agentleFS
Othmane-KhadriOthmane-Khadri/YALC-the-GTM-operating-system/.claude/skills/find-lookalikes/SKILL.md

find-lookalikes

Skill298 starsChanged 6 months agoMITView on GitHub

Find companies similar to a seed domain via PredictLeads' similar_companies endpoint and persist them as a result set ready for enrichment or qualification. Use when the user says 'find lookalikes for [domain]', 'companies similar to [name]', 'show me lookalike accounts', 'expand from this company', or 'discover similar prospects'. Side-effecting — calls PredictLeads API and writes to local cache.

  • Reads credentials

The file

Files
SKILL.md

Find Lookalikes

I'll wrap signals:similar. Ask for a seed domain, shell out to PredictLeads, dedupe + cache, and surface the lookalike list as a result set.

When This Skill Applies

  • "find lookalikes for [domain]"
  • "companies similar to [name]"
  • "show me lookalike accounts"
  • "expand from this company"
  • "discover similar prospects"

NOT this skill (use prospect-discovery-pipeline instead):

  • "find prospects like our best client" — that's the full 5-phase orchestrator (lookalikes → ICP filter → CMO finder → signals → variants).

NOT this skill (use enrich-with-signals instead):

  • "enrich these companies with PredictLeads signals" — that pulls jobs/news/funding/tech for an EXISTING list.

Workflow

Step 0 — Ask for seed domain

"What's the seed domain or company URL?"

Step 1 — Validate (basic domain format)

Step 2 — Shell out

cd ~/Desktop/gtm-os && set -a && source .env.local && set +a && \
  npx tsx src/cli/index.ts signals:similar --domain <domain>

Single-command side-effecting → shell out per the benchmark.

Step 3 — Parse output

The CLI emits the lookalike list + result set id + cache hit/miss flags.

Step 4 — Render

See references/example-output.md.

Step 5 — Offer follow-ups

"Want me to (a) enrich these with signals via enrich-with-signals, (b) qualify them via qualify-leads?"

Notes

  • Requires PREDICTLEADS_API_KEY in ~/.gtm-os/.env.
  • Cached 7 days per seed domain.
  • ~1 PredictLeads credit per call.

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.