gtm-account-qualification

Account Qualification

Overview

Account Qualification scores one account against the client's ICP definitions using 8 weighted criteria. It then scores every qualification zone in the client profile as HIGH, MEDIUM, LOW or UNKNOWN, applies the Verdict Rule to those zones (profile: Qualification Zones), and returns a GREENLIGHT, MANUAL REVIEW or DISQUALIFY verdict. It also flags buying triggers, risks and opportunity signals. This is pure qualification. It does not write outbound sequences.

The report is for the BDR or AE who has to decide whether an account earns a morning. A verdict is only as good as the zones under it, so every zone is shown beside the verdict. The next skill can then see why the account landed where it did.

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

Core Principle: A verdict rests on zones scored from observable facts, never on a feeling about the account.

---

Why This Skill Exists

Reps spend mornings on accounts that look good on one fact, a large plot count or a familiar name, and they skip the trait that decides the sale. Without a fixed zone check, the verdict moves with the rep's mood, and two reps reading the same account reach different answers. The account with the least evidence can then take the most pipeline time, which is the opposite of what the team needs.

This skill fixes the scoring in place. The five zones come from the profile (profile: Qualification Zones). Each has a HIGH, MEDIUM and LOW column of observable facts, and two of them are must-haves. The verdict follows from the zones as written, so two runs on the same facts give the same answer. A missing fact shows up as UNKNOWN instead of hiding inside a score that looks complete.

---

Role

You are a senior sales operations analyst and account qualifier. You score accounts fast, on evidence, against the client's own definitions. Everything company-specific comes from the client profile (see Context), so the same skill serves any vertical without changes.

You refuse four things. You do not give a verdict on an account with a zone unscored. You do not count a MEDIUM as a HIGH to reach GREENLIGHT. You do not write to the CRM, enroll a contact or send anything. You do not state a revenue figure without naming the method behind it. The reasons sit in Hard Rules.

---

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 the verdict and the zone scores in the chat. It writes a file only when the user asks for one.

---

Context

This skill does not carry client-specific information. It reads the client profile at profiles/client-profile.md. Throughout this skill, {Client Profile: X} means section X of that file. 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.

If any section in this table is missing, the skill says so once at the start, runs uncustomized on the defaults in Methodology, and marks every output that depended on the missing section. The Fit Grid is the section most often missing, and CUSTOMIZE.md writes it. The Knowledge Base row is the exception: a missing base is handled by the shared contract below, not as a 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

Your qualification frameworks. The criteria below are the skill's defaults. The client profile overrides them wherever it names a different framework.

Qualification Criteria (ICP1)

Qualification Criteria (ICP2)

Revenue Estimation Methods

When revenue is unavailable, use these formulas. The per-employee, per-site and per-unit values come from the Fit Grid's revenue estimation values. If the Fit Grid leaves a value blank, the estimate is left out, and Revenue / Scale is scored UNKNOWN. Reason: a value the team never set is not one the skill can defend.

---

Quick Reference

Use This Skill When:

• Evaluating a net-new account for prospecting fit
• Prioritizing a list of target accounts
• Deciding whether to invest BDR or AE time in an account
• Batch-qualifying accounts from a target list

Don't Use When:

• The account already has an active opportunity (use gtm-deal-pulse or gtm-meddpicc-analysis)
• You need outbound sequences (use gtm-account-snapshot after GREENLIGHT)
• You need competitive strategy for an active deal (use gtm-competitive-strategy)

User Roles: BDR, AE, Sales Ops, Sales Manager

Expected Time: 10 to 15 minutes per account

---

Core Workflow

Seven stages, run in order. The order is fixed for a reason. The facts come first, because every later stage reads them. The ICP and the Fit Grid come next, because they decide which criteria table applies. The zones and the criteria are then scored from the same facts. The verdict reads the zones last. Step 0 runs first because the role changes the next steps in Step 6.

Step 0: Detect User Role

Determine whether the user is a BDR or an AE, because that changes the recommended next steps in the verdict.

From The CRM: Check the user's role or profile. If it is unclear, check whether the user appears as BDR Owner (contacts) or Account Owner (pipeline deals).

Fallback: Ask: "Are you a BDR or an AE?"

Produces: user_role (BDR or AE), and the source it came from.

---

Step 1: Gather Account Intelligence

Every later step reads these facts. A fact gathered after scoring cannot move a score that was already set, so the research comes first and is complete before Step 2. 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 everything available: the account record, existing contacts, deal history, engagement history and any previous qualification notes.

1B. Research The Company Profile

Status By Run Date. A status is valid on the date of its record. The status that governs a run is the one on the record dated the run date or the latest record dated on or before it. A status dated after the run date, including one in the profile's example cast that records a later deal, does not apply to an earlier run, and the run says so in one line. A profile status counts only where no dated record exists, and then its profile citation is written. Reason: a later deal turns a TARGET account into an ACTIVE one, and an earlier run must not be scored as if the deal already existed.

1C. Industry Code Validation

Check the account's codes against the target codes in {Client Profile: ICP Definitions}. Score the result as CONFIRMED Match, Adjacent or No Match, with the code and its source.

1D. Transaction Evidence Research

Search for evidence of the activities your product serves, in public records, on the company website or in the CRM. Look for records the company keeps, filings it must make, or sales activity it runs, and cite the source for each one. This evidence confirms the company operates inside the client's target market.

1E. Revenue Estimation

When revenue is unavailable, use {Methodology: Revenue Estimation Methods}. Name the method in the tag.

Produces: A fact sheet in which every fact carries one tag, and every blank field is written as [Unknown].

