people-research

name	people-research
description	People research using Exa search. Finds LinkedIn profiles, professional backgrounds, experts, team members, and public bios across the web. Use when searching for people, finding experts, looking up professional profiles, or identifying decision-makers and warm-intro paths.
context	fork

People Research

Use the exa-search MCP server's web_search_advanced_exa tool. Do NOT use web_search_exa or any other Exa tool from this skill. Load it via ToolSearch if not already available.

Token Isolation (Critical)

For bulk people searches, spawn an explore/generalPurpose subagent via the Task tool:

• Subagent runs the Exa search
• Subagent returns only distilled output (compact JSON / brief markdown)
• Main context stays clean regardless of search volume

A single small lookup can run inline.

Dynamic Tuning

No hardcoded numResults. Tune to user intent:

• "a few" → 10–20
• "comprehensive" → 50–100
• Specified number → match it
• Ambiguous → ask: "How many profiles would you like?"

Query Variation

Generate 2–3 phrasings, run in parallel, merge and dedupe.

Categories

• people → LinkedIn profiles, public bios (primary for discovery)
• personal site → personal blogs, portfolio sites, about pages
• news → press mentions, interviews, speaker bios
• omit / type: "auto" → general web

Start with category: "people" for profile discovery, then use other categories for deeper context on specific individuals.

Category-Specific Filter Restrictions

When using category: "people", these parameters error:

• startPublishedDate / endPublishedDate
• startCrawlDate / endCrawlDate
• includeText / excludeText
• excludeDomains
• includeDomains — LinkedIn domains only (e.g. "linkedin.com")

Without a category, all parameters are available (but includeText/excludeText still only support single-item arrays).

LinkedIn

Public LinkedIn via Exa: category: "people", no other filters. Auth-gated content → use Claude in Chrome browser fallback.

Browser Fallback

Fall back to Claude in Chrome when:

• Exa returns insufficient results
• Content is auth-gated
• Dynamic pages need JavaScript

Examples

Discovery by role

{
  "query": "VP Engineering AI infrastructure",
  "category": "people",
  "numResults": 20,
  "type": "auto"
}

With query variations

{
  "query": "machine learning engineer San Francisco",
  "category": "people",
  "additionalQueries": ["ML engineer SF", "AI engineer Bay Area"],
  "numResults": 25,
  "type": "auto"
}

Deep dive on a specific person

{
  "query": "Dario Amodei Anthropic CEO background",
  "type": "auto",
  "numResults": 15
}

News mentions

{
  "query": "Dario Amodei interview",
  "category": "news",
  "numResults": 10,
  "startPublishedDate": "2024-01-01"
}

Output Format

Return:

1. Results — name, title, company, location if available
2. Sources — profile URLs
3. Notes — profile completeness, verification status

After research: distilled findings fold into investors/<slug>.md or are proposed via round investors update — proposal-only, never --yes, never write the DB directly. The live workspace DB is round.db.