ast-code-graph
Text-based search (grep, ripgrep) finds string matches.
Connecting the steps of a workflow
What it does
Text-based search (grep, ripgrep) finds string matches. AST-based analysis understands structure — it knows the difference between a function definition, a function call, a comment, and a string literal.
Use this skill when the task involves: | Task | Why AST beats grep | | ------ | -------------------- | | Refactoring / renaming | Grep…
You don’t need to name it. Ask for the job in your own words — your AI loads the skill when the request matches.
What it can touch
Includes 9 scripts
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: scripts/build-graph.py, scripts/parse-js.mjs, tests/fixtures/sample-cjs.js, tests/fixtures/sample-esm.mjs…; binary files: tests/__pycache__/test_build_graph.cpython-310.pyc, tests/__pycache__/test_build_graph.cpython-312.pyc.
Mentions an outside service
The instructions point your AI at these sites or APIs. Anything it sends there leaves your computer.
How we know
Web addresses in the SKILL.md, excluding GitHub and documentation sites: ast-grep.github.io.
Installs other software
Following it will install packages (npm, pip, brew or similar). Those come from their own publishers, not from this skill.
How we know
The SKILL.md contains package-install commands.
Partly checked
Launch7’s check could not read everything in this skill: 2 compiled program files it cannot read. Nothing is known about the parts it skipped.
How we know
15 text files read; skipped files are listed by name only. Read 2026-10-05, commit 83744c4.
Recently maintained
Its repository has had changes recently.
How we know
Last push to rolandbrecht/agent-skills: 2026-09-21 (14 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 9 scripts beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end