predictleads-lookalikes
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.
适合你，如果常需要从现有客户出发寻找更多潜在客户
npx oh-my-skill add othmane-khadri/yalc-the-gtm-operating-system/predictleads-lookalikescurl -fsSL https://oh-my-skill.com/install.sh | bash -s -- othmane-khadri/yalc-the-gtm-operating-system/predictleads-lookalikesnpx oh-my-skill verify othmane-khadri/yalc-the-gtm-operating-system/predictleads-lookalikes怎么用
商店整理自技能原文 · 版本 ffc6e37 · 表述以原文为准装后，Claude 能根据一个已知公司域名，从 PredictLeads 找出最多 50 家相似公司，并返回相似度评分和可选的原因说明。结果会缓存 7 天。
当你说“找相似公司”“类似 [域名]”或要求从已知客户扩展目标列表时触发。只做公司发现，不写文案也不找联系人。
技能原文 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_identifybefore going further. - Multiple seed merge: if you run two seeds (
stripe.comandlinear.app), results are stored separately by source domain. Dedupe in code or useprospect-discovery-pipelinewhich handles the merge. similar_companyrows 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.