched against sold records (profile: Value Propositions).
2. Trust fund and records reporting by hand (event date unknown). LOW confidence. [Inferred]. The last state review found a records problem [CRM], and its date is [Unknown]. Neither test is met, because no trust reporting done by hand is on record and the state, so any annual state filing, is [Unknown]. The undated finding counts toward neither test, so the hypothesis stays LOW. The finding is a discovery question only, never the hook. Discovery question: "When was the last state review, and what did it ask you to fix?"
3. Plot Lookups Take Minutes To Hours. LOW confidence. [Inferred]. No lookup time is on record, so the trait test is not met, and the row names no setting. It is shown only to fill the third slot (profile: Core Pain Points, Pain 3). Discovery question: "When a family asks about a plot, how long does the lookup take?"

Step 5: The Reply, Not A Sequence. Quill Hollow is ENGAGED, so there is no cold sequence. Email 1 is not sent again as a cold touch, and Emails 2 and 3 are not drafted (Hard Rule 11). The one draft replies to her message.

The words of her 2026-10-27 reply are not in the records [Unknown]. The draft therefore answers only what the records hold: that she replied, and that she booked the call. Before it goes out, Nadia Brandt reads her message and edits the draft to answer anything she asked. Nothing in the draft assumes what she wrote.

Subject: Re: Your move to Quill Hollow and the plot maps

Ines,

Quill Hollow's plot maps are still on paper, so Monday's call is a good place to look at how sold and open plots are checked today.

Thank you for writing back on October 27, and for booking the call on November 2.

Before we talk, one question to think about: when a family asks for a sold plot, which record does your team check first?

Claim tags for the reply: the paper plot maps [CRM] (illustrative), and the October 27 reply and the November 2 booking [CRM] (illustrative). The question at the end is a question, so it needs no tag. Proof point: none. Every PlotIQ result is Illustrative (profile: Proof Points), and the two Benchmarks do not answer a reply to a booked call.

Verdict: GREENLIGHT, so the reply is ready. It is not held, and the rep still reads it before anything is sent.

Step 6: Call Prep.

Call Goal: keep the 15-minute discovery call that Ines booked for Monday 2026-11-02 [CRM] (illustrative), and hand the research to the AE. The ENGAGED row of the Call Goal table asks for the discovery call, and her booking already holds it. The AE is not named in the records [Unknown].

Opener: If the call moves and a phone call is needed, the opener refers to her reply, by its date and tag: "Hi Ines, this is Nadia Brandt from PlotIQ. I'm calling about the call you booked for November 2, after your reply on October 27. Do you have 30 seconds?" Tag: reply 2026-10-27 [CRM] (illustrative). Do not reference the Lowmoor history unless she raises it.

Discovery Question For The Call: "When a family asks for a sold plot, which record does your team check first?" The next step after this call is another discovery call, not a demo, until the pain is confirmed.

Step 7: Summary. BDR. Quill Hollow Memorial Park, ENGAGED, GREENLIGHT, with Zones 3 and 5 HIGH. One contact on file, Ines Carmody, Developing (1 of 7 behaviours). One reply draft, ready, to her reply of 2026-10-27. No cold sequence. Next action: Nadia Brandt sends the reply to Ines Carmody by 2026-10-29. This is the first step in the order, family (1), a reply owed to a buyer. A reply to a buyer's own message is due the next business day after the run date, which is Thursday 2026-10-29 (Wednesday 2026-10-28 plus one business day). The booked call on 2026-11-02 is a different date set by the record, so it is a later step, and the five-business-day default of 2026-11-04 does not apply to this reply.

Hand-off (read by 06):
account: Quill Hollow Memorial Park (ENGAGED, reply 2026-10-27 [CRM], no open deal)
run_date: 2026-10-28
account_status: ENGAGED
verdict: GREENLIGHT
zone_scores: 1 MEDIUM, 2 UNKNOWN, 3 HIGH, 4 UNKNOWN, 5 HIGH (illustrative)
contact_priority: 1 Ines Carmody (General Manager, champion label, Developing, 1 of 7 met), 2 Pre-need manager, name Unknown (gap), 3 Operations Director, name Unknown (gap), signer: owner, name Unknown (economic buyer gap)
pain_hypotheses: 1 Plot records on paper, binders or pencil maps (HIGH, Inferred), 2 Trust fund and records reporting by hand (event date unknown) (LOW, Inferred), 3 Plot lookups take minutes to hours (LOW, Inferred)
sequence: one reply draft to Ines Carmody's reply of 2026-10-27, ready (GREENLIGHT). No cold sequence, because the account is ENGAGED
report_path: none (inline)
next_action: Nadia Brandt sends the reply to Ines Carmody by 2026-10-29, the next business day after the run date (a reply to a buyer's own message, with no earlier record date)