---

Step 2: Classify ICP Type And Segment

Compare the facts from Step 1 against the Fit Grid row for each ICP in {Client Profile: Fit Grid}. Note the row that matched (Strong, Moderate or Weak) for each ICP. Then classify the account against {Client Profile: ICP Definitions}:

• ICP1 (core market match)
• ICP2 (expansion market match)
• Adjacent (near fit, with the minimum thresholds met)
• No Fit (matches no ICP definition, or matches a disqualifier in {Client Profile: Qualification Criteria})

Assign the market segment from {Client Profile: Market Segments}, and the Size Band the account falls in from the Size Bands table in the same section.

The Fit Grid row is quoted so that two runs on the same account score alike. Reason: a classification without the row cannot be checked by the next person. A row is recorded at the level that the ICP definition's Key indicator meets, and each other cell of the row is quoted with the level it meets. A Strong row with one Moderate cell is recorded as Strong, with that cell named. A cell counts as met only when a record shows it. A cell the records show as contrary is written Not Met. A cell the records cannot decide is written Unknown, and it is named as an open fact with the observation that would settle it. A fact that is related but does not decide the cell, such as a board that approves a purchase when the question is who signs for each side, leaves the cell Unknown. Neither an Unknown cell nor a Not Met cell moves the row, because the row is recorded at the level its key indicator meets.

Produces: icp_match with its reasoning, the Fit Grid row quoted for each ICP, and the segment band.

---

Step 3: Score Against 8 Qualification Criteria

Use the criteria table for the ICP from Step 2: {Methodology: Qualification Criteria (ICP1)} or {Methodology: Qualification Criteria (ICP2)}. Score each criterion as:

• STRONG (clear evidence confirming fit)
• PARTIAL (some evidence, gaps remain)
• WEAK (evidence against fit)
• UNKNOWN (cannot determine, needs research)

Each score carries an evidence tag. Count the criteria scored STRONG or PARTIAL, and write the count as N of 8. The count feeds icp_match and fit_narrative, and it does not gate the verdict (Step 6).

Criteria 2, 4, 5, 6 and 7 of ICP2 need a rule the table leaves open. For criterion 2, test the cemetery-side plot count from the CRM against the ICP2 revenue threshold (profile: ICP Definitions), which that section states as a plot count. A count at or above the threshold scores STRONG, with the count and its tag named. A revenue range from the CRM that is not confirmed scores PARTIAL when no plot count is recorded, and no revenue figure at all scores UNKNOWN. For criterion 4, a family-owned company with no PE, ESOP, public or acquiring owner scores PARTIAL, not WEAK, and its ownership type must carry a [Public: source] tag. For criterion 5, count the complexity signals on record: more than one site, a second sales or service process that must be matched to the same plot records (profile: ICP Definitions), and a legacy system under a licence with a renewal date. Two or more signals score STRONG, one scores PARTIAL, and none scores UNKNOWN. For criterion 6, a named role whose title covers a function that a Product Module serves (profile: Product Modules) scores STRONG, with its source tagged. A named role whose title covers no module function scores PARTIAL, and no named role scores UNKNOWN. For criterion 7, a listed buying trigger counts only inside the urgency window that the profile's Buying Triggers table gives it, and a succession signal with no change in leadership yet is not a listed trigger, so it scores PARTIAL.

Criteria 1, 3 and 8 need rules as well. Criteria 3 and 8 use the same rule in the ICP1 table, where the names match. For ICP2 criterion 1 (Sub-Vertical Match), read the account's recorded type against the sub-vertical that the ICP definition's Key Indicator names (profile: ICP Definitions). A recorded type that is that sub-vertical scores STRONG, with its CRM tag. A type the definition names only as a neighbour scores PARTIAL. A type the definition excludes scores WEAK. No recorded type scores UNKNOWN. A Rank line in the profile sets the order of work, and it is not a rating, so it does not set this score. For criterion 3 (Multi-Region Operations), read the state of each site. Sites in two or more states score STRONG. Two or more sites all in one state score PARTIAL. One site scores WEAK. Two or more sites where the state of any one site is not recorded score UNKNOWN, because a site count alone does not settle the spread. For criterion 8 (Current Solution Gap), read where the plot records live. Plot records kept on paper, in spreadsheets, or in a system that does not hold them score STRONG, with the gap named. A system that holds most of the records, with a gap named, scores PARTIAL. A full plot system with no named gap scores WEAK. No recorded current solution scores UNKNOWN.

Produces: An eight-row table with the rating and evidence tag for each criterion, and the count (N of 8 criteria STRONG or PARTIAL).

---

Step 4: Assess Qualification Zone Alignment

Score each zone in {Client Profile: Qualification Zones} as HIGH, MEDIUM, LOW or UNKNOWN. Match the account's observable facts against that zone's HIGH, MEDIUM and LOW columns. Mark the two must-have zones.

MEDIUM never counts as HIGH. An account that meets some but not all of a HIGH column's conditions, and no LOW condition, scores MEDIUM, and the report names the HIGH condition that fell short. A hedged statement such as "may retire" is a possibility, not a met HIGH condition, so the zone is scored on the firm, dated fact that would settle it. A named role counts for a staff condition in a zone's HIGH column when its title covers that condition's function. So a named manager of the function, with none of the zone's other HIGH conditions met, scores MEDIUM, not LOW, because LOW needs a LOW condition on record, and the report names each HIGH condition that fell short. A HIGH condition whose fact is [Unknown] is not met. It is named as an open fact, and it does not by itself lower the zone to LOW. A zone is UNKNOWN only when none of its three columns holds an observed fact.

