LinkedIn Data Skill
Lee datos públicos de LinkedIn con UnifAPI MCP: las operaciones linkedin/... exactas y sus respuestas para investigación B2B. Nunca conecta ni escribe.
Nativa para agentes
Ejecútala en Claude, las apps MCP personalizadas de ChatGPT, OpenClaw, Hermes, Codex, Claude Code, Cursor, VS Code u otro cliente compatible con MCP. Sin flujo de GUI dedicado y sin clave API de LLM aparte.
Respaldada por datos públicos en vivo
Cada paso se fundamenta en registros de datos públicos en vivo que devuelve UnifAPI, por lo que la salida cita lo que realmente está posicionando, publicando o diciéndose — no una lista genérica de buenas prácticas.
Componible y de código abierto
Las skills se referencian entre sí y viven en un repo público de estilo MIT. Lee el SKILL.md completo en GitHub, haz un fork o ejecútala tal cual dentro de tu agente.
Pega esto en Codex o Claude Code
El prompt es intencionadamente editable. Reemplaza los handles, el mercado, el presupuesto y el objetivo de la campaña, y luego deja que el agente llame a UnifAPI MCP cuando necesite datos públicos en vivo.
Using the LinkedIn Data Skill, research stripe on public LinkedIn: pull the company profile and recent posts, run a company-filtered job search for one relevant keyword, and return a sourced brief with unsupported capabilities called out. Read-only.
La skill completa, renderizada desde su SKILL.md
Use this skill to read the eight LinkedIn operations currently published by UnifAPI. Treat this list as the capability boundary: do not invent legacy sub-resources or promise people search, keyword post search, company employee listings, reactions, follower counts, or job counts.
Use UnifAPI for live evidence
Connect with the unifapi skill, inspect the chosen operation with get_operation, then call it with call_api. Successful responses use UnifAPI's standard envelope:
{
"data": {},
"pagination": { "has_more": false, "next_cursor": null },
"billing": { "records_charged": 1 }
}
Keep billing in cost reporting. For list operations, pass pagination.next_cursor as the next request's cursor only when pagination.has_more is true.
Core operations
| Need | Operation |
|---|---|
| Company profile | linkedin/companies/{slug} |
| Company posts | linkedin/companies/{slug}/posts |
| Member profile | linkedin/users/{username} |
| Member posts | linkedin/users/{username}/posts |
| Search jobs | linkedin/search/jobs |
| Job detail | linkedin/jobs/{id} |
| Post detail | linkedin/posts/{id} |
| Post comments | linkedin/posts/{id}/comments |
Workflow
- Resolve the public key. Read a company
{slug}from/company/<slug>or a member{username}from/in/<username>. - Inspect the contract. Call
get_operationbefore the first live call so query fields, pagination, response shape, and billing are current. - Read the narrowest record. Start with the company or member profile; add its posts only when the task needs current themes or authored evidence.
- Research hiring carefully. Read
company_idfrom the company profile, then calllinkedin/search/jobswith a meaningfulkeywordand the numeric company filter. This is a filtered search, not an exhaustive company job list or a historical job-count series. - Open evidence. Use a returned job id with
linkedin/jobs/{id}or a post id withlinkedin/posts/{id}; fetch comments only when reception matters. - Report limits. Separate fields read directly from hypotheses inferred from posts, jobs, or company size. State when a requested capability is outside the current eight-operation surface.
Shape notes
- Company profiles expose the URL slug plus
company_id, description, industry, size/headcount fields, headquarters, specialties, and public counts when present. - Member profiles expose the URL username, headline, location, website, and public status flags. Follower and connection counts are not part of the current profile contract.
- Job search is cursor-paginated and requires a free-text keyword. The
companyfilter accepts the numericcompany_idfrom a company profile. - Post lists and comments are cursor-paginated. Preserve returned ids and source URLs so every downstream claim is traceable.
Gotchas
- Companies are keyed by URL slug; members are keyed by URL username. Do not substitute display names.
- A company profile's headcount is a current public field, not proof of growth over time.
- A filtered job result is evidence that a matching role was returned, not proof of the company's complete hiring plan.
- Capacity-limited collection and job operations may retry inside the gateway. Do not add a second retry loop unless the returned error contract says it is safe.
- If an operation is absent from
list_operations, treat it as unavailable rather than guessing an older path.
Output
Return the records the caller needs with source URLs, dates where available, a clear distinction between observed facts and inference, and one cost line using billing.records_charged.
Related Skills
- linkedin-account-research — turns company profiles, posts, filtered job results, named member profiles, and news into an account brief.
- account-news-signals — corroborates dated company news against official company posts.
- buying-signal-monitor — combines X intent search with named-account LinkedIn evidence.
- unifapi — connects MCP and exposes the current operation catalog and schemas.
Fuente: linkedin/SKILL.md en GitHub — abre un PR ahí para mejorarla.
Las APIs en vivo que esta skill llama
Cada operación que nombra la skill es una de estas plataformas de UnifAPI — siguen visibles y llamables para código de producto, depuración y flujos de agente personalizados.
- Las operaciones `linkedin/...` concretas para cada tarea de lectura B2B habitual
- Notas sobre el contrato de respuesta y la forma de empresas, usuarios, empleos y publicaciones
- Recetas deterministas: investigación de cuentas, evidencia de contratación dirigida, miembros y publicaciones
- Detalles de la plataforma (claves de slug frente a username, paginación por cursor, facturación)