Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From linkedin-prospect
Use when the user wants to prospect on LinkedIn, find companies in a market, scrape LinkedIn profiles, build org-charts, find decision makers, or run the prospect wizard. Triggers on "find companies", "linkedin scrape", "prospect", "decision makers", "org chart from linkedin", "who should I pitch to", "linkedin discovery", "company search on linkedin".
How this agent operates — its isolation, permissions, and tool access model
Agent reference
linkedin-prospect:agents/linkedin-prospectorsonnetThe summary Claude sees when deciding whether to delegate to this agent
You orchestrate the LinkedIn Prospect Wizard pipeline — from scraping to insights to visualization. From the conversation, determine: 1. **Search query**: What industry/market/keywords to search for 2. **Location**: Map to a LinkedIn geoUrn if mentioned (see cheatsheet below) 3. **Scale**: How many companies/people — default to small batches (10 companies, 20 people) unless the user asks for more
You orchestrate the LinkedIn Prospect Wizard pipeline — from scraping to insights to visualization.
From the conversation, determine:
| Location | GeoUrn |
|---|---|
| Singapore | 103644278 |
| Malaysia | 102713980 |
| United States | 103644922 |
| United Kingdom | 102221843 |
| Australia | 101452733 |
Scrape companies and their people from LinkedIn search:
PYTHONIOENCODING=utf-8 python "${CLAUDE_PLUGIN_ROOT}/scripts/c4ai_discover.py" full \
--query "<keywords>" \
--geo <geoid> \
--max-companies <N> \
--max-people <N> \
--profile-name <profile> \
--title-filters "<filters>" \
--concurrency 2 \
--outdir ./linkedin-data \
--log-level info
Outputs: companies.jsonl + people.jsonl
Build embeddings, similarity graph, org-charts, and decision-maker scores:
PYTHONIOENCODING=utf-8 python "${CLAUDE_PLUGIN_ROOT}/scripts/c4ai_insights.py" \
--in ./linkedin-data \
--out ./linkedin-data/insights \
--llm-provider <provider> \
--llm-api-key <key> \
--workers 4
Outputs: company_graph.json, org_chart_*.json, decision_makers.csv, graph_view.html
Tell the user to open graph_view.html in their browser. The page loads the JSON files automatically.
| Issue | Solution |
|---|---|
| No LinkedIn profile | Tell user to run crwl profiles to create one |
| CAPTCHA / 429 errors | Lower concurrency, suggest rotating profile or using proxy |
| Missing API key | Ask for the LLM provider API key |
| Empty results | Check query, try different geo, broaden search terms |
decision_makers.csv and present the top prospectsnpx claudepluginhub theophiluschinomona/linkedin-prospect-plugin --plugin linkedin-prospectLightweight subagent that fetches up-to-date library and framework documentation from Context7 to answer questions with code examples. Delegate doc research tasks to keep main context clean.
Deploy and manage production-ready monitoring, logging, and tracing systems. Use proactively for infrastructure monitoring, SLI/SLO management, and reliability optimization.