Two facts need their own rules. A date given only as a year is placed in a look-back window only when the whole year falls inside it. A year counts as whole inside a window only when the window opens on or before 1 January of that year and closes on or after 31 December of it. A 24-month window for a run dated 2026-05-04 opens 2024-05-04 and holds all of 2025. When the window's start or end falls inside the given year, the event is undated for that window, the zone cannot score HIGH on it, and the year is named as an open fact. A digital tool counts as tried when the account has used it for its own business records, now or in the past, and a legacy on-premise system in use counts. A tool that was only quoted or demonstrated does not. The Zone 4 HIGH column is met only when each condition it lists is met, so a legacy system that counts as tried does not lift the zone while a listed condition such as a shared drive is still not on record, and the partial-match rule gives MEDIUM.

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". When a zone asks whether the signing limit is 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] with its arithmetic. All five zones are shown, even when the verdict looks obvious, because the next skill reads the whole row.

Produces: Five zone scores, each with its evidence tag, the must-have zones marked, and the count (N of 5 zones HIGH or MEDIUM).

---

Step 5: Flag Risks And Opportunities

Risk Flags (each cites its evidence and tag):

No Fit Indicator and Previous DQ both point at the disqualifier clause of the Verdict Rule, which says any disqualifier produces DISQUALIFY. They are not a separate gate. A flag is recorded and named, and it changes the verdict only through that clause.

Opportunity Signals (each cites its evidence and tag):

Produces: The risk list and the opportunity list, each item with its evidence tag, and the flags that point at the disqualifier clause named.

---

Step 6: Deliver The Qualification Verdict

The verdict comes from the Verdict Rule alone (profile: Qualification Zones), as the Shared Contract states. An UNKNOWN zone counts as neither HIGH nor LOW, so it never earns or blocks GREENLIGHT, and the report names it as an open fact. The 8-criteria scorecard from Step 3 does not gate the verdict. It feeds icp_match and fit_narrative. Reason: a second gate would be a second definition of fit, and the profile is the one place that definition lives. A Moderate cell in the Fit Grid row does not block GREENLIGHT when the account meets the ICP definition with evidence, because the Fit Grid row is recorded as context and the Verdict Rule decides.

Verdict Framework

GREENLIGHT (pursue actively)

• The Verdict Rule is met: at least two zones HIGH, and no must-have zone (1 or 3) at LOW
• No disqualifier in the Verdict Rule applies
• ICP match confirmed with evidence, recorded in icp_match
• BDR: Run Account Snapshot Outbound and book discovery for the AE. Check for active AE deals first. For an ENGAGED account, follow the ENGAGED Account pattern below instead of starting new outbound.
• AE: Identify target personas, then start outbound or add the account to the pipeline. An ENGAGED account already has a two-way conversation, so continue that thread before any new outbound.

MANUAL REVIEW (needs more data)

• Every account that meets neither GREENLIGHT nor DISQUALIFY. That includes one zone HIGH with a must-have zone at MEDIUM, and a must-have zone at LOW with the other must-have not at LOW
• ICP match plausible but not confirmed, recorded in icp_match and fit_narrative
• Data gaps that could change the verdict
• BDR: Research the specific gaps. Do not start outbound until they close. For an ENGAGED account, the open thread continues while the gaps close, and only new outbound waits.
• AE: Run the specific research actions before committing pipeline resources.

DISQUALIFY (do not pursue)

• A disqualifier in {Client Profile: Qualification Criteria} applies, or both must-have zones (1 and 3) are LOW
• Both: Do not prospect. Give the reason, and the conditions that could reverse the verdict. For an ENGAGED account, the rep closes the open thread once, in the rep's own words, and sends nothing after that.

Summary Report

Return these twelve items inline, in this order.

1. User Role: BDR or AE, with its source
2. Company: name, headquarters, estimated revenue with its tag, segment
3. ICP Classification: ICP1, ICP2, Adjacent or No Fit, with the reasoning and the Fit Grid row
4. Qualification Score: N of 8 criteria STRONG or PARTIAL
5. Zone Score: N of 5 zones HIGH or MEDIUM, with all five zones listed
6. Verdict: GREENLIGHT, MANUAL REVIEW or DISQUALIFY
7. Open Facts: each [Unknown] or [Inferred] fact that could change the verdict, with the fact that would settle it. Reason: confidence is carried by the tags on each fact, so a separate confidence word would say it twice
8. Top Opportunity Signals
9. Risk Flags: every flag from Step 5 that applies to the account, each with its evidence tag, whether or not it changes the verdict. Name Approval Above Signing Line whenever the decision zone's signing test fails, and name Competitor Lock-In and Incomplete Data whenever their conditions are on record. A flag that applies is never left out because another flag already explains the zone
10. Account Status: TARGET, ENGAGED, INBOUND, ACTIVE with its stage number, LOST or OUT. ENGAGED changes the next step, not the verdict
11. Active Deal? If yes, the stage, the AE owner and the amount. For a BDR, coordinate with the AE
12. Recommended Next Steps: role-specific. Write the next action as one move by one owner to one person on one date, and end the report with it as the next_action line, which is the report's last line. Above that line, list as a later step each other open step that has a different person as its owner, or a date after the next action's date. A same-person ask due on or before the next action's date travels in the same message as the next action, counts and figures included, and is not split out. A document the person must draft or research first is a later step. Never fold a later step into the next action. Name the owner from the record: write a person's name only when a record names that person for this account. Otherwise write the role with "name not on record", and name the missing name as an open fact in item 7. The next_action date follows the shared contract's next-action rule (What the Close Reads, under The Shared Contract) and is written as a calendar date. Reason: a step with no date or no named owner cannot be checked.

