Enrich With Signals
Apps & Automationenrich-with-signalsEnrich With Signals is an Agent Skill for apps & automation published in the Othmane-Khadri/YALC-the-GTM-operating-system repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Pull PredictLeads buying-intent signals (jobs, news, funding, tech, leadership changes) for a result set of companies and write them back into the local cache. Use when the user says 'enrich these companies with signals', 'add buying signals to this list', 'pull intent data for [domain]', 'check signals for these accounts', or 'fetch jobs and news for these companies'. Side-effecting — calls PredictLeads API and writes to local SQLite + JSON cache.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/Othmane-Khadri/YALC-the-GTM-operating-system/blob/HEAD/.claude/skills/enrich-with-signals/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/enrich-with-signals, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Enrich With Signals
I'll wrap signals:enrich. Take a result set, fan out PredictLeads calls (cached 7 days per domain), and surface signal counts + summary per company.
When This Skill Applies
- "enrich these companies with signals"
- "add buying signals to this list"
- "pull intent data for [domain]"
- "check signals for these accounts"
- "fetch jobs and news for these companies"
NOT this skill (use find-lookalikes instead):
- "find similar companies" — that discovers new prospects.
NOT this skill (use qualify-leads --enrich-signals instead):
- "qualify these leads with signals" — that's the qualification pipeline with signal enrichment as a gate.
Workflow
Step 0 — Ask which result set
"Which result set should I enrich? Pass the id, or use the most recent."
Step 1 — Validate result set exists
Step 2 — Ask which signal types
"Which signal types? (default: jobs, funding, tech, news; also available: leadership)"
Step 3 — Shell out
cd ~/Desktop/gtm-os && set -a && source .env.local && set +a && \
npx tsx src/cli/index.ts signals:enrich --result-set <id> --types <types>
Side-effecting → shell-out per benchmark.
Step 4 — Parse output
CLI emits per-company signal counts + cache hit ratio + total credits consumed.
Step 5 — Render
See references/example-output.md.
Step 6 — Offer follow-ups
"Want me to (a) qualify the enriched set via
qualify-leads, (b) launch a campaign segmented by signal type?"
Notes
- ~1 PredictLeads credit per uncached domain per signal type.
- 7-day cache TTL; pass
--no-cacheto force re-fetch. - Companies with no signals get an empty entry (still cached so we don't re-query).