niche-signal-discovery
Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts for ICP analysis. Use when the user provides won/lost customer domain lists and wants differential signals (website content, job listings, tech stack, maturity markers) to build account scoring models and prospecting criteria. Triggers: ICP analysis, niche signals, won vs lost analysis, differential signals, signal discovery, ICP signal report, account scoring signals, lead scoring, first-party signals, buyer signals. Before reading this file, first read deepline-gtm to understand the Deepline CLI tool and
npx skills add majiayu000/claude-skill-registry --skill niche-signal-discovery --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Niche Signal Discovery Discover differential signals between Closed Won and Closed Lost accounts by extracting multi-page website content and job listings, then computing Laplace-smoothed lift scores to identify what distinguishes buyers from non-buyers. ## Prerequisites - **Deepline CLI** — All enrichment runs through `deepline enrich`. No separate API keys for exa/crustdata/apollo etc. - **Python 3** stdlib only — no pip dependencies for any shipped script. - **Credits** — ~0.47 credits/company (serper 0.02 + firecrawl 0.05 + crustdata 0.40). Step 7 contact discovery is additional. **Always get user approval before paid steps.** ## Deepline-First Principle Use `deepline enrich` for all enrichment, `deepline tools execute` for one-offs, `deepline playground` for inspection. Reruns are idempotent. Refer to `deepline-gtm` for command patterns and provider playbooks. ## Input requirements - Won and lost customer domain lists (≥20 won + ≥10 lost for statistical significance) - **Lookalikes can supplement Won** if Closed Won < 15. Add a Dataset Caveat to the report. - **Target company context** from Step 0 — what they sell, who they sell to, key personas. ## Pipeline ``` 0. Discover
- Prerequisites
- Deepline-First Principle
- Input requirements
- Pipeline
- Signal reliability hierarchy
- What NOT to use for scoring
- Step 0: Target company discovery
- Step 0.5: Ecosystem discovery
- Step 1: Prepare input CSV
- Step 1.0.5: Build "do not re-contact" index
- Step 1.5: Generate vertical-specific configs
- Step 2: Deepline enrichment
- Step 3: Quality gate
- Step 3.5: Review configs against enriched data
python3 scripts/dedupe_utils.py --selftest # one-time sanity check
python3 scripts/dedupe_utils.py \
deepline enrich \
echo "Input: $INPUT_ROWS, Output: $OUTPUT_ROWS" # should match
deepline playground output/{{company}}-enriched.csv
python3 scripts/analyze_signals.py \
Companies only — no extra credits beyond Step 2 enrichment:
python3 scripts/find_contacts.py --input prospects_actionable.csv --output top10.csv --top 10 --no-contacts
Companies + contacts + emails — asks for credit approval.
titles surfaced in YOUR Step 0/0.5 (not a stale list from a different vertical):What does the niche-signal-discovery skill do?
Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts for ICP analysis. Use when the user provides won/lost customer domain lists and wants differential signals (website content, job listings, tech stack, maturity markers) to build account scoring models and prospecting criteria. Triggers: ICP analysis, niche signals, won vs lost analysis, differential signals, signal discovery, ICP signal report, account scoring signals, lead scoring, first-party signals, buyer signals. Before reading this file, first read deepline-gtm to understand the Deepline CLI tool and
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill niche-signal-discovery --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.