菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Push the campaign-ready list into the configured sequencer (capability sequencer_push) — the final stage. Reads the storage export, builds the campaign payload, and pushes via the chosen sequencer's manifest/adapter, behind an always-on activation gate. Use when the user wants to "push to the sequencer", "create the campaign", "activate list N", or "send to lemlist".
Find target companies that fit the ICP (capability company_search), create the pipeline list, and hand the company set to people_search. Supports look-alike / segment / expansion modes and synthesizes company_search from people_search when a provider lacks native org search. Use when the user wants to "find companies", "build a target account list", or run only the discovery stage.
Build deep, source-cited account intel for an accepted company list (capability company_enrich) — funding, tech stack, leadership, hiring/"why now" signals, description — using Fire-Enrich-style Claude subagent fan-out, BEFORE people sourcing. Persists to the companies store. Use when the user wants to "enrich the companies", "get account intel", "research these accounts", or run only the company-enrichment stage.
Score sourced contacts against the ICP and tier them QUALIFY / MAYBE / SKIP so paid enrichment is spent only on good-fit contacts. Context-driven (segments.md rubric + personas.md + exclusions.md); no provider, no credits. Always includes a human review gate. Use when the user wants to "qualify the list", "score these contacts", or run only the qualify stage.
Find and validate work emails for a list's contacts (capability email_enrich), advancing them to stage 'email_enriched'. Runs the configured email_enrich waterfall, stops at the first valid email, re-verifies "guessed" results, and honors the pre-paid-enrichment gate. Use when the user wants to "find emails", "enrich emails for list N", or run only the email stage.
Run the GTM contact pipeline from a plain-English campaign brief. Interprets the brief against context/ + gtm.config.yaml, plans the run, and drives the stages (company_search → people_search → qualify → email_enrich → phone_enrich → activate) threading one list_id, with approval gates. Use when the user describes a campaign ("find me … at … for …"), says "/gtm …", "run the pipeline", or "build a list".
| name | contact-sourcer |
| description | 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. |
| allowed-tools | Read, Bash, WebSearch, WebFetch |
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.