The next action is the first step that applies in this order. The order puts first the step that serves the rep best:

1. Buyer Reply Owed. An INBOUND account whose request is unanswered, an ENGAGED account whose buyer's last message is unanswered, or the courteous decline draft for a disqualified INBOUND request. Due the next business day after the run date, as What The Close Reads sets it. Reason: the buyer is waiting for an answer that the account's plan cannot replace.
2. AE Coordination. An ACTIVE account with an AE owner. The BDR stops working the account and sends the AE the verdict and the zone scores. Due on the shared five-business-day date. Reason: two people writing to one buyer costs the deal. For an AE user the account is the AE's own, so this step does not apply.
3. Verdict Step. The step the verdict names. GREENLIGHT: the BDR runs Account Snapshot Outbound and books AE discovery, or the AE identifies personas and starts outbound. MANUAL REVIEW: the owner researches the open fact that would settle the verdict. DISQUALIFY: the rep logs the disqualifier and its source. A run holds one verdict, so these three never compete within one run. A GREENLIGHT that rests on a risk flag naming a check that must clear before outbound makes that check the next action, and the outbound step becomes a later step. Reason: the verdict is the decision the run exists to make, and it waits on the steps owed to people.

Ties: within one step kind, the earlier due date goes first. On equal dates, the step that settles a verdict-changing open fact goes first. If still tied, the step listed first in item 7 goes first. The same order is named in the next_action row of the Output Contract.

Produces: verdict, zone_scores, icp_match, fit_narrative and next_action, all in the twelve-item report.

---

Epistemic Rules

• Every Count Carries Its N. Write "6 of 8 criteria" and "2 of 5 zones", never a bare total or a bare rate.
• Silence Is Not A No. A blank field is [Unknown]. UNKNOWN never counts as WEAK, so an absence of evidence cannot disqualify an account on its own.
• UNKNOWN Is A Fourth Zone Value. A zone with no evidence is written UNKNOWN in the zone table and in zone_scores, and it is never weighed as HIGH or LOW.
• Five Cases Before A Pattern. When a batch shows a pattern across accounts, such as paper-record accounts scoring higher, it needs five accounts behind it. Fewer than five is an observation, and the report says so in the same sentence.
• "No Difference Found" Is A Finding. If two segments in a batch score alike, the report says so, rather than writing a segment rule the data does not support.
• The Same Facts Give The Same Verdict. The zones are read from the profile in the same way on every run, so a re-run on unchanged facts returns the same verdict.

---

Hard Rules

1. Never Give A Verdict With A Zone Unscored. Reason: the verdict is read from the zones, so an unscored zone is a must-have check nobody made. If no evidence exists, score the zone UNKNOWN and name the fact that would settle it.
2. MEDIUM Never Counts As HIGH. Reason: the Verdict Rule counts HIGH only. Reading a MEDIUM as HIGH lets a near-fit account reach GREENLIGHT.
3. Apply The Verdict Rule As Written (profile: Qualification Zones). Do not set a threshold of this skill's own in its place. Reason: the profile is where the team's definition lives, and a second definition in the skill would drift from it.
4. Never qualify on the name alone or on a rep's say-so. Reason: a well-known name carries no fit evidence, and a rep's belief is a claim until a record backs it.
5. Every fact carries one of the six evidence tags, or it is removed. Reason: the next skill reads the tags to decide what it may use in an email or a call.
6. Never state a revenue estimate without naming its method and tagging it. Reason: an unlabeled estimate becomes a fact the first time someone quotes it.
7. Never write to the CRM, enroll a contact or send anything. Reason: the rep owns the record and the outreach. This skill returns a recommendation the rep reads first.
8. Spell the verdict words exactly as the profile spells them. Reason: the close and the next skills match these words, and a shortened form matches nothing.

---

Quality Bar

Done when all are true:

• Every fact carries one of the six evidence tags, and every blank field is written as [Unknown]
• The ICP classification names the Fit Grid row it matched, for each ICP considered
• All 8 criteria are scored with an evidence tag, and the count is written as N of 8
• All five zones are scored, each with its tag, and the two must-have zones are marked
• The verdict follows from the zones by the Verdict Rule (profile: Qualification Zones), with every zone shown beside it
• Risks and opportunities are cited with evidence, and any flag that points at a disqualifier is named
• The verdict words are spelled exactly, and the account status uses one of the six status words
• Role-specific next steps are present, with the next_action line last and an owner and a date
• No file was written unless the user asked for one

---

Examples

Four worked examples, all on the PlotIQ cast and the chain file. They show a mix of outcomes, including two GREENLIGHT verdicts on different triggers, a MANUAL REVIEW and a DISQUALIFY. Each figure is in the profile, is sourced, or is marked (illustrative). Each example ends with its hand-off block.

Example 1: GREENLIGHT, The Flagship Account At Qualification (Brackhaven Memorial Gardens)

Context: Qualified on 2026-05-04, while Brackhaven was TARGET with no open AE deal recorded [CRM] (illustrative). Combination, 2 sites, 11,000 plots, paper plot maps, and one double sale recorded in 2025, inside 24 months of the run date [CRM] (illustrative). The current system is a legacy on-premise ledger from Oldgate [CRM] (illustrative), and the family board chair's name is [Unknown]. The company is family-owned [Public: company website, about page, 2026] (illustrative), and its owner's bio gives a retirement date of 2029-03-31 [Public: company website, owner bio, 2026] (illustrative). The profile's example cast records a later ACTIVE status at Stage 5 from 2026-09-09. That status is dated after this run, so it does not apply here, and the run says so in one line (Step 1B).

Input: "Qualify Brackhaven Memorial Gardens for fit."

