Exa people research

Skill CodeAlive-AI/exa-skills/exa-people-research

Exa web search as standalone Agent Skills — no MCP server, just an EXA_API_KEY. Company, people, papers, code, finance, personal-site & X search + lead generation for Claude Code, Codex, Cursor, OpenCode, Gemini CLI, and any SKILL.md agent.

Install

npx -y skills add CodeAlive-AI/exa-skills --skill exa-people-research

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Find people with Exa semantic search — by role, company, and location, LinkedIn-weighted. Use to map a company's team, find experts/decision-makers, locate a specific person, or build people lists. Runs a local script against the Exa API; no MCP server required.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.7 KB, as published. Nobody here has run it

People Research (Exa)

Find people via Exa's LinkedIn-weighted index — by company + role, role + location, or a named individual. Calls the Exa REST API through a local script; no MCP server needed, only an EXA_API_KEY.

Setup (once)

export EXA_API_KEY=your-key            # or EXA_API_KEY=... in a .env at the repo root

Get a key at https://dashboard.exa.ai/api-keys. Shared details: exa-native-base.

Run it

python scripts/people_research.py "<role + company/location>" [-n N] [--json]

Examples:

python scripts/people_research.py "engineer at OpenAI" -n 10
python scripts/people_research.py "Head of Growth B2B SaaS startup San Francisco" -n 12
python scripts/people_research.py "Jane Smith Anthropic machine learning" -n 5

Defaults to category=linkedin profile. Be specific — vague queries like "researcher founder CEO startup" match many irrelevant profiles. Always include a concrete company, timeframe, role, or location.

Token isolation (for team maps / lists)

For comprehensive coverage, dispatch subagents in parallel and merge. Search by department + seniority in parallel rather than one broad query:

python scripts/people_research.py "category:people engineering at Acme"        -n 10
python scripts/people_research.py "category:people product design at Acme"     -n 10
python scripts/people_research.py "category:people sales marketing at Acme"    -n 10

Supplement LinkedIn with non-LinkedIn sources (use exa-native-base's generic exa.py):

python ../exa-native-base/scripts/exa.py search "Acme team page employees about us" -n 5
python ../exa-native-base/scripts/exa.py search "joined Acme recently hired new role announcement" -n 5

Deduplicate by LinkedIn URL (canonical), or by name + current company as a fallback.

Override categories with `-c`

linkedin profile (default) · personal site (their own writing) · news (press mentions). For outbound prospect lists that start from companies, use exa-lead-generation.

After you get results

Results are similarity, not validation — confirm role/company from the snippet before reporting.
Deep-read a profile or bio page: python ../exa-native-base/scripts/exa.py contents <url> --text.
Deliver a table: name · current role · company · location · LinkedIn URL.