---

Common Patterns

Pattern: Rapid-Fire Batch Mode

When: A BDR needs snapshots for five to ten accounts in one prospecting block. Approach: Run Steps 1 to 4 for each account, produce the ranked table, then write full sequences for the top two or three. See Example 3.

Pattern: Active Deal Guard (BDR)

When: The user is a BDR and the account has an open AE deal. Action: Show the deal in the summary, and recommend sharing the research with the AE instead of sending independent emails.

Pattern: ENGAGED Account

When: The account replied or met with us, and no deal is open. Approach: Build the same brief. Step 5 drafts one reply to the open thread, not a cold sequence. The verdict decides whether the reply is ready or held. The brief names the date and tag of the account's last reply. Reason: three cold emails to someone already talking to us restart the outreach they answered. See Example 5.

Pattern: INBOUND Account

When: The account asked us first, and no deal is open. Approach: Build the same brief. Step 5 drafts one reply to the request, carrying the top pain hypothesis, and no sequence. The verdict decides whether the reply is ready or held. A sequence follows only if the account goes quiet. Reason: the request is still open, and a cold sequence ignores it.

Pattern: Quick Call Prep Only

When: The user says "quick call prep" or "calling in five minutes." Approach: Skip the sequence. Deliver Steps 1 to 4 and Step 6. See Example 2.

Pattern: Snapshot Reveals A Trigger Event

When: Research turns up a recent event such as an acquisition, an expansion or a leadership change. Action: Note the trigger in the summary, and recommend Trigger Event Outbound (04), which runs on the trigger's own window.

Pattern: Snapshot Reveals A Known Incumbent

When: The CRM or the research names a specific competing product. Action: Note the incumbent in the summary, and recommend Competitive Displacement (12) for the competitive sequence.

---

Troubleshooting

"No CRM Data Available"

Likely Cause: The CRM record is missing, or the rep has no access. Response: Proceed with public research only. Write "No existing CRM record" in the output. Tag every fact [Public: source], [Inferred] or [Unknown]. Recommend CRM enrichment as the first action.

"No Contacts Found For The Target Personas"

Likely Cause: The CRM holds no contacts for those personas. Response: Look for likely contacts through public sources. Write each persona gap as "Unknown, no contact found." Make contact discovery the first action. Personalize emails by title until a name is found.

"The Company Spans More Than One Segment"

Likely Cause: A company with a secondary division. Response: Classify the account by its primary business, and score the zones on that segment. Note the secondary division as an opportunity, not as a second verdict.

"The Account Is A Previous Customer That Churned"

Likely Cause: The account was lost after it bought. Response: Flag it as a risk, and read the churn reason from the CRM. If the reason was fixed, outreach may still fit. Consider Closed-Loss Reactivation (05), which is built for this case.

"Research Turns Up Almost Nothing On The Company"

Likely Cause: Small private companies often publish little. Response: Work with what the CRM and the company's own website show. Tag everything [Public: source], [Inferred] or [Unknown]. Produce a lean snapshot with two or three pain hypotheses, and let the discovery call be the main research.

"Should I Prospect If The Verdict Is MANUAL REVIEW?"

Likely Cause: The Verdict Rule found one HIGH zone, or a must-have zone at LOW. Response: Find which zones are the gap. If the gap is data, such as an UNKNOWN zone, prioritize the discovery questions that fill it. If the gap is fit, such as a must-have at LOW, deprioritize the account in favor of GREENLIGHT accounts.

"A Zone Is UNKNOWN And The Verdict Is Close"

Likely Cause: The record is silent on that zone. Response: Do not score it. Name it in the summary as the question that would decide the verdict, and say which way the verdict moves if the answer is HIGH or LOW.

