tree-sitting
AST-powered code navigation using tree-sitter. Parses all source files in a codebase into in-memory syntax trees, then provides fast query tools for symbol search, file/directory overview, source retrieval, and reference finding.
Features
- Fast scanning — parses ~250 files in ~700ms, then all queries are sub-millisecond from cache
- Symbol search — find by exact name, substring, or glob pattern across the entire codebase
- Directory and file overview — structural summaries with symbol counts, signatures, and doc comments
- Source retrieval — fetch implementation of any symbol, preferring definitions over declarations
- Reference finding — locate all textual references to a symbol via fast grep against cached source
- 11 bundled grammars — Python, JavaScript, TypeScript, TSX, Go, Rust, Ruby, Java, C, HTML, Markdown (extensible: drop more
.sofiles inparsers/) - Three-tier extraction — custom extractors (richest), community tags.scm queries, and generic heuristic fallback
- Dual deployment — direct Python calls in Claude.ai, or long-lived MCP server in Claude Code
Dependencies
- tree-sitter — bare parser runtime, loads grammars from bundled
parsers/*.so - fastmcp — required only for MCP server mode (Claude Code)
Skill folder: tree-sitting
Release of tree-sitting version 0.5.0
📥 Download & Install
To install:
- Click the download link above (ignore the "Source code" archives below - they're auto-generated by GitHub)
- Go to Claude.ai Skills Settings
- Upload the downloaded ZIP file
- Requires paid Claude Pro or Team account
See official documentation for more details.
Recent Changes
caf12d6 tree-sitting: drop tree_sitter_language_pack, load bundled .so directly (fixes #572) (#573)
0a6b1b6 docs: Update CHANGELOG.md for released skills