ast-grep-outline
Use when exploring or modifying a codebase and you need a cheap structural map of files, directories, imports, exports, or direct members before reading full source.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- ast-grep-outline
- description
- Use when exploring or modifying a codebase and you need a cheap structural map of files, directories, imports, exports, or direct members before reading full source.
03 SKILL.md 正文
Use ast-grep outline
ast-grep outline prints a structural map of source code with line
numbers: top-level declarations (imports, functions, classes, structs,
interfaces, modules, enums) and their direct members (fields, methods,
constructors, enum variants). It is a local, syntax-only view — cheap enough
to run before any full file read.
Read code in stages: find candidate files with search or file names, outline them, then open only the source range the outline points to. Defaults adapt to input: a file shows its local structure with member digests; a directory shows only its exported surface as grouped names.
When To Use It
Understand a file before editing. Get a table of contents, dependencies, and public entry points before reading implementation details:
ast-grep outline <file>
ast-grep outline <file> --items imports
ast-grep outline <file> --items exports
Map an unfamiliar directory. Scan the public surface of a subtree, then narrow by symbol type when you know what you are looking for:
ast-grep outline <dir> --items exports
ast-grep outline <dir> --type struct,enum,function
Zoom into a known symbol. After search finds a likely name, list its members with line numbers instead of reading the whole body:
ast-grep outline <file> --match <symbol> --type class --view expanded
Trace dependency direction. Find which files import a package or module to decide where a change belongs:
ast-grep outline <dir> --items imports --view signatures
Review changed files after editing. Git tells you what changed; outline summarizes the resulting structure and public surface:
ast-grep outline $(git diff --name-only HEAD) --items exports
Argument Guide
--items <KIND>selects top-level items:structurefor local declarations,exportsfor public API,importsfor dependencies,allwhen import/export edges matter together. The default,auto, picksstructurefor a file andexportsfor a directory. No other value is accepted; to keep only functions, classes, or another symbol kind, use--type.--view <VIEW>controls detail, from least to most:namesfor directory scans,signaturesfor one line per item,digestfor signatures plus member names,expandedfor one line per member with its line number. The default,auto, picks one from the input path. No other value is accepted.--match <REGEX>filters top-level items by name or signature. Rust regex, case-sensitive; it never matches members.--type <TYPE[,TYPE...]>keeps only some top-level symbol types, such as--type class,function. Member types likemethod,fieldnever match top-level items.--pub-membershides private members when the view prints members.--json=streamemits one JSON object per file with precise ranges. Use it only to pipe or post-process entries; prefer text for navigation.
Limits
outline shows local syntax structure. It does not resolve references, infer
types, follow re-export chains, or build a call graph. Use ast-grep run,
rg, or compiler-backed tools for those questions, then outline the candidate
files they surface.
04 同仓库更多 Skills
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
wait-what
Stop. That last message did not land: re-pitch it.
unslop
Cut AI tells from any writing.