agentleFS
lyh843lyh843/AgentSkills/skills/use-code-wiki/SKILL.md

use-code-wiki

Skill1 starsChanged 5 months agoMITView on GitHub

Navigate a documented Git repository through .code-wiki/wiki.json to locate implementation files, plan changes, and answer codebase-structure questions. Use when a Code Wiki index exists and repository exploration should proceed from summaries to headers to full source.

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 6 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the Code Wiki as a progressive navigation cache.

    line 9
  2. Very specific:

    Run python3 scripts/query_index.py --root <absolute-root> --json status from this skill directory.

    line 14
  3. Very specific:

    If the index is absent, invalid, or unsupported, stop using it and recommend build-code-wiki.

    line 15
  4. Very specific:

    Run python3 scripts/query_index.py --root <absolute-root> --json show .

    line 16
  5. Distinctive:

    Read the managed headers of shortlisted files.

    line 19
  6. Distinctive:

    Read complete files only when implementation detail is required or an entry is stale.

    line 20
  7. Distinctive:

    Read adjacent tests and configuration before editing.

    line 21
  8. Distinctive:

    Verify claims against current source before answering or modifying code.

    line 22
  9. Very specific:

    Use show <relative-path> for one repository, directory, or file node.

    line 27
  10. Very specific:

    Use stale only when freshness affects the task.

    line 28
  11. Very specific:

    Never pass absolute paths or paths containing ...

    line 29
  12. Distinctive:

    Do not load the complete index when targeted subtree queries are sufficient.

    line 30
  13. Very specific:

    Read wiki.schema.json only when schema interpretation or validation detail is required.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Use Code Wiki

Use the Code Wiki as a progressive navigation cache. Treat current source code as authoritative.

Workflow

  1. Resolve the target Git root.
  2. Run python3 scripts/query_index.py --root <absolute-root> --json status from this skill directory.
  3. If the index is absent, invalid, or unsupported, stop using it and recommend build-code-wiki.
  4. Run python3 scripts/query_index.py --root <absolute-root> --json show . for repository orientation.
  5. Query only directory nodes relevant to the request.
  6. Shortlist files from their summaries.
  7. Read the managed headers of shortlisted files.
  8. Read complete files only when implementation detail is required or an entry is stale.
  9. Read adjacent tests and configuration before editing.
  10. Verify claims against current source before answering or modifying code.
  11. Recommend build-code-wiki after source changes.

Query operations

  • Use show <relative-path> for one repository, directory, or file node.
  • Use stale only when freshness affects the task.
  • Never pass absolute paths or paths containing ...
  • Do not load the complete index when targeted subtree queries are sufficient.

Read wiki.schema.json only when schema interpretation or validation detail is required.

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.