agentleFS
Sign inStart free
JayRHaJayRHa/AgentSkills/people-data/SKILL.md

people-data

Skill12 starsChanged 5 months agoMITView on GitHub

Research professional profiles and public business contact data through LinkedIn and YouTube, including profile details, email, phone, and channel business email lookup. Use when a user asks to identify, enrich, or find people, creators, or business contacts.

2 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read references/tool-reference.md for exact endpoints, input fields, and auth.

    line 11
  2. Distinctive:

    Look up a public professional profile from a canonical LinkedIn URL.

    line 15
  3. Distinctive:

    Prefer a canonical profile or channel URL.

    line 22
  4. Very specific:

    Use only documented snake_case query parameters.

    line 23
  5. Distinctive:

    Verify that returned identities match the request.

    line 24
  6. Distinctive:

    Use contact information only for an authorized business purpose.

    line 38
  7. Distinctive:

    Use an existing user-provided Agent Body credential through a secure environment variable.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

People Data

Perform authorized people and public business-contact research through the Agent Body REST API.

Read references/tool-reference.md for exact endpoints, input fields, and auth.

When to Use

  • Look up a public professional profile from a canonical LinkedIn URL.
  • Find a public business email or phone number tied to one profile.
  • Find public business emails from YouTube channels.

Workflow

  1. Select the smallest endpoint that satisfies the request.
  2. Prefer a canonical profile or channel URL. Do not invent a name-only search endpoint; request a canonical URL if none is available.
  3. Use only documented snake_case query parameters.
  4. Verify that returned identities match the request. Deduplicate search results by canonical profile identity when possible.
  5. Present only returned contact data. Never construct or guess an email address or phone number.

Examples

  • Input: Find the profile for https://www.linkedin.com/in/example-person/ Output: call GET /v1/linkedin/profile?profile_url=https://www.linkedin.com/in/example-person/ and summarize only the returned public fields.
  • Input: Get the email for https://www.linkedin.com/in/example-person/ Output: call GET /v1/linkedin/email?profile_url=https://www.linkedin.com/in/example-person/ if the endpoint finds one; otherwise say no result was returned.
  • Input: Find public business emails for https://www.youtube.com/@examplechannel Output: call GET /v1/youtube/channel/email?channel=https://www.youtube.com/@examplechannel and preserve per-channel found/not-found status.

Safety

Use contact information only for an authorized business purpose. Do not infer sensitive traits, bypass access controls, expose credentials, or treat a missing result as evidence that a person has no contact information.

Best Practices

Use an existing user-provided Agent Body credential through a secure environment variable; never embed it in a skill, URL, output or log. Confirm the external provider is configured before sending profile URLs. Return the source URL and distinguish returned data from inference.

Common Pitfalls

The upstream reference does not define a people-search route or filters. Do not promise that capability without a verified contract. API availability and paid access are provider-dependent; bundled examples are request shapes, not proof of a successful live lookup.

Source

Adapted from Agent Body people-data. Upstream MIT notice is retained in LICENSE. The external API has not been called during this integration.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free