Unif API DocsSkills
How UnifAPI Skills turn task prompts into MCP calls over live public-data APIs.
Skills are task-specific workflows an agent can run with UnifAPI MCP. They start from an outcome — a KOL pricing brief, creator shortlist, social listening summary, or competitor launch analysis — then let the agent discover and call public-data operations as needed.
The recommended path is Skills-first: choose the task result, use the install path your AI client supports, then sign in when the MCP server needs live public data. Non-developer users should not need to run npx skills or hand-wire raw skill files.
Use path
Start from a Skill. Use the UnifAPI Skill catalog to choose the artifact the agent should produce.
Add UnifAPI to your agent client. Use the verified MCP setup path your client supports:
Claude connectors, ChatGPT developer mode custom apps, OpenClaw or Hermes MCP config,
Codex/Claude Code CLI setup, or Cursor/VS Code mcp.json. If the client asks for a connector
URL, use https://mcp.unifapi.com.
Keep raw skills as a developer fallback. npx skills add unifapi-agent/agents remains
supported for local raw-skill installs, but it is not the main onboarding path.
Skill model
Start with the result. A Skill prompt names the artifact the agent should produce, such as a ranked creator table or competitive brief.
Discover operations through MCP. The agent uses list_operations and get_operation to
find public-data APIs that match the task.
Call live public data. The agent uses call_api only when it needs evidence, then returns
the result with assumptions, confidence, and follow-up questions.
First benchmark Skill
The first public benchmark is KOL Pricing:
Analyze these Twitter/X KOLs for an AI developer-tool campaign: @vercel, @shadcn, @rauchg.
Use UnifAPI public data, compare recent engagement, audience fit, posting cadence, and collaboration risk.
Return a ranked table with estimated sponsored-post price ranges, confidence, evidence, and follow-up questions.This runs well in Claude, ChatGPT custom apps, OpenClaw, Hermes, Codex, Claude Code, Cursor, VS Code, or any compatible MCP client. The user keeps their existing agent plan; UnifAPI bills only the public-data records returned by call_api.
Data boundary
UnifAPI Skills use public data. OAuth authorizes the UnifAPI MCP workspace and credit balance; it does not grant access to a user's private Twitter/X, Google, CRM, or SaaS account.
Use a connector platform when a workflow needs user-authorized SaaS data. Use UnifAPI when the workflow needs public social records, posts, comments, profiles, videos, trends, communities, or company signals.
Output expectations
A Skill should return a decision artifact, not raw API dumps:
- evidence-backed tables or briefs
- assumptions and confidence notes
- source operations used
- follow-up searches the agent should run
- risks, missing evidence, and next actions
Related resources
MCP integration
Connect Claude, ChatGPT custom MCP apps, OpenClaw, Hermes, Codex, Claude Code, Cursor, VS Code, and other MCP clients.
API reference
Live public-data operations Skills can call.
Authentication
OAuth for MCP and API keys for HTTP.
Marketing Skills page
User-facing Skills catalog and KOL Pricing benchmark.