agentleFS
Sign inStart free
WireCatLabsWireCatLabs/cli-docs/skills/wirecat-documentation/SKILL.md

wirecat-documentation

Skill1 starsChanged 5 days agoApache-2.0View on GitHub

Write, review or maintain WireCat Telegram/MAX documentation using reader tasks, reviewed release contracts and shared documentation checks. Use for WireCat documentation work, not live messenger tasks.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Read docs/AUTHORING.md and docs/README.md there before drafting.

    line 7
  2. Distinctive:

    Before implementation, fetch current main and verify the checkout base.

    line 11
  3. Very specific:

    Read docs/TOOLING.md when gathering source or validating changes.

    line 15
  4. Very specific:

    Use targeted searches for narrow questions.

    line 20
  5. Distinctive:

    Use isolated fixtures for behavioral checks.

    line 34
  6. Very specific:

    Run relevant build/export/browser checks so graphics do not disappear from Markdown twins.

    line 37
  7. Distinctive:

    Follow the existing reviewed-release workflow for translations and publication.

    line 38

≈ “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

Find the cli-docs checkout; when working in tg-cli/max-cli it is normally a sibling directory. Read docs/AUTHORING.md and docs/README.md there before drafting. They own the audience, page openings, expected results, endings, cross-links and current task homes. Documentation serves nontechnical readers first; retain exact reference material for developers and agents.

Before implementation, fetch current main and verify the checkout base. Use a clean worktree from current main unless the user explicitly chose another base; preserve existing work. Report the actual base commit and distinguish your changes from already-shipped