Systems Lab

Skill library

b2bforce/b2bforce

Publisher description: Skills + workspace for AI agents in B2B service firms

Catalogue scope: 35 procedural entries from 35 source paths.

MIT

Publisher site ↗

Repository health

GitHub’s own figures, read from its REST API. Commit and contributor totals come from the paging header rather than an estimate.

Repository metadata checked 2026-11-02 · skill files extracted 2026-11-02 · published 2026-09-05

Extraction and automated analysis describe the files at the recorded revision. They are not an editorial review or a test of the skills in use.

Stars
2
Commits
29
Last 90 days
17commits
Contributors
1
Last push
2026-10-19
First commit
2026-06-06repo created

35 skill entries

  • client-account-plan

    Map an account's buying committee and build expansion hypotheses from the firm's services this client has not bought, each with a trigger that says when to raise it. Use for account planning, expansion or cross-sell planning, or when asked where growth in the existing client base could come from.

    Self-containedInstructions only1,014 words
  • client-health-review

    Sweep every client folder and report what needs attention — renewals inside 90 days, accounts in their first 90 days, missing success definitions, accounts with no QBR in two quarters, unfilled proof stubs, stale reviews, and referral-ready accounts. Use for portfolio review, retention review, or before starting new prospecting.

    Self-containedActs undeclared1,109 words
  • client-onboarding

    Turn a won deal into a first-90-days plan with a written success definition, named stakeholders and what each judges success by, and checkpoints at day 14, 30, and 90. Use right after a win, when a new client starts, or when an existing account has no agreed definition of what success means.

    Self-containedInstructions only1,102 words
  • client-qbr

    Prepare a quarterly business review for one client — delivered versus what was promised, scored against the success definition agreed at onboarding, then the next quarter, an expansion ask, and a referral ask. Use for QBRs, quarterly or renewal reviews, or account check-ins.

    Self-containedActs undeclared1,133 words
  • firm-context

    Create and maintain the firm profile for a professional service firm skills + workspace repo. Use when starting a new firm repo, onboarding, missing business context, or before any marketing/sales/intelligence skill. For competitor monitoring, see intel-competitor-monitoring.

    Self-containedInstructions only865 words
  • firm-pdca-cycle

    Run one Plan-Do-Check-Act cycle for a PDCA area in workspace/pdca/, ending in a measured result and an explicit decision. Use when the user wants to plan a measurable experiment, record what was done, check the outcome against a baseline, close a cycle, or asks whether previous work actually worked. Requires an area created by firm-pdca-setup.

    Self-containedInstructions only1,447 words
  • firm-pdca-eval

    Independently evaluate a PDCA cycle against the acceptance criteria written before the work started, using deterministic checks first and an LLM judge second. Use before a cycle's Check, when verifying whether work actually met its criteria, or when a result needs a second opinion that is not the executor's.

    Self-containedInstructions only904 words
  • firm-pdca-setup

    Set up a files-only PDCA measurement area for one process or outcome in a professional service firm — outcome, metrics, direction, source of truth, cadence, and baseline. Use when the user wants to measure whether marketing, sales, delivery, or content work actually moves a business outcome, or asks for KPIs, a scoreboard, or a measurement loop. Read firm profile first.

    Self-containedInstructions only1,343 words
  • intel-ai-visibility

    Track whether answer engines name the firm — build a versioned panel of buyer-intent prompts, run them across ChatGPT/Claude/Gemini/Perplexity, and roll results into a share-of-answer table with citation rate and named competitors. Use for AI visibility, GEO/AEO monitoring, "do LLMs recommend us", or answer-engine share of voice.

    Self-containedActs undeclared1,651 words
  • intel-competitor-discovery

    Discover new competitors via SERP results for a search phrase and location, deduplicate by root domain against already-monitored accounts, and propose candidates to add to monitoring. Use when the user wants to find competitors, research the market, or seed the monitoring list. Read firm profile first.

    Needs a keyActs undeclared649 words
  • intel-competitor-monitoring

    Files-only competitor website monitoring for a shared B2BForce workspace. Use to maintain competitor profiles, monitored page lists, page snapshots, change notes, and weekly report inputs under workspace/intelligence/. Read firm profile first; for firm profile setup, see firm-context.

