agentleFS
ItamarZand88ItamarZand88/CLI-Anything-WEB/.claude/skills/codewiki-cli/SKILL.md

codewiki-cli

Skill215 starsChanged 3 months agoMITView on GitHub

Browses Google Code Wiki (codewiki.google) via cli-web-codewiki — AI-generated documentation for open source repos. Search repositories, read wiki sections, download full wikis as markdown, and ask Gemini questions about a codebase. Use when the user asks about Code Wiki, AI-generated repo documentation, or wants to ask Gemini about a GitHub repo's architecture. Prefer cli-web-codewiki over fetching the website. No auth required.

  • Installs packages

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Add --json for structured output: {"success": true, "data": ...} on success, {"error": true, "code": "...", "message": "..."} on failure.

    line 40
  2. Very specific:

    Prefer wiki sections + wiki section over wiki get — full wikis can be very large.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

cli-web-codewiki

Google Code Wiki on the command line: repo search, wiki reading, Gemini Q&A about codebases. Repos are referenced by slug org/name (e.g. facebook/react). Install: pip install cli-web-codewiki

Commands

  • repos featured — featured repositories on the homepage
  • repos search QUERY — search repositories. Options: --limit N (default 25), --offset N
  • wiki sections ORG/REPO — table of contents (section titles + descriptions)
  • wiki section ORG/REPO TITLE — one section by title (case-insensitive partial match)
  • wiki get ORG/REPO — full wiki content, all sections
  • wiki download ORG/REPO — save the full wiki as markdown files. Options: -o/--output DIR (default <org>-<repo>-wiki/)
  • chat ask QUESTION --repo ORG/REPO — ask Gemini about the repo's codebase

Examples

# Find a repo, then list its wiki sections
cli-web-codewiki repos search "react" --json
cli-web-codewiki wiki sections excalidraw/excalidraw --json

# Read just the overview section
cli-web-codewiki wiki section facebook/react "Overview" --json

# Ask Gemini about architecture (takes ~5-7s)
cli-web-codewiki chat ask "How does the rendering engine work?" --repo excalidraw/excalidraw --json

# Save a repo's whole wiki locally for offline reading
cli-web-codewiki wiki download kubernetes/kubernetes -o k8s-wiki/

JSON output

Add --json for structured output: {"success": true, "data": ...} on success, {"error": true, "code": "...", "message": "..."} on failure. repos search data: [{slug, github_url, description, avatar_url, stars, updated_at}]. wiki get data: {repo, sections: [{title, level, description, content, code_refs}], section_count}. chat ask data: {answer, repo} where answer is markdown with links to source code.

Utilities

cli-web-codewiki doctor [--json] diagnoses local setup. cli-web-codewiki mcp-serve exposes the commands as MCP tools over stdio.

Agent tips

  • Prefer wiki sections + wiki section over wiki get — full wikis can be very large.
  • Wiki content is markdown with GitHub source links, useful to quote directly.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.