agentleFS
Sign inStart free
youdcodeyoudcode/open-company/.agents/skills/prospect/SKILL.md

prospect

Skill2 starsChanged 53 days agoMITView on GitHub

Finds N new companies matching the ideal customer profile, each verified on its own website and recorded with sources through tools/leads.mjs, then scored. Use when the human types "prospect" or "prospect <n>".

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Check workspace/prospecting/icp.md exists and is filled.

    line 11
  2. Very specific:

    Search (web search, and node tools/registry-fr.mjs for France).

    line 15
  3. Very specific:

    Add leads in batches: write a JSON array to workspace/tmp/batch.json, then node tools/leads.mjs add --as researcher --file …

    line 19

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “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

Prospect

Input: a number N (default 10) and optionally a segment. Role: researcher (delegate to the researcher subagent if your tool has one, otherwise follow roles/researcher.md yourself).

  1. Check workspace/prospecting/icp.md exists and is filled. If not, run the setup skill first.
  2. node tools/board.mjs add "Prospect <N>: <segment>" --role researcher then move it to doing.
  3. Budget: about 3 searches per lead found, and stop at N. Tell the human if the segment is too narrow instead of lowering the bar.
  4. Search (web search, and node tools/registry-fr.mjs for France). Collect candidates, remove those already in node tools/leads.mjs list.
  5. For each candidate: confirm on its own website. Write workspace/prospecting/accounts/<id>.md from templates/docs/account.md (id = the slug of the company name, as tools/leads.mjs creates it).
  6. Add leads in batches: write a JSON array to workspace/tmp/batch.json, then node tools/leads.mjs add --as researcher --file workspace/tmp/batch.json. Fix and retry rejected ones.
  7. node tools/score.mjs --as researcher.
  8. Move the card to done, handoff to sales with the count of hot and warm leads, log the end.
  9. Report to the human in 5 lines max and point to the Pipeline tab of the live page.

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