    Reaches the webInstructions only990 words
  • intel-weekly-report

    Generate a weekly competitive-intelligence report from monitored competitor page changes within a date range, with an AI business-impact summary and per-page change list. Use when the user wants a weekly digest, monitoring summary, or shareable intel report. Read firm profile and monitoring files first.

    Self-containedInstructions only625 words
  • marketing-company-profile

    Create, enrich, or refresh workspace/firm/profile.md from a company website URL. Use during setup after firm-context interview, or later when the firm's website, positioning, proof points, or target market changed.

    Self-containedInstructions only719 words
  • marketing-content-blog-post

    Write an 800-1500 word B2B blog post in Markdown from a content idea. Use when content_type is blog_post. Applies stage-specific frameworks and Exa reference articles. Output to workspace/marketing/content/drafts/blog/. For LinkedIn or X use marketing-content-linkedin-post or marketing-content-x-post instead.

    Self-containedInstructions only443 words
  • marketing-content-case-study

    Write a B2B case study (500-1500 words, PASTOR framework) from a content idea. Use when content_type is case_study and buying_stage is decision or vendor. Uses Exa reference articles. Output to workspace/marketing/content/drafts/case-studies/.

    Self-containedInstructions only547 words
  • marketing-content-consistency

    Review pass 2 for long-form content: inventory every claim with its paragraph, then find pairs that contradict each other, mismatched numbers, counters that do not match ("five steps" with four), broken cross-references, examples that break the text's own rules, sections that undercut the idea's angle, and repetition. Report only. Use to check whether a draft contradicts itself, find repetition, or check that a post holds its angle.

    Self-containedInstructions only625 words
  • marketing-content-deslop

    Review pass 3 for content: detect AI-writing patterns in English or Polish prose, score the text 5×10 against a 35/50 threshold, and in rewrite mode fix the flagged places without changing facts, links, markers, or frontmatter. Use to deslop a draft, remove AI-isms, check whether a post sounds generated, or humanize a draft — blog, case study, service page, LinkedIn, or X.

    Self-containedInstructions only669 words
  • marketing-content-factcheck

    Review pass 1 for long-form content: list every claim in a draft (numbers, names, dates, quotes, product capabilities, causal claims, claims about what others write), fetch the source of each again, and rate it match, paraphrase ok, distorted, not found, rejected source, or no source. Report only — never edits the draft. Use to fact-check a blog post or case study, verify statistics, or check that sources say what the text claims.

    Self-containedInstructions only604 words
  • marketing-content-ideas

    Generate B2B content ideas across buying stages and content types (blog, LinkedIn, X, case study, service-page opportunity). Use when planning a content calendar from ICP and service context. Requires firm profile, service, ICP, and persona files. For writing drafts use marketing-content-* skills per type.

    Needs a keyActs undeclared1,062 words
  • marketing-content-linkedin-post

    Write a LinkedIn post (150-250 words, plain text) from a content idea. Use when content_type is linkedin_post. No Exa research. Stage-specific frameworks apply. Output to workspace/marketing/content/drafts/linkedin/. Not for blog or X formats.

    Self-containedInstructions only273 words
  • marketing-content-reader-test

    Review pass 4 for long-form content: hand the draft to a separate agent with no conversation context, reading as the target persona, and ask whether it answers the title's question, what is unclear, where they would stop reading, which claim is weakest, what sounds generated, and whether it reads as an ad for the firm. Compares the angle they read with the idea's. Use for a reader test, to check whether a post is clear, or to get a fresh read before publishing.

    Self-containedInstructions only615 words
  • marketing-content-sources

    Collect the facts a long-form draft may state and write {slug}.sources.md, where every claim has a source fetched in this session, a verbatim excerpt, a type, a tier, and an access date. Prefers primary sources, treats echoes as one source, and sends anything unsupported to the user instead of into the draft. Use before writing a blog post, case study, or service page, or when asked to research a post, find sources, or back claims with data.

    Self-containedInstructions only779 words
  • marketing-content-x-post

    Write an X (Twitter) post or thread from a content idea. Use when content_type is x_post. Max 280 chars per tweet, no external links in body. Output to workspace/marketing/content/drafts/x/. For LinkedIn use marketing-content-linkedin-post.

