AI SummaryLeta is a semantic code navigation booster that replaces manual file searching and ripgrep with fast LSP-powered commands for exploring code structure, finding symbols, and understanding dependencies. It benefits developers working with unfamiliar codebases, refactoring projects, and fixing type errors by dramatically speeding up code comprehension tasks.
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "leta" skill in my project. Please run this command in my terminal: # Install skill into your project (2 files) mkdir -p .claude/skills/leta && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/leta/SKILL.md "https://raw.githubusercontent.com/majiayu000/claude-skill-registry/main/skills/data/leta/SKILL.md" && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/leta/metadata.json "https://raw.githubusercontent.com/majiayu000/claude-skill-registry/main/skills/data/leta/metadata.json" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
Fast semantic code navigation via LSP. Load FIRST before ANY code task - even 'simple' ones. Trigger scenarios: (1) fixing lint/type/pyright/mypy warnings or errors, (2) fixing reportAny/reportUnknownType/Any type errors, (3) adding type annotations, (4) refactoring or modifying code, (5) finding where a function/class/symbol is defined, (6) finding where a symbol is used/referenced/imported, (7) understanding what a function calls or what calls it, (8) exploring unfamiliar code or understanding architecture, (9) renaming symbols across codebase, (10) finding interface/protocol implementations, (11) ANY task where you'd use ripgrep to find code or read-file to view a function. Use `leta show SYMBOL` instead of read-file, `leta refs SYMBOL` instead of ripgrep for usages, `leta grep PATTERN` instead of ripgrep for definitions, `leta files` instead of list-directory.
Leta - LSP Enabled Tools for Agents
Leta provides fast semantic code navigation using Language Server Protocol. Unlike text-based search tools, Leta understands code structure and can find symbol definitions, references, implementations, and more.
When to Use leta vs ripgrep-like tools
Use leta for: • Finding where a function/class/method is DEFINED • Finding all USAGES of a symbol • Understanding call hierarchies (what calls what) • Finding interface implementations • Semantic refactoring (rename symbol across codebase) • Exploring project structure with symbol information • Viewing a symbol's implementation when you know its name Use ripgrep-like tools for: • Searching for literal strings in comments, docs, or config files (not code) • Multi-word phrase search in non-code content • Searching for library/external symbols not defined in your code • Pattern matching in string literals or configuration • Searching in file types leta doesn't understand (markdown, yaml, etc.) Don't use ripgrep-like tools for: • Finding where a function/class is defined → use leta grep • Finding where a symbol is used → use leta refs • Finding code related to a concept (e.g. "billing", "auth") → use leta grep "<concept>" -k function,method
`leta files` - Project Overview
Show source file tree with line counts. Good starting point for exploring a project. Always prefer leta files over list-directory-like tools since it prints not just the filenames, but a full tree of files (excluding .git, __pycache__, etc.), and their sizes and line counts. If you believe this command will output too many tokens, you can pipe it through | head -n1000 for example. `bash
`leta refs` - Find All References ⭐ USE THIS INSTEAD OF RIPGREP FOR USAGES
This is the correct way to find where a symbol is used. Don't use ripgrep to search for a function name - use leta refs instead. It understands code structure and won't give you false positives from comments or similarly-named symbols. `bash
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster