agentleFS
keinsaasforeverkeinsaasforever/gtm-pipeline-skills/CLAUDE.md

gtm-pipeline-skills

CLAUDE.md75 starsChanged 35 days agoMITView on GitHub

This repo contains 10 Claude Code skills for B2B lead generation pipelines. All skills use the gtm-pipeline: prefix. Invoke them with /gtm-pipeline:<skill-name>. Skills chain together — each outputs a CSV that becomes the next skill's input: The pipeline skill orchestrates this sequence. The demo skill runs a condensed version for ~10 contacts. Each project lives in a {slug}-gtm/ directory (created by the setup skill): - context/icp.md — ICP definition (job tiers, industries, locations, size filter) - context/profile.md — what the…

The file

We split this CLAUDE.md into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are 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.

  • 3

    Very specific

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

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

    All skills use the gtm-pipeline: prefix.

    line 7
  2. Very specific:

    All CSV outputs use snake_case.

    line 42
  3. Very specific:

    Run /gtm-pipeline:setup — it handles installation verification, API key configuration, PhantomBuster agent lookup, and first client ICP …

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 28,029 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

GTM Pipeline Skills

This repo contains 10 Claude Code skills for B2B lead generation pipelines.

Skill Namespacing

All skills use the gtm-pipeline: prefix. Invoke them with /gtm-pipeline:<skill-name>.

How Skills Relate

Skills chain together — each outputs a CSV that becomes the next skill's input:

company-search
    → company-enrichment (+ ICP scoring)
        → signal-search
        → people-search
            → contact-filter
                → people-enrichment
                    → outreach

The pipeline skill orchestrates this sequence. The demo skill runs a condensed version for ~10 contacts.

Per-Project Work

Each project lives in a {slug}-gtm/ directory (created by the setup skill):

  • context/icp.md — ICP definition (job tiers, industries, locations, size filter)
  • context/profile.md — what the company sells, value prop, tone
  • csv/ — input, intermediate, and output CSVs

See examples/sample-client-gtm/ for a fully filled-out reference.

Shared Configuration

  • skills/_shared/conventions.md — field naming, terminology, provider disambiguation
  • skills/_shared/phantombuster.md — PB API patterns and agent config key reference
  • skills/_shared/local.md — personal config (gitignored): PB agent IDs, GTM_ENV_PATH

Field Naming Convention

All CSV outputs use snake_case. Provider-native names are mapped on ingestion. See the Canonical Field Names table in _shared/conventions.md.

New to this repo?

Run /gtm-pipeline:setup — it handles installation verification, API key configuration, PhantomBuster agent lookup, and first client ICP setup.

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.