    Self-containedInstructions only275 words
  • marketing-geo-placement

    Turn the domains answer engines actually cite into a ranked backlog of surfaces to get onto — listicles, directories, communities, review sites — each with an owner, a next action, and a status. Use after intel-ai-visibility, or when asked how to get recommended by AI, mentioned in LLM answers, or onto third-party rankings.

    Self-containedInstructions only1,063 words
  • marketing-icp

    Create or enrich an Ideal Customer Profile and 1-3 buyer personas for a B2B service. If the service is missing, first create it from a URL, text description, or both via marketing-service. Use when ICP/personas are missing before content, landing pages, or prospecting. Output to workspace/marketing/icp/.

    Self-containedActs undeclared675 words
  • marketing-positioning

    Work out a positioning statement for the whole firm, one department (several services), or one service: list what buyers chose instead of the firm, the differences against those alternatives, a proof record for each difference, and only then the one-sentence statement. Use when positioning is missing, reads like every competitor's, a service or department needs its own "why us", or the user asks for a positioning statement, differentiation, or "how do we stand out".

    Self-containedActs undeclared1,084 words
  • marketing-seo-research

    Research SEO keywords and search metrics for a topic (DataForSEO with AI research fallback), then produce an SEO context block and a target keyword for content. Use when the user wants keyword research, SEO data, or a target keyword for a content idea or draft. Read firm profile for industry/location.

    Needs a keyActs undeclared643 words
  • marketing-service

    Create, enrich, or refresh a B2B service definition in workspace/firm/services/ from a URL, a text description, or both. Use when a service is missing, incomplete, or outdated before ICP generation.

    Self-containedInstructions only792 words
  • marketing-service-page

    Create or refresh a standalone B2B service page from a service brief, URL, existing service file, or a mix of inputs. Use when the user wants a landing page/service page without first creating a content idea. Output to workspace/marketing/landing-pages/{slug}/.

    Needs a keyInstructions only531 words
  • sales-bid-qualification

    Decide bid, no-bid, or conditional on one opportunity by scoring the discovery brief against the service fit criteria and the ICP anti-fit criteria. Use before writing a proposal, when deciding whether to answer an RFP, or when the pipeline holds more requests than the firm can serve well.

    Self-containedInstructions only1,006 words
  • sales-discovery-brief

    Turn call notes, an inbound email, or RFP text into a structured discovery brief for one opportunity, with a qualification verdict and the list of unanswered questions. Use when a prospect replies, a fit call happens, an RFP arrives, or before writing a proposal. Output to workspace/sales/opportunities/.

    Self-containedInstructions only989 words
  • sales-outcome-log

    Record how an opportunity ended — won, lost, or no-decision — with the reason and the competitor, then create the verified proof record on a win. Also backfills proof records for past engagements. Use after a proposal is decided, for win-loss review, or when the firm has client results nothing in the repo has captured.

    Self-containedInstructions only1,385 words
  • sales-proposal

    Assemble a B2B service proposal or SOW from the discovery brief, firm profile, service definition, ICP, and the verified proof library — with mandatory scope boundaries, assumptions, change control, and one pricing table. Use after a bid decision when the user needs a proposal, SOW, or RFP response.

    Self-containedActs undeclared1,504 words
  • sales-prospecting-sequence

    Generate a one-to-one B2B outbound email sequence for a service, ICP, and persona, with framework selection, cadence, proof/compliance guardrails, and ready-to-send email copy. Use when content_type is prospecting_sequence or the user needs outbound sales emails. Output to workspace/sales/prospecting/. Not for blog, social content, or newsletter campaigns.

    Self-containedInstructions only1,034 words
  • tool-dataforseo

    Fetch Google SERP results or keyword search-volume data via the DataForSEO API. Use when a skill needs competitor discovery (SERP), keyword research, or search metrics. Reads DATAFORSEO_LOGIN and DATAFORSEO_PASSWORD from .env.

    Needs a keyActs undeclared431 words

Ask about b2bforce/b2bforce

Opens your assistant with this page's recorded context. Check the linked sources before relying on it.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah

Need help setting it up?

This page tells you what b2bforce/b2bforce does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.

Build my GTM engine

Tell us what you want to improve. Fedor reviews the workflow and replies by email when there is a useful fit.

Fedor reviews every request personally. If there is a useful fit, he will reply by email.