agentleFS
heypastelheypastel/pastel-outbound-system/skills/fit-check/SKILL.md

fit-check

Skill2 starsChanged 57 days agoMITView on GitHub

Gatekeeper — answers yes, maybe, or no for each lead against the outbound brief, using Pastel's match reasons, and shows the reason so the user can overrule it. Use on any list before research or writing, for "are these a fit", or to clean a lead list.

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read Pastel's match reasons with pastel_get_details (five at a time), then:

    line 14

≈ “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

Fit check — Gatekeeper

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

Pastel already scored each lead against the ICP definitions. This skill adds the user's own brief on top, and makes every verdict readable.

Three gates

Read Pastel's match reasons with pastel_get_details (five at a time), then:

  1. Account gate — would this company appear in the market map? Sector, headcount, and country inside the lines; not a current customer; not on the off-limits list.
  2. Person gate — is this role close to the problem we solve? Read what the headline says they work on, not just the title: a "Head of Partnerships" rarely touches the tools a sales-tooling product replaces, even at the right company.
  3. Timing gate — is the signal still alive? Activity older than 60 days, or a role change older than 6 months, closes the gate unless something newer reopens it.

Yes = all three open → why-now. No = a gate is closed. Maybe = a gate can't be judged from what Pastel holds → listed separately with the one question that would settle it, for the user to decide.

Each verdict shows its reason in one line, so the user can overrule any of them at a glance. For the no group, prepare one batched mark_lead_status → NOT_INTERESTED request, sent after approval.

Output

# Fit check — [date]
Yes: n · Maybe: n · No: n

| Person | Company | Account | Person | Timing | Verdict | Reason |

Maybe — needs your call:
- [Person]: [the open question]

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.