agentleFS
Sign inStart free
automatewithudayautomatewithuday/gtm-prospecting-system/CLAUDE.md

gtm-prospecting-system

CLAUDE.md1 starsChanged 56 days agoMITView on GitHub

20 stage skills + one orchestrator in skills/. To run the workflow, follow skills/prospecting-system/SKILL.md; it is the source of truth for stage order, file names, columns, gates, and operating rules.

  • Reads credentials

The file

We split this CLAUDE.md 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:

    After editing any skill: bash scripts/validate.sh.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

Prospecting System

20 stage skills + one orchestrator in skills/. To run the workflow, follow skills/prospecting-system/SKILL.md; it is the source of truth for stage order, file names, columns, gates, and operating rules.

  • Runs live in runs/<run>/ (git-ignored). After each stage: update state.json, then uv run scripts/check_run.py runs/<run>.
  • engine/ is vendored verbatim from GTM-Skills. Scripts import each other by relative path — never rename or move anything in it. Read engine/list-builder/RUNBOOK.md before running an engine script.
  • Spend cap in state.json is hard. Estimate, count, then call. Never loop around a cap or a provider limit.
  • Propose, don't edit, anything a human decided: 02-client-profile.yaml, judge prompts, score weights, segments, copy frameworks, thresholds inside skills.
  • Per-row bulk work (judging, classifying, personalizing) → Haiku sub-agents in batches, after a human approves a sample.
  • Python via uv only. Secrets only in .env; never print them. Quote paths — they may contain spaces.
  • After editing any skill: bash scripts/validate.sh.

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