Generate a config file for documentation scraping. Interactively creates a JSON config for any documentation website.

List all available preset configurations.

Validate a config file for errors.

Sync a config's start_urls against what's live on the docs site.

Estimate how many pages will be scraped from a config. Fast preview without downloading content.

Scrape documentation and build LLM skill. Supports both single-source (legacy) and unified multi-source configs. Creates SKILL.md and reference files. Automatically detects llms.txt files for 10x faster processing. Falls back to HTML scraping if not available.

Scrape GitHub repository and build Claude skill. Extracts README, Issues, Changelog, Releases, and code structure.

Scrape PDF documentation and build Claude skill. Extracts text, code, and images from PDF files.

Extract transcripts and metadata from videos (YouTube, Vimeo, local files) and build Claude skill.

Analyze local codebase and extract code knowledge. Walks directory tree, analyzes code files, extracts signatures, docstrings, and optionally generates API reference documentation and dependency graphs.

Detect design patterns in source code (Singleton, Factory, Observer, Strategy, Decorator, Builder, Adapter, Command, Template Method, Chain of Responsibility). Supports 9 languages: Python, JavaScript, TypeScript, C++, C, C#, Go, Rust, Java, Ruby, PHP.

Extract usage examples from test files. Analyzes test files to extract real API usage patterns including instantiation, method calls, configs, setup patterns, and workflows. Supports 9 languages (Python AST-based, others regex-based).

Build how-to guides from workflow test examples. Transforms workflow examples extracted from test files into step-by-step educational guides with prerequisites, verification points, and troubleshooting tips.

Extract configuration patterns from config files (C3.4) with optional AI enhancement. Analyzes config files, detects patterns (database, API, logging, etc.), generates documentation, and optionally enhances with AI insights (security analysis, best practices, migration suggestions). Supports 9 formats.

Scrape content from new source types: jupyter, html, openapi, asciidoc, pptx, confluence, notion, rss, manpage, chat. A generic entry point that delegates to the appropriate CLI scraper module.

Package skill directory into platform-specific format (ZIP for Claude/OpenAI/Markdown, tar.gz for Gemini). Supports all platforms: claude, gemini, openai, markdown. Automatically uploads if platform API key is set.

Upload skill package to target LLM platform API. Requires platform-specific API key. Supports: claude (Anthropic Skills API), gemini (Google Files API), openai (Assistants API). Does NOT support markdown.

Enhance SKILL.md with AI using target platform's model. Local mode uses AI coding agent (no API key). API mode uses platform API (requires key). Transforms basic templates into comprehensive 500+ line guides with examples.

Complete one-command workflow: fetch config → scrape docs → AI enhance (MANDATORY) → package → upload. Enhancement required for quality (3/10→9/10). Takes 20-45 min depending on config size. Supports multiple LLM platforms: auto (detects from environment), claude, gemini, openai, markdown. Auto-uploads if platform API key is set.

Split large configs into multiple focused skills. Supports documentation (10K+ pages) and unified multi-source configs. Auto-detects config type and recommends best strategy.

Generate router/hub skill for split documentation. Creates intelligent routing to sub-skills.

Fetch config from API, git URL, or registered source. Supports three modes: (1) Named source from registry, (2) Direct git URL, (3) API (default). List available configs or download a specific one by name.

Submit a custom config file to the community. Validates config (legacy or unified format) and creates a GitHub issue in skill-seekers-configs repo for review.

Register a git repository as a config source. Allows fetching configs from private/team repos. Use this to set up named sources that can be referenced by fetch_config. Supports GitHub, GitLab, Gitea, Bitbucket, and custom git servers.

List all registered config sources. Shows git repositories that have been registered with add_config_source. Use this to see available sources for fetch_config.

Remove a registered config source. Deletes the source from the registry. Does not delete cached git repository data.

Push a config to a registered config source repository. Validates, places in category directory, commits, and pushes.

Register a plugin marketplace repository. Allows publishing skills to private/team plugin repos. Supports GitHub, GitLab, Bitbucket with per-repo authentication.

List all registered plugin marketplace repositories.

Remove a registered plugin marketplace. Deletes from registry but not cached data.

Publish a packaged skill to a plugin marketplace repository. Creates a Claude Code plugin in the target marketplace repo.

Export skill to Weaviate vector database format. Weaviate supports hybrid search (vector + BM25 keyword) with 450K+ users. Ideal for production RAG applications.

Export skill to Chroma vector database format. Chroma is a popular open-source embedding database designed for local-first development with 800K+ developers.

Export skill to FAISS vector index format. FAISS (Facebook AI Similarity Search) supports billion-scale vector search with GPU acceleration.

Export skill to Qdrant vector database format. Qdrant is a modern vector database with native payload filtering and high-performance search, serving 100K+ users.

List all available enhancement workflows (bundled defaults + user-created). Returns name, description, and source (bundled/user) for each.

Get the full YAML content of a named enhancement workflow. Searches user dir first, then bundled defaults.

Create a new user workflow from YAML content. The workflow is saved to ~/.config/skill-seekers/workflows/.

Update (overwrite) an existing user workflow. Cannot update bundled workflows.

Delete a user workflow by name. Bundled workflows cannot be deleted.