---

Best Practices

• Prioritize Speed. This skill is built for volume prospecting. Past ten minutes on one account, switch to Research Outbound (03).
• Use The CRM First. It is the record a manager can check, and it is faster than web research alone.
• Match Proof Points To The Segment. A prospect in one vertical does not care about a result from another.
• Tag Every Fact. The six tags are the only labels, and a reader checks the report by tag.
• Rank Pain Hypotheses By Confidence. HIGH-confidence hypotheses lead the outreach.
• Name The Persona Gaps. Knowing who is unknown is as useful as knowing who exists.

---

Integration With Other Skills

Reads From The Skill Before It:

• gtm-account-qualification (01). Reads verdict, zone_scores, icp_match and fit_narrative. When zone_scores arrive, use them instead of scoring the zones again, and say so. When they are absent, score the zones from the profile and say that the scores are new.
• gtm-competitive-displacement (12). Reads incumbent_type, displacement_difficulty, target_personas and sequence. Use target_personas to order the contacts, and use incumbent_type in the competitive objections. Do not write a snapshot sequence for a persona that already has a displacement sequence.

Hands To The Skills After It:

• gtm-research-outbound (03), gtm-trigger-event-outbound (04) and gtm-meeting-prep (06). Each receives account_status, verdict, contact_priority, pain_hypotheses and sequence. The receiving skill reads these names as written.

Hands To The Close:

• Wrap-Up reads report_path when a file was written, the verdict, and next_action with its owner and date.

Chains

• Qualify To Book: Account Qualification (01), then Account Snapshot (02, this skill, second), then Research Outbound (03) or Trigger Event Outbound (04), then Meeting Prep (06). This skill turns the verdict into the one-page brief, the ranked contacts, the pain hypotheses and the first sequence.
• Beat The Incumbent: Competitive Strategy (11) and Competitive Displacement (12) come first, then this skill (02, last in the chain) or Meeting Prep (06). This skill sets the contact order and the incumbent objections on one page, using the incumbent type from 12.

Guild Pro Kits (Optional)

The Business Case & ROI Kit (a paid Guild Pro kit) reads this skill's hand-off block by field name. This skill is free and works without any kit. The kit reads these five fields, with contact_priority as the economic buyer candidates and each pain hypothesis as a candidate value driver graded assumed until a buyer fact arrives:

• account
• run_date
• verdict
• contact_priority
• pain_hypotheses

---

Changelog

2.1.17 (2026-10-27)

• The shared contract now says an ask to the next action's person with no date of its own travels with the next action, and defines the champion test "explains the internal politics" (the contact tells the rep who decides, or how the decision gets made).

2.1.16 (2026-10-27)

• The shared contract's Champion Tests section now defines "commits to next steps with dates": the contact agrees, on record, to a dated next step in the deal, such as a meeting they book or a date they commit to on a call.
• The shared contract's next-action rule now says which asks travel with the next action: every ask to the same person due on or before its date, counts and figures included, and never a document the person must draft first or an ask due later.
• Next action. The next_action row and the Step 7 summary rule drop "no separate date" and "a later date set by a record" for the due-date test. The Quill Hollow summary and try-it now list the call's open questions as a later step, since they are asked after Email 1 goes out, instead of saying they stay with Email 1. No example's next action, owner or date changes.

2.1.15 (2026-10-27)

• The shared contract's Champion Tests section now defines "asks how to help" (the contact asks what the rep can supply to move the internal decision). The PlotIQ profile dates Brackhaven's deal from 2026-05-06, names the economic buyer for the Stage 2 gate the way the Buying Committee does, and limits the $25K board line claim to one-site accounts.

