Agent Skills

SocialKit Agent Skills are a drop-in instruction pack for coding agents. They teach an agent, like Claude Code, Cursor, or Codex, how to use every SocialKit endpoint: the parameters, the response shapes, and the common workflows.

Install them once and the agent stops needing the API explained in every prompt. It just calls the right endpoint and gets structured social data back.

The skills live at github.com/SocialKit-API/skills.

Skills or MCP?

Both surfaces sit on the same SocialKit REST API and use the same access key.

Agent Skills fit coding agents that read skill files (Claude Code, Cursor, Codex). They call api.socialkit.dev directly. No MCP server is required.
MCP Server fits tool-calling clients (Claude Desktop, MCP Inspector, custom agents) that discover typed tools over Streamable HTTP.

If your agent supports skills, start here. If it speaks MCP, use the MCP server. You can run both.

Install

In any coding agent that supports the skills CLI:

npx skills add SocialKit-API/skills --all

The --all flag installs the full set without an interactive picker. To clone instead:

git clone https://github.com/SocialKit-API/skills.git

Authentication

The skills read your access key from the environment. Copy the example file and fill it in:

cp .env.example .env

SOCIALKIT_API_KEY=your_access_key_here

Get a key from your project’s Access Keys page in the dashboard. The same key works for the REST API and the MCP server. The skills attach it as the x-access-key header on every request. Treat it like a password, and never commit .env.

What’s included

Installing with --all gives you seven skills:

Skill	What it does
`socialkit-api`	Shared routing layer: auth, the full endpoint index, platform coverage, and hard rules
`video-transcripts`	Transcripts across YouTube, TikTok, Instagram, Facebook, X, LinkedIn, and direct URLs, single or bulk
`video-summaries`	AI summaries with topics, key points, tone, and quotes
`channel-research`	Profile and channel stats plus a creator’s recent videos, reels, posts, or tweets
`content-discovery`	Keyword and hashtag search across YouTube, TikTok, and Instagram
`engagement-analysis`	Per-video stats and comments, with sentiment you can summarize
`video-download`	Download YouTube, TikTok, and Instagram videos to a hosted file

Each skill is a SKILL.md file the agent reads on demand, plus an agents/openai.yaml descriptor.

Example prompts

Once the skills are installed and your key is set, ask for outcomes, not endpoints:

Get the transcript of this TikTok and pull out the three main claims it makes.

Research the @MrBeast YouTube channel: subscriber count and his last 10 videos
with view counts, then tell me which topics show up most.

Find the top reels for the hashtag "coldplunge" this week and rank them by views.

Pull the top comments on this Instagram reel and summarize the sentiment.

The agent picks the right skill, calls the matching endpoint, and shapes the result to your request.

How it works under the hood

Every skill maps onto the REST API documented in this reference. For example, video-transcripts calls POST /youtube/transcript, POST /tiktok/transcript, and the other transcript endpoints depending on the URL.

Because the skills use plain REST, there is nothing to run and nothing to keep in sync. A successful call costs one credit, failed calls are free, and your per-tier rate limits apply exactly as they do for direct API calls.

Credits and rate limiting

Skills consume credits identically to the REST API and MCP: one credit per successful call, failures free. The monthly credit allowance on your plan acts as a spend cap. See Authentication for key management and the API Reference for per-endpoint details.

MCP Server Overview