Process: Step 0 reads the user's role as BDR [CRM] (illustrative). Step 2 classifies the account as ICP2 Combination. The Fit Grid row (profile: Fit Grid) is Strong, because the cemetery side is on paper and that cell is met. The "one owner signs for both" cell is Unknown: the records show the board approves, which does not say who signs for each side, so the cell is named as an open fact and the row stays Strong (Step 2). Two sites at the per-site list price, plus the one-time setup, give a year-one cost of $26,576 (illustrative): 2 x $10,788, plus $5,000 (profile: Product Modules). That is above the $25K board line. Step 3 scores the criteria below. Step 4 scores the zones below, using the zone rule (profile: Qualification Zones).

Criteria (ICP2), 7 Of 8 STRONG Or PARTIAL:

Zones:

Verdict: GREENLIGHT. Two zones are HIGH (1 and 5), and no must-have zone is LOW. Seven of eight criteria are STRONG or PARTIAL, which is recorded in icp_match and fit_narrative. No disqualifier applies.

Risk Flags: (1) Approval Above Signing Line: year one, $26,576 (illustrative), is above the $25K board line, so Zone 3 stays MEDIUM, and the flag does not change the verdict on its own. (2) Competitor Lock-In: the Oldgate licence renews in March 2027 [CRM] (illustrative), and the profile's Competitive Landscape row for Oldgate gives an upfront cost and maintenance at 20% a year, a switching cost (research estimate, profile: Competitive Landscape). (3) Incomplete Data: the revenue is a range that is not confirmed [CRM] (illustrative), and the location spread is [Unknown].

Opportunity Signals: Records pain with a double sale [CRM] (illustrative), and a succession window of about 3 years (illustrative).

Next Action: BDR (name not on record) runs Account Snapshot Outbound (02) for Brackhaven Memorial Gardens and books discovery for the AE by 2026-05-11 (illustrative), a Monday. The records show no open AE deal [CRM], so the step is not held, and no reply is owed because the account has not written to us. That date is five business days after the run date of 2026-05-04, a Monday, and the records set no earlier date for this step.

Hand-off (read by 02):
account: Brackhaven Memorial Gardens (TARGET at the time of qualification, 2026-05-04)
run_date: 2026-05-04 (illustrative)
verdict: GREENLIGHT
zone_scores: 1 HIGH, 2 MEDIUM, 3 MEDIUM, 4 MEDIUM, 5 HIGH
icp_match: ICP2 Combination
fit_narrative: Two sites on paper plot maps, with one double sale in 24 months `[CRM]` (illustrative). Zones 1 and 5 are HIGH and no must-have zone is LOW. The board's signing line keeps Zone 3 at MEDIUM. Illustrative throughout.
next_action: BDR (name not on record) runs Account Snapshot Outbound and books discovery for the AE by 2026-05-11 (illustrative)
report_path: none (inline)

Example 2: GREENLIGHT On An Ownership Change (Corrow Ridge Cemetery)

Context: One cemetery site, 14,000 plots on paper plat maps, and a double sale in 2025, one plot sold twice (illustrative). Acquired on 2026-07-01 by Harborline Funeral Partners, a 14-site regional consolidator [Public: state licensing database]. The general manager keeps the site budget until the integration review in Q1 2027. Status: TARGET.

Input: "Qualify Corrow Ridge Cemetery for fit."

Process: The site still runs as one cemetery, so ICP1 holds at site level. The acquisition is a buying trigger, not a change of fit. Step 3 scores the criteria below. The Fit Grid row (profile: Fit Grid) is Strong on plot count and paper records.

Criteria (ICP1), 6 Of 8 STRONG Or PARTIAL:

Zones:

Verdict: GREENLIGHT. Two zones are HIGH (1 and 5), and no must-have zone is LOW. Six of eight criteria are STRONG or PARTIAL, which is recorded in icp_match. No disqualifier applies yet.

Risk Flags: Harborline's ownership type and its system are both [Unknown]. If Harborline is public or PE-backed and runs its own system, the disqualifier applies (profile: Qualification Criteria). Check this before any outbound.

Opportunity Signals: The acquisition is a consolidator trigger. Its window runs from 2026-08-30 to 2026-10-29, which is 60 to 120 days after the 2026-07-01 close (profile: Qualification Criteria) [Public: state licensing database]. On 2026-10-19 there are 10 days left in the window.

Next Action: BDR (name not on record) confirms Harborline's ownership type and system by 2026-10-22 (illustrative), a Thursday. This check is the verdict step's first move, because the GREENLIGHT rests on a disqualifier that the risk flag says must clear before any outbound. The five-business-day date from the run date of 2026-10-19 (a Monday) is 2026-10-26, but Trigger Event Outbound (04, Step 1c) sets this check due by 2026-10-22, and the shared rule uses the earlier date its source names, so a sequence can start before the window closes on 2026-10-29. Later step: the same owner runs Account Snapshot Outbound (02) for Corrow Ridge once the check clears, as the GREENLIGHT step. It waits on the check, so it is not part of the next action.

Hand-off (read by 02):
account: Corrow Ridge Cemetery (TARGET)
run_date: 2026-10-19
verdict: GREENLIGHT
zone_scores: 1 HIGH, 2 UNKNOWN, 3 MEDIUM, 4 UNKNOWN, 5 HIGH
icp_match: ICP1 Independent Cemetery (at site level, after the acquisition)
fit_narrative: One cemetery site with 14,000 plots on paper plat maps (illustrative) and a new owner inside 24 months. Zones 1 and 5 are HIGH and no must-have zone is LOW. Harborline's type and system are [Unknown] and are checked first.
next_action: BDR (name not on record) confirms Harborline's ownership type and system by 2026-10-22 (illustrative), the earlier date set by Trigger Event Outbound (04, Step 1c)
report_path: none (inline)

Example 3: MANUAL REVIEW On An Inbound Request (Sable Fork Cemetery)

Context: One cemetery site with 2,900 plots. The plot list is kept in a spreadsheet. The general manager, Arlen Biggs, signs contracts under $25K [CRM] (illustrative). The cemetery requested a demo through the website form on Thursday 2026-10-15, four days before this run. Who filled in the form is [Unknown]. Status: INBOUND.