2.1.14 (2026-10-27)

• The shared contract's Champion Tests section now defines "creates urgency" (a dated deadline the decision works to, with its date and source on record) and "defends the solution" (a recorded case of arguing for us in our absence to someone who decides), and says a test not yet run is never scored.
• The Trait Test reads the trait the Pain Point column names. A record of one means does not meet a trait that names another, so plot records on paper meet row 1 and do not show trust reporting by hand, which is row 2.
• The Setting Test reads a fact about how the account operates. A market figure about other operators is not a setting, and a row that names no setting cannot meet the test. Brackhaven's pre-need pain meets the test through its pre-need sales line, and Quill Hollow's does not, because its pre-need activity is unknown.
• An undated event counts toward neither test at any level. It never makes a hypothesis HIGH or MEDIUM. A hypothesis that depends on one takes "(event date unknown)" at the level its dated facts give.
• The lowest-numbered LOW hypotheses fill the slots left after the HIGH and MEDIUM ones.
• Quill Hollow's trust pain is LOW, not MEDIUM. Example 1, Example 5 and the try-it promise change that one level. Sable Fork's trust pain moves to LOW the same way, and Brackhaven's trust pain moves to LOW while its pre-need pain enters the top three at MEDIUM.

2.1.13 (2026-10-26)

• Pain hypothesis confidence is set by a Trait Test and a Setting Test, each read from the profile's Core Pain Points row on tagged facts. HIGH needs both, MEDIUM one, LOW neither. A dated event counts only when dated, and an undated event takes "(event date unknown)" and counts toward neither test.
• Quill Hollow's lookup pain is LOW, not MEDIUM, because no lookup time is on record and a paper map is the means, not the measure. Example 1, Example 5 and the try-it promise change that one level. Pains 1 and 2 keep their levels.
• Sable Fork's three pains are re-derived under the two tests: plot records on paper MEDIUM (a spreadsheet is not paper), trust reporting by hand MEDIUM, and plot lookups LOW. Its hand-off changes to match.
• Brackhaven's second pain is named from the Core Pain Points taxonomy, Trust fund and records reporting by hand, MEDIUM, in place of the Oldgate renewal, which becomes an Email 2 angle and not a pain. A LOW third pain, plot lookups, is added so the example shows three pains, as the Step 4 rule requires.
• Zone 3 HIGH reads the approver of record, and the year-one signing cost is derived from the profile's list price, so the records name who approves and not the signing rule. Example 1 and Example 5 say "approver of record" where they said "signs under $25K alone". Step 3 names the approver as the signer.
• The try-it records remove the champion-label rule clause, and the try-it promise's region line uses the Output Contract's wording, "Region tier: no tier yet".

2.1.12 (2026-10-26)

• The Output Contract's next_action row and Step 7 give one priority order for the next action. (1) A reply owed to a buyer who wrote to us. (2) AE coordination for an ACTIVE account with an AE owner. (3) The first send of a GREENLIGHT sequence. (4) A meeting already on the calendar. (5) The first send of a MANUAL REVIEW package, after a person clears it. (6) A DISQUALIFY with no reply owed, with no outreach. A meeting ranks ahead of a held package because a held package cannot go out until it is cleared.
• Ties inside one step kind go to the earlier due date, then the earlier date of the buyer's message, then the account name. Same-person asks with no separate date stay with the next action, and only a different person or a later record date is listed after it.
• Step 3 defines an applicable persona and the top three. The top three are the first three applicable personas in the ranking, so Persona 3 is a gap when it has no contact, and the economic buyer is a gap when the signer is unnamed.
• Step 4 names each pain hypothesis from the Core Pain Points taxonomy. A dated event is added in brackets, and an undated event adds "(event date unknown)". Every pain hypothesis carries the [Inferred] tag. The Output Contract and the Quality Bar say so.
• The Methodology sets the primary-fit rule. Primary fit is Partial when part of the key indicator is Unknown, and it never scores Yes on an Unknown part.
• Example 1, Example 2, Example 5 and the try-it use the taxonomy names, the three persona gaps and the Partial primary fit where the record leaves a key-indicator part unknown. Example 4 sends Email 1 as its next action, because the first send ranks ahead of the call the email asks for.
• No verdict, zone score, account status or next action changes, except Example 4, whose next action moves from booking a call to sending Email 1. The try-it promise changes its pain names, its persona gaps and its later-steps wording.

2.1.11 (2026-10-26)

• Step 3 settles the persona tie. Once no persona has a HIGH pain, a champion ranks ahead of an influencer, so the pre-need manager (champion) comes before the Operations Director (influencer) in Example 1.
• Step 3 settles the signer. The economic buyer is the person the record names as the signer, so the owner is the gap when the record says the owner signs, even if the GM champions the account. A GM is the signer only when the record says so.
• Step 2 writes "no tier yet" on its own line when the state is not recorded.
• The records state the signing fact only. The words "no board approval step is recorded" leave the records, and Zone 3 HIGH reads the signing fact under the rule that a condition which cannot apply counts as met.
• No try-it promise, verdict, zone score or contact gap changes.

