accelerator-research-agent
Research accelerator portfolio companies using Firecrawl and Tavily MCPs. Generates structured CSV and markdown reports with systematic impact scoring. Optimized for token efficiency.
npx skills add majiayu000/claude-skill-registry --skill scout-ai-lite --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.
# Accelerator Research Agent A token-optimized Claude Desktop skill for researching accelerator portfolio companies with systematic impact analysis. ## When to Use This Skill Activate when user asks to: - **"Research companies from [accelerator name]"** - **"Analyze [accelerator] portfolio"** - **"Score companies for impact"** or **"evaluate mission alignment"** - Mentions: YC, Techstars, Fast Forward, 500 Global, a16z ## Prerequisites **Required MCP Servers** (both tested and validated): 1. **Firecrawl MCP** - Structured extraction - Free tier: 500 credits/month - Use `firecrawl_extract` for JSON extraction 2. **Tavily MCP** - AI-optimized search - Free tier: 100 RPM (6,000/hour) - Use `tavily-search` for company research ## Core Workflow (3 Phases) ### Phase 1: Portfolio Extraction **Goal**: Get company list from accelerator portfolio page **Tool**: `firecrawl_extract` (PRIMARY - 100% success rate) **Schema Pattern**: See `SCHEMA-TEMPLATES.md` for tested schemas (YC, Fast Forward, Healthcare, Climate, Fintech) **Quick Schema** (customize based on accelerator): ```json { "name": "mcp__MCP_DOCKER__firecrawl_extract", "arguments": { "urls": ["PORTFOLIO_URL"], "prompt": "Extract all
- When to Use This Skill
- Prerequisites
- Core Workflow (3 Phases)
- Phase 1: Portfolio Extraction
- Phase 2: Company Research
- Phase 3: Impact Scoring
- Phase 4: Report Generation
- Token Management Best Practices
- Common Scenarios
- Scenario 1: YC Research
- Scenario 2: Fast Forward Impact
- Scenario 3: Healthcare Medicaid
- Troubleshooting
- Files Reference
What does the accelerator-research-agent skill do?
Research accelerator portfolio companies using Firecrawl and Tavily MCPs. Generates structured CSV and markdown reports with systematic impact scoring. Optimized for token efficiency.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill scout-ai-lite --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.