Systems Lab

Agent skill

contact-sourcer

Source people at target companies (capability people_search) and write them to storage at stage 'sourced'.

activeSelf-containedDeclared tools62 words

Filed under CRM and RevOps.

From kkrlstrm/gtm-pipeline · 9 skill entries · 16 · pushed 2026-09-29

What it does when it runs

Source people at target companies (capability people_search) and write them to storage at stage 'sourced'. Runs the configured people_search waterfall, backfills domains, dedups, and cross-references the master DB. Use when the user wants to "source contacts", "find people at these companies", or run only the sourcing stage.

Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
  • Read
  • Bash
  • WebSearch
  • WebFetch
Actions present in the files
shellnetwork

Ask about contact-sourcer

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗
git clone --depth 1 --filter=blob:none --sparse https://github.com/kkrlstrm/gtm-pipeline.git /tmp/gtm-pipeline
git -C /tmp/gtm-pipeline sparse-checkout set ".claude/skills/contact-sourcer"
mkdir -p ~/.claude/skills/contact-sourcer
cp -R "/tmp/gtm-pipeline/.claude/skills/contact-sourcer/." ~/.claude/skills/contact-sourcer/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

The skill

Source on GitHub ↗

Reproduced in full from kkrlstrm/gtm-pipeline/blob/3fdc07a14e4f3991eba66ec2e8a9feb8fec4a197/.claude/skills/contact-sourcer/SKILL.md, which is licensed APACHE-2.0 (repository). 62 words, 0 headings.

Input (companies + persona/titles + geography, and optionally an existing list_id): $ARGUMENTS

Execute the contact sourcer: read agents/contact-sourcer/agent.md and follow it exactly — bootstrap (config + context + resolve the people_search waterfall from keyed providers), source per provider via their manifests, backfill domains, dedup + crossref_master, then write via storage/cli.py (create_list if needed, upsert_contacts). Report the waterfall table and the resulting list_id.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what contact-sourcer does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.