2.1.10 (2026-10-26)

• Gone quiet is no longer restated locally. Step 5 points to the shared rule in What The Close Reads.
• Example 5's reply to Ines Carmody is due 2026-10-29, the next business day after the 2026-10-28 run. The booked call on 2026-11-02 is later, so it sets no earlier date. The Step 7 summary and the hand-off next_action carry the new date.
• A DISQUALIFY on an INBOUND account gets one short decline draft, held for the rep to read, in Step 5, the Output Contract, Hard Rule 13 and the Quality Bar. Quick Call Prep keeps its no-draft rule except for that decline.
• No try-it promise, verdict, zone score or pain hypothesis changes.

2.1.9 (2026-10-26)

• INBOUND accounts, which asked us first with no open deal, get one reply to their request first, carrying this skill's angle. A cold sequence follows only if the account goes quiet, meaning no reply within five business days after the reply is sent.
• The INBOUND rule sits in Step 5, the Call Goal table, the opener rule, a new INBOUND pattern, Hard Rule 12, the Quality Bar and the Output Contract.
• A new example covers the ENGAGED path, with one reply draft and no cold sequence.

2.1.8 (2026-10-26)

• Every profile citation is written (profile: Section), naming the real section. Template placeholders and the shared contract are unchanged.
• ENGAGED is one of six statuses. Step 5 gives an ENGAGED account one reply draft to its open thread, not a cold sequence, and the Call Goal table, the opener, a new ENGAGED pattern, Hard Rule 11 and the Quality Bar follow the same rule. The verdict itself does not change with status.
• A MANUAL REVIEW package is held: it is marked Held on its first line, nothing in it goes out before a person clears the verdict, and Hard Rule 10 says so. Quick Call Prep drafts none. Batch mode names its ready and held sets.
• Example 1 and its try-it no longer show two replies from the GM before the run date. The account stays TARGET on 2026-10-19 and the reply that makes it ENGAGED comes later, so the status and the contact ranking reason are restated.
• Example 3 gives Greyfield no snapshot sequence, because Competitive Displacement (12) already holds its sequence, and gives Tamsin Vale a held package in place of the hold note.
• Headings and labels are capitalized word by word.

2.1.7 (2026-10-26)

• The rule text no longer refers to the examples by number. The try-it pointer names a full first run.
• The zone rules separate the regulatory signal from Zone 1. The signal asks whether a finding is on the record at any date. Zone 1 HIGH needs a dated finding inside 24 months.
• Step 3 names the rule for ranking the top personas, and states the Champion Test list and its thresholds where the step applies it.
• Step 4 shows every HIGH or MEDIUM pain hypothesis, up to five, and at least three. Example 1 and its try-it follow that rule.
• The try-it records state facts only. The owner's signing line keeps the fact and drops the rule phrase.

2.1.6 (2026-10-26)

• The GM move in Examples 1 and the try-it is tagged to the state licensing database, not the CRM.
• Example 1 opens its three emails and its call opener on the dated GM move. The undated records finding is used only as a discovery question, and no email or call line quotes it.
• Example 2 cites the recorded no-pre-need fact for Zone 2 and the recorded flat-sales and no-succession facts for Zone 5. Both zones stay LOW, so the MANUAL REVIEW verdict is unchanged.
• Example 3 dates the Corrow Ridge Email 1 to the first day of the Corrow Ridge sequence, and the hand-off next action carries the same date.
• Example 4 names the BDR as the one who books the first discovery call for the AE, and tags the owner retirement and the board check to their public sources.

2.1.5 (2026-10-26)

• The Zone 3 sentence of Example 4 quotes the profile's Zone 3 cell as written.
• The next action follows the family's one deadline rule (five business days after the run date, or an earlier date the records or the skill's own schedule set for that step). The Output Contract and Step 7 point to that rule, and each example next action carries its date under it.
• The UNKNOWN zone sentence beside a GREENLIGHT uses the profile's Verdict Rule wording: neither HIGH nor LOW, never earns or blocks GREENLIGHT.
• The flagship example's hand-off run date matches its own context line, and its next action gains a date.

