agentleFS
Sign inStart free
prosyo-aiprosyo-ai/gtm-skill/skills/buying-committee-mapper/SKILL.md

buying-committee-mapper

Skill13 starsChanged 24 days agoMITView on GitHub

Use this skill when a B2B deal or target account needs more than one contact: \"who else should I talk to\", \"map the buying committee\", \"multi-thread this deal\", or a single-threaded deal is at risk. Maps the economic buyer, champion, influencers, users, technical evaluator and blockers, names the likely people and titles, scores coverage and sentiment, and produces a multi-threading plan with what each person needs to hear and who should reach them.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this whenever a deal depends on one person.

    line 16
  2. Distinctive:

    MUST mark each person as confirmed or inferred.

    line 70
  3. Distinctive:

    MUST flag any deal with a single engaged contact as at risk.

    line 71
  4. Distinctive:

    NEVER contact a new stakeholder in a way that undermines the champion without discussing it with them first.

    line 72

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Use this whenever a deal depends on one person. Single-threaded deals close far less often than deals with three or more engaged contacts, and they die quietly when the one contact changes jobs or goes quiet.

Inputs

  • The account or deal, its size and stage.
  • Contacts already engaged and what each has said.
  • The product and the departments it touches.

The play

1. List the roles the deal needs

RoleQuestion they answerTypical titles
Economic buyerIs it worth the money?VP, C-level, budget owner
ChampionWill this make my life and my team better?Manager or director who feels the pain
Technical evaluatorWill it work with what we have?IT, engineering, operations, RevOps
UsersWill I actually use it?Individual contributors
BlockersIs it safe and compliant?Security, legal, procurement, finance
InfluencersWhat do I recommend?Peers, advisors, adjacent team leads

Deal size sets how many roles show up: under $10k often 1-2 people; $10-50k usually 3-5; above $100k usually 6-10.

2. Name the people

For each role, find the most likely person at the account. Mark each as confirmed (they told you or you met them) or inferred (from the org chart or titles).

3. Score each contact

Engagement (none, aware, engaged, active) and sentiment (supporter, neutral, sceptic, unknown). An unknown blocker is the most dangerous cell on the map.

4. Plan the threads

For each gap, decide who reaches out (rep, manager, executive sponsor, solutions engineer), through which route (champion introduction is best, then direct), and what that person needs to hear in their own language.

5. Arm the champion

Give the champion the material they need to sell internally: a one-paragraph business case, the security pack, a short answer to the most likely objection from each other role.

Output format

Deal: <account> - <size> - <stage>
Committee:
  role | name | title | confirmed/inferred | engagement | sentiment | what they need
Coverage: <roles engaged / roles needed>  Risk: <single-threaded? unknown blocker?>
Plan: <next 3 actions with owner and date>
Champion kit: <items to send>

What good looks like

  • At least three engaged contacts before a deal is called "commit".
  • The blocker is identified before the proposal, not after.
  • Outreach to new contacts goes through the champion when possible, so it reads as collaboration rather than going around them.
  • The common mistake is mapping titles without talking to anyone: a map full of inferred names gives false comfort.

Rules

  • MUST mark each person as confirmed or inferred.
  • MUST flag any deal with a single engaged contact as at risk.
  • NEVER contact a new stakeholder in a way that undermines the champion without discussing it with them first.

Example prompts

  • "Map the buying committee for our $80k deal with Contoso. I only talk to the IT manager."
  • "Who else should I bring into this deal, and how?"
  • "Build a multi-threading plan for my top 5 deals."

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free