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

predictleads-lookalikes

Skill298 starsChanged 6 months agoMITView on GitHub

Use when a teammate wants to find companies similar to a known account, asks "find lookalikes for [domain]", "companies like [client]", "similar to [domain]", "competitors of [company]", or "expand the target list from [client]". Pure account discovery — no outreach drafting, no CMO finding.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 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.

  • 2

    Very specific

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

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

    Always 1 credit per seed domain regardless of --limit.

    line 34
  2. Very specific:

    Multiple seed merge: if you run two seeds (stripe.com and linear.app), results are stored separately by source domain.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill 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
SKILL.md

PredictLeads Lookalikes (account discovery)

Pulls up to 50 companies similar to a seed domain via PredictLeads' similar_companies endpoint. Returns ranked results with a similarity score (0–1) and (when available) a sentence explaining why each is similar. Cheapest possible discovery: 1 credit per seed domain.

When to use

  • Expanding a target list from a known anchor account ("find more like Stripe")
  • Sanity-checking that a prospect fits an existing client's pattern
  • Building a watchlist of competitors for monitoring
  • First step of prospect-discovery-pipeline (but use that skill if outreach is downstream)

Don't use when: you need contacts/CMOs at the lookalikes (use prospect-discovery-pipeline); you want signal data on a single known company (use predictleads-signals).

Quick reference

# 50 lookalikes from a seed domain (1 credit)
npx tsx src/cli/index.ts signals:similar --domain stripe.com --limit 50

# Tighter list (still 1 credit per call)
npx tsx src/cli/index.ts signals:similar --domain linear.app --limit 20

# Read back from local SQLite (no API call)
npx tsx src/cli/index.ts signals:show --domain stripe.com --type similar

Cost

Always 1 credit per seed domain regardless of --limit. Result rows land in company_signals with signal_type='similar_company' and stay cached for 7 days.

Output shape

Each result is a domain + score + reason:

deel.com (score=0.85)
remote.com (score=0.849)
oysterhr.com (score=0.848)  — Both provide global EOR services for distributed teams.

Reasons are populated for some seed domains and not others (PredictLeads inconsistent). Score above 0.80 typically means strong match in their model.

Common pitfalls

  • Megacaps in results: PredictLeads returns market peers including SAP, Microsoft, Google for many B2B SaaS seeds. Filter by hand or via Crustdata company_identify before going further.
  • Multiple seed merge: if you run two seeds (stripe.com and linear.app), results are stored separately by source domain. Dedupe in code or use prospect-discovery-pipeline which handles the merge.
  • similar_company rows have no event date: they're a lookup, not an event. Don't sort by event_date; sort by score (in payload) or position.

Required env

PREDICTLEADS_API_KEY + PREDICTLEADS_API_TOKEN in ~/.gtm-os/.env. See TEAM_SETUP.md.

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.