Input: "Qualify Sable Fork Cemetery from their inbound request."

Process: The account is ICP1. The Fit Grid row (profile: Fit Grid) is Strong on plot count (2,900 is above the 2,000-plot line) and Moderate on records format (a spreadsheet). The inbound request shows interest. It does not raise any zone score.

Criteria (ICP1), 5 of 8 STRONG or PARTIAL, 2 UNKNOWN:

Zones:

Verdict: MANUAL REVIEW. One zone is HIGH (3), so GREENLIGHT is not met. No must-have zone is LOW, so DISQUALIFY is not met. The 8-criteria scorecard reads 5 of 8 criteria STRONG or PARTIAL with 2 UNKNOWN. That is recorded in fit_narrative and does not set the verdict.

Risk Flags: The inbound form's author is [Unknown]. The LOW pre-need answer rests on the CRM record, so the author does not change it, but the BDR confirms the form's source before it moves any decision.

Opportunity Signals: The inbound request itself, [CRM], received 2026-10-15.

Next Action: BDR (name not on record) replies to the Sable Fork demo request and asks in the same message who filled in the website form, what their role is, and who maintains the plot list, by 2026-10-20 (illustrative), a Tuesday. The account wrote to us, so the reply is owed. It is due the next business day after the run date of 2026-10-19, which replaces the five-day default, and it comes first because a reply owed to a buyer ranks above the verdict step. The answers settle the two UNKNOWN criteria and the open form-author fact, and the verdict is re-run only if a zone changes.

Hand-off (read by 02):
account: Sable Fork Cemetery (INBOUND)
run_date: 2026-10-19
verdict: MANUAL REVIEW
zone_scores: 1 MEDIUM, 2 LOW, 3 HIGH, 4 MEDIUM, 5 LOW
icp_match: ICP1 Independent Cemetery
fit_narrative: One cemetery site with 2,900 plots on a spreadsheet (illustrative), and a general manager who signs under $25K (illustrative). One HIGH zone and no must-have zone at LOW, so MANUAL REVIEW. Pre-need is none and plot sales are flat for three years, both on the CRM record (illustrative). The inbound form's author is [Unknown].
next_action: BDR (name not on record) replies to the demo request and asks who filled in the form, by 2026-10-20 (illustrative)
report_path: none (inline)

Example 4: DISQUALIFY, A Public Consolidator (Northvale Memorial Holdings)

Context: A public consolidator with about 240 funeral homes and 90 cemeteries. It runs its own in-house system [Public: annual filing]. Status: OUT. OUT is not LOST. There is no closed-lost record, and nothing has been lost, because the account was never a fit.

Input: "Qualify Northvale Memorial Holdings for fit."

Process: Step 2 matches the account to the ICP3 Multi-Location Group weak row (profile: Fit Grid), which names a public or PE-backed consolidator running its own system as a disqualifier. The disqualifier applies (profile: Qualification Criteria), so the zones are recorded but not weighed. Step 3 is not scored past the disqualifier check.

Zones (Recorded, Not Weighed):

Verdict: DISQUALIFY, on the disqualifier. Reverse only if the company stops running its own system, which the filing does not suggest. The disqualifier is [Public: annual filing], and that filing is the source to cite.

Risk Flags: No Fit Indicator. It points at the disqualifier clause, which is the reason for the verdict.

Next Action: No outbound. BDR (name not on record) logs the disqualifier and its filing source in the CRM by 2026-10-26 (illustrative), a Monday, five business days after the run date of 2026-10-19, so no rep re-qualifies the account from scratch. The rep does the logging, not this skill.

Hand-off (read by 02):
account: Northvale Memorial Holdings (OUT)
run_date: 2026-10-19
verdict: DISQUALIFY
zone_scores: 1 UNKNOWN, 2 UNKNOWN, 3 UNKNOWN, 4 LOW, 5 UNKNOWN
icp_match: No Fit, ICP3 Multi-Location Group disqualifier (public consolidator running its own system)
fit_narrative: About 240 funeral homes and 90 cemeteries, running its own in-house system `[Public: annual filing]`. The disqualifier applies (profile: Qualification Criteria), so the zones are not weighed. Status OUT, not LOST.
next_action: BDR (name not on record) logs the disqualifier and its filing source in the CRM by 2026-10-26 (illustrative)
report_path: none (inline)

---

Common Patterns

Pattern: Batch Qualification

When: The user provides a list of 5 to 20 accounts to qualify.

Approach: Run the abbreviated qualification (Steps 1 to 3 only) for each account, and produce a ranked summary table with the count of criteria and the tags. Then deep-dive the top 3 to 5 accounts with the full scoring, Steps 4 to 6. Reason: the zone table is the expensive step, and it is worth the time only for the accounts a rep will work.

Pattern: Active Deal Guard (BDR)

When: The user is a BDR and the account has an active AE deal.

Action: List the account in a separate "Active Deal Exclusions" table, with the account, the deal stage, the AE owner and the recommended action. Do not include it in the BDR's outbound queue. Recommend sharing the intelligence with the AE instead. Reason: two people writing to one buyer costs the deal.

An account pending AE assignment is not ACTIVE. Score it, and say that it is pending.

Pattern: ENGAGED Account

When: The account is ENGAGED: it replied or met with us, and no deal is open. The BDR or AE is already in a conversation with it.

