agentleFS
heypastelheypastel/pastel-outbound-system/skills/buying-committee/SKILL.md

buying-committee

Skill2 starsChanged 58 days agoMITView on GitHub

Detective — maps who else matters at a target account (signer, hands-on user, fan, skeptic) from the people Pastel already found there, so outreach reaches more than one person. Use for "who else should I talk to at [company]", key or high-value accounts, or when a single contact went quiet.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Order of approach: start with whoever has the freshest signal, then work toward the signer.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Buying committee — Detective

House rules: ../command-center/shared/house-rules.md · Pastel tools: ../command-center/shared/pastel-tools.md

Deals rarely hang on one person. When one lead at an account looks promising, find who else is part of the decision — among the people Pastel already knows.

Steps

  1. Everyone Pastel knows at the account: pastel_query_leads(search="<company name>"), then pastel_get_details for the matches. Pastel can't search LinkedIn for people it hasn't found — say so when the committee is incomplete, and suggest market-map to add an agent watching that company's team.
  2. Give each person a seat:
    • Signer — the budget is theirs;
    • Hands-on user — does the work our product changes;
    • Fan — already reacted to something in public (their Pastel signal);
    • Skeptic — owns the tool or process we'd replace, and has most to lose.
  3. Order of approach: start with whoever has the freshest signal, then work toward the signer. Talk to the skeptic before they hear about us secondhand. Explain the order in one line for this account.
  4. One angle per seat: the signer hears about the business result, the hands-on user about their week, the fan about what they already said, the skeptic about what stays the same for them. Each angle goes to message-writer with the seat noted.
  5. No pile-on: at most one first message per account per week, so two colleagues don't compare identical notes.

Output

# Buying committee — [company]

| Seat | Person | Headline | Signal | Angle | Order |

Missing seats: [who we'd need and don't have]
Open questions:

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.