← ClaudeAtlas

signal-scannerlisted

Detect buying signals across TAM companies and watchlist personas. Three-phase architecture: (1) free diff-based signals from existing data (headcount growth, tech stack changes, funding rounds), (2) Apify-powered signals (job postings, LinkedIn content analysis, profile changes), and (3) post-processing with dedup, scoring, and lead status updates. Writes signals to Supabase signals table for downstream activation.
gooseworks-ai/goose-skills · ★ 727 · Data & Documents · score 82
Install: claude install-skill gooseworks-ai/goose-skills
# Signal Scanner Scheduled scanner that detects buying signals on TAM companies and watchlist personas, writes them to the `signals` table, and sets up downstream activation. ## When to Use - After TAM Builder has populated companies and personas - As a recurring scan (daily/weekly) to detect timing-based outreach triggers - When you need to move from static lists to intent-driven outreach ## Prerequisites - `SUPABASE_URL` + `SUPABASE_SERVICE_ROLE_KEY` in `.env` - `APIFY_TOKEN` in `.env` (for Phase 2 signals) - `ANTHROPIC_API_KEY` in `.env` (optional, for LLM content analysis) - TAM companies populated via `tam-builder` - Watchlist personas created for Tier 1-2 companies ## Signal Types | Priority | Signal | Level | Source | Cost | |----------|--------|-------|--------|------| | P0 | Headcount growth (>10% in 90d) | Company | Data diffs | Free | | P0 | Tech stack changes | Company | Data diffs | Free | | P0 | Funding round | Company | Data diffs | Free | | P0 | Job posting for relevant roles | Company | Apify linkedin-job-search | ~$0.001/job | | P1 | Leadership job change | Person | Apify linkedin-profile-scraper | ~$3/1k | | P1 | LinkedIn content analysis | Person | Apify linkedin-profile-posts + LLM | ~$2/1k + LLM | | P1 | LinkedIn profile updates | Person | Apify linkedin-profile-scraper | ~$3/1k | | P2 | New C-suite hire | Company | Derived from person scans | Free | ## Config Format See `configs/example.json` for full schema. Key sections: - `client_name` — wh