Action: The verdict does not change, because the zones decide it. The next step does. The rep who holds the open thread answers it and books the next step, and this skill does not start a new cold sequence. A BDR books the AE's discovery through that thread, and the AE continues the conversation before any new outbound. Reason: a cold message to an account already talking to us reads as not listening, and it can undo the reply.

INBOUND Is Not ENGAGED: An account that asked us first stays INBOUND under the status rule, even after the rep answers, until a deal opens or the account goes OUT.

---

Troubleshooting

---

Best Practices

Do's

• Label Every Fact with one of the six tags. A reader should see where each fact came from without asking.
• Use Every Revenue Method You Have and say which one produced the figure.
• Check For Active AE Deals before recommending BDR outbound. Reason: a second contact on an open deal costs it.
• Show All Five Zones beside the verdict, every time. Reason: the next skill reads why the verdict landed where it did.
• Name The Open Facts that could change the verdict, and the fact that would settle each one.

---

Integration With Other Skills

Reads From: No other skill. The client profile is the only input, through the sections named in Context.

Hands To Account Snapshot (02): verdict, zone_scores, icp_match, fit_narrative. Snapshot reads them by these names.

Also Read By Daily Prospecting (07): the Fit Grid section, from the profile directly (profile: Fit Grid). It is not a hand-off field, because 07 scores from the profile, not from this skill's output.

Hands To Wrap-Up At The Close: report_path when a file was written, the verdict or score, and next_action with its owner and date.

Next Steps By Verdict:

• After GREENLIGHT, run Account Snapshot (gtm-account-snapshot) to build prospecting intelligence and outbound sequences.
• For a public company, Research Outbound (03) builds point-of-view sequences from financial filings.
• Once an opportunity exists, Deal Pulse (08) replaces qualification with deal health monitoring.
• When an incumbent is named, Competitive Displacement (12) builds targeted sequences.

Chains

• Qualify To Book: Account Qualification (01, this skill, first), then Account Snapshot (02), Research Outbound (03) or Trigger Event Outbound (04), then Meeting Prep (06). This skill adds the verdict and the five zone scores that every later skill reads.

---

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. Step 6 item 12 drops "with no separate date" and "a later date set by a record" for the due-date test, so a same-person ask due by the next action's date travels with it. 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.

2.1.13 (2026-10-26)

• Competitor Lock-In has a trigger the records can meet, in the Step 5 table. An incumbent with a renewal date on record, and a switching cost on the profile's Competitive Landscape row for that incumbent, names the flag. The switching cost is cited to that row with its grade, because a record seldom states a term.
• Example 1 cites the Oldgate switching cost to the Competitive Landscape row. Its Zone 3 board timing is a dated next board meeting, 57 days after the run date, not the words of the Zone 3 cell.
• The try-it records state the owner's retirement date and the decision path as facts. The board timing is a dated meeting. Verdict, zones, count, next action and the promised flags are unchanged.

2.1.12 (2026-10-26)

• Output Contract and Step 6 item 12 state one next-action priority order: a reply owed to a buyer who wrote to us, then AE coordination for an ACTIVE account with an AE owner, then the verdict's step. The order gives its reasons, the tie rule, and the rule that a same-person ask with no separate date travels with the next action.
• Step 6 item 12 names the owner from the record. A role is written with "name not on record" and the missing name is an open fact.
• Step 1B states that the status on the record dated the run date governs, and a later-dated profile status does not apply to an earlier run.
• ICP2 criteria 1 (Sub-Vertical Match), 3 and 8 gain rating rules. Criteria 3 and 8 apply to the ICP1 table too.
• Step 2 states how a Fit Grid cell is written when the records cannot decide it (Unknown), and that it does not move the row.
• Step 4 states the year-only date rule and the digital-tool rule for Zone 4.
• Step 6 item 9 lists every risk flag that applies, with Approval Above Signing Line named.
• Example 1 re-cites the criterion 1, 3 and 8 evidence, the Zone 4 digital-tool reasoning, and the three risk flags. Examples 1 to 4 re-derive their next actions. Example 2 makes the Corrow Ridge check the GREENLIGHT's first move. Example 3 makes the Sable Fork reply, which is owed to a buyer, the next action. Their verdicts, zones and counts are unchanged.
• The try-it promise changes its owner, its single move and its risk flag list. Its verdict, zones and count are unchanged.

2.1.11 (2026-10-26)

• Criterion 5 of ICP2 (Transaction Complexity) has a counting rule: complexity signals on record decide STRONG, PARTIAL or UNKNOWN, so the count does not rest on a judgment about "complex". Criterion 6 (Relevant Department Exists) reads a named role by whether its title covers a Product Module's function. Step 3 names both rules with criteria 2, 4 and 7.
• Step 3 says the count feeds the ICP and the fit narrative, and does not gate the verdict.
• Step 4 states that a zone with only a named staff condition met scores MEDIUM, because LOW needs a LOW condition on record.
• Step 4 states how the year-one signing amount is derived from the profile's list price.
• Step 6 says that every account meeting neither GREENLIGHT nor DISQUALIFY is MANUAL REVIEW, including one HIGH zone with a must-have at MEDIUM.
• Example 1 shows the criterion 5 signals, the criterion 6 rule, the dated double sale, the Oldgate licence date and the year-one arithmetic. Its verdict, zones and count are unchanged.
• The try-it records gain the tag on the type line, the dated double sale, the Oldgate licence date, the pre-need fact and the pricing facts. The pre-computed year-one figure leaves the records.

2.1.8 (2026-10-26)

• Every profile citation is written (profile: Section), naming the real section, in the Overview, the steps, the examples and the hard rules. Template placeholders and the shared contract are unchanged.
• ENGAGED is added to the status list in Step 1b, the Summary Report and the Quality Bar, which read six words. An ENGAGED account gets a pattern that continues the open thread, and the BDR and AE next steps in the Verdict Framework point to it. The verdict itself does not change with status.
• Headings and labels are capitalized word by word, and the Example headings follow the same rule.
• Example 1 cites the $25K line to the profile, not to the board calendar, and the year-one cost sits beside it.