2.1.4 (2026-10-26)

• Try-it evidence completed so a strict first run reproduces Example 1.
• Methodology gains one paragraph: a fact the profile's Example Cast supplies takes the tag of the record that would hold it, and carries (illustrative).
• Zone Scores gains a sentence on UNKNOWN zones beside a GREENLIGHT.
• Confidence gains a sentence: a signal whose date is unknown does not count toward the three signals when the hypothesis depends on a recent event.
• Scale is read from the profile's Size Bands, with the band rule quoted, and the examples' scale signals name their band.
• Contact Mapping gains two sentences: the gaps are the top-three personas with no contact and the economic buyer when the person is unknown, and the Champion Test is reported as not yet run when the records hold none of its behaviours.
• Pain Hypotheses gains one clause: a hypothesis that depends on a dated event is named with that event.
• Step 5 gains one sentence: only a GREENLIGHT account gets a sequence.
• The next_action in the Output Contract and Step 7 gains the date rule, and the Output Contract example is now a placeholder.
• The records and Example 1 gain the BDR owner, the tag on the GM move and the Example 1 scale band.

2.1.3 (2026-10-26)

• Try-it evidence completed so a strict first run reproduces Example 1. Adds the last logged contact with the champion to the records, so the ranking reason is evidenced.
• Zone Scores gains the partial-match sentence, with a pointer to Account Qualification (01) Step 4. The Zone 3 sentence is unchanged.
• Confidence gains one sentence: a hypothesis with no signal and no record data is LOW.
• Contact Mapping gains one sentence: a CRM champion label is recorded as a label until the shared Champion Test runs.
• Scale and Team signals are defined from counts, with no team label that the rule does not support. The examples' team words change to match.
• Examples 1 and 4 gain Emails 2 and 3 and a call prep, the parts the default Full Snapshot mode defines. Example 3 says which accounts get full sequences and that the block shows their rows only.

2.1.2 (2026-10-25)

• Try-it evidence completed so a strict first run reproduces Example 1.

2.1.1 (2026-10-25)

• Adds examples/try-it.md so a first run reproduces Example 1. No other change.

2.1.0 (2026-10-25)

• Reads the Context OS account folder and offers read-only CRM and call connectors through the shared contract's new Knowledge Base and Connectors section. Adds a Chains subsection and a Guild Pro Kits subsection. No other change.

2.0.1 (2026-10-20)

• Every hand-off block carries a run_date line after its account line, so two instruments on one deal are compared by date (found by the wave two hand-off tests). No other change.

Version 2.0.0 (2026-10-20)

• Verdict now comes from the profile's Qualification Zones and Verdict Rule, applied as written, with zone scores beside it. The five-signal quick-score stays as the one-glance read and no longer sets the verdict.
• Region map uses the profile's own tiers, with a source per tier.
• Proof points come only from the profile's Proof Points table, one per email. Illustrative results are never cited in an email.
• Evidence labels replaced by the six shared tags.
• Epistemic Rules gain the n rule and the five-case rule. Silence is not a no.
• Hard Rules with reasons replace the Don'ts. The Quality Bar is now a checklist.
• Hand-off fields named in the Output Contract, the Integration section and each example's hand-off block.
• Examples aligned to the PlotIQ chain file. Sable Fork carries its chain zone scores. Quill Hollow carries its own zone scores. A flagship snapshot for Brackhaven is added as the first account in the chain.
• The old output-format section is folded into the Output Contract's file option, which is Markdown only and written on request.

Version 1.3.0 (2026-10-13)

• Examples re-cast on PlotIQ, with the tier wording made vertical-neutral.

Version 1.2.0 (2026-09-29)

• Worked examples rewritten around a single case study. Em dashes removed from prose.

Version 1.1.0 (2026-07-06)

• Restructured around the five-part skill anatomy. Company-specific data moved to the shared profile. Framework machinery moved to an explicit Methodology section.

Version 1.0.0 (2026-03-04)

• Initial release, with the profile-driven design and the batch and quick call prep patterns.