- Add Claude Code Plugin: plugin.json, .mcp.json, 3 slash commands, skill-builder agent skill - Add GitHub Action: composite action.yml with 6 inputs/2 outputs, comprehensive README - Add Smithery: publishing guide with namespace yusufkaraaslan/skill-seekers created - Add render-mcp.yaml for MCP server deployment on Render - Fix Dockerfile.mcp: --transport flag (nonexistent) → --http, add dynamic PORT support - Update AGENTS.md to v3.3.0 with corrected test count and expanded CI section - Allow distribution/claude-plugin/.mcp.json in .gitignore
1.6 KiB
1.6 KiB
description
| description |
|---|
| Create an AI skill from any source (URL, repo, PDF, video, notebook, etc.) |
Create Skill
Create an AI-ready skill from a source. The source type is auto-detected.
Usage
/skill-seekers:create-skill <source> [--target <platform>] [--output <dir>]
Instructions
When the user provides a source via $ARGUMENTS, run the skill-seekers create command to generate a skill.
- Parse the arguments: extract the source (first argument) and any flags.
- If no
--targetis specified, default toclaude. - If no
--outputis specified, default to./output. - Run the command:
skill-seekers create "$SOURCE" --target "$TARGET" --output "$OUTPUT" - After completion, read the generated
SKILL.mdand summarize what was created.
Source Types (auto-detected)
- URL (https://...) → Documentation scraping
- owner/repo or github.com URL → GitHub repo analysis
- file.pdf → PDF extraction
- file.ipynb → Jupyter notebook
- file.docx → Word document
- file.epub → EPUB book
- YouTube/Vimeo URL → Video transcript
- ./directory → Local codebase analysis
- file.yaml with OpenAPI → API spec
- file.pptx → PowerPoint
- file.adoc → AsciiDoc
- file.html → HTML page
- file.rss → RSS/Atom feed
- cmd.1 → Man page
Examples
/skill-seekers:create-skill https://react.dev
/skill-seekers:create-skill pallets/flask --target langchain
/skill-seekers:create-skill ./docs/api.pdf --target openai
/skill-seekers:create-skill https://youtube.com/watch?v=abc123