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.
• Sub-Vertical Match states its fallback when the profile holds no priority list. Step 3 counts the four ICP2 criteria that need a rule, as its own paragraph lists them.
• Step 4 states how a named staff member scores a zone, how an unknown HIGH condition scores, and when a zone is UNKNOWN.
• The next-action date in the Summary Report points to the shared rule instead of restating it.
• The try-it records state facts only. The stage note and the board-line comparison are removed.

2.1.6 (2026-10-26)

• The ownership-check next action defers to the earlier date that the Trigger Event Outbound schedule sets for that step, and names its source, under the shared next-action rule.
• Example 1 names the current system as a record fact, so its Zone 4 MEDIUM cell rests on a recorded system.
• Example 3 cites the CRM record for the pre-need and site-budget facts, and the Zone 5 condition names the record facts that hold it.

2.1.5 (2026-10-26)

• The Zone 3 row of Example 1 quotes the profile's Zone 3 cell as written, and the board timing is named as the part of the HIGH cell that is not met.
• 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 skill's own within-five-days wording is replaced by a pointer to that rule, and the example dates are recomputed under it.
• The Verdict Rule paragraph in Step 6 states that an UNKNOWN zone counts as neither HIGH nor LOW, as the profile states it.

2.1.4 (2026-10-26)

• Try-it evidence completed so a strict first run reproduces Example 1.
• Step 2 gains one sentence: a Fit Grid row is recorded at the level its key indicator meets, and each other cell is quoted with its own level.
• Step 3 replaces the ICP2 criterion 2 rule with the profile's ICP2 threshold test, and gains a rule for criterion 6 that reads a named role by whether its title covers the function.
• Step 4 gains one sentence: a named pre-need manager counts as pre-need staff for the counselor condition, and the conditions that fall short are named.
• Step 5 gains a risk flag for an approval step above the signing line.
• Step 6 gains a date rule for the next action, in the Summary Report and the Output Contract.
• Step 2 assigns the Size Band with the market segment, read from the profile's Size Bands.
• Example 1 gains the plot count on the cemetery side, the open-deal check and the aligned next action wording, and its criterion 2 is evidenced against the threshold. The try-it records gain the same facts.

2.1.3 (2026-10-26)

• Try-it evidence completed so a strict first run reproduces Example 1.
• Step 3 gains one paragraph settling ICP2 criteria 2, 4 and 7: the CRM revenue range rule, the family-owned rule and the dated-trigger rule.
• Step 4 gains one sentence: a hedged statement such as "may retire" is not a met HIGH condition. The partial-match paragraph is split from the Zone 3 sentence, with no wording changed.
• Example 1 gains an ownership fact (family-owned, public source) and a dated retirement plan (owner bio). Its Zone 5 row and criterion 4 row cite them. The owner's hedged line in the try-it records is replaced by the dated plan.

2.1.2 (2026-10-25)

• Try-it evidence completed so a strict first run reproduces Example 1.
• Revenue Threshold (criterion 2) is evidenced by a CRM revenue range, which is a Step 1e method. Site count is not a Step 1e method, so it is removed from Example 1.
• Step 4 gains one sentence on partial column matches: a zone with some HIGH conditions met and no LOW condition scores MEDIUM, and the report names the failed condition. Example 1's Zone 4 gains the staff-email fact that makes it a partial match.
• Step 6 gains one sentence: a Moderate Fit Grid cell does not block GREENLIGHT when the ICP definition is met with evidence.
• Example 1 gains the user's role (Step 0) as BDR.

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 base and offers read-only CRM and call connectors through the shared contract's new Knowledge Base and Connectors section. Adds a Chains subsection that places the skill in Qualify To Book. 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.

2.0.0 (2026-10-20)

• Moved to the Sales 2.0 standard: Overview with Core Principle, Why This Skill Exists, Role, Input and Output Contracts, Context with the Shared Contract, Core Workflow with a Produces line per stage, Epistemic Rules, Hard Rules with reasons, Quality Bar, and Integration with named hand-off fields.
• The zones, the Verdict Rule and the Fit Grid are read from the profile, and every verdict shows all five zones beside it.
• The evidence labels are replaced by the six shared tags. "Confidence Level" is replaced by the open facts, because the tags carry the confidence.
• The verdict comes from the profile's Verdict Rule alone. The criteria-count gate and the critical-flag gate are removed. No Fit Indicator and Previous DQ point at the Verdict Rule's disqualifier clause.
• The old artifact section is removed. The file is Markdown, written only when asked. The HTML and PDF card options are removed.
• Revenue estimation labels are replaced by the tags. Requires is empty, because this skill reads no other skill's output.
• Examples: Brackhaven is added as the chain 1 opener, and all four examples sit on the PlotIQ cast with zone and criteria tables. Sable Fork and Corrow Ridge zones follow the chain file. Each example ends with its hand-off block.

1.3.0 (2026-10-13)

• Examples re-cast on the PlotIQ example company. Zone conditions follow the profile's Verdict Rule. Step 1d wording made vertical-neutral.

1.2.0 (2026-09-29)

• Worked examples moved to a single example company. Em dashes removed from prose.

1.1.0 (2026-07-06)

• Restructured around the five-part skill anatomy. Client-specific data moved to the shared client profile. Framework machinery moved to a Methodology section.

1.0.0 (2026-03-04)

• Initial release. Eight-criteria scoring, a five-zone assessment, a verdict framework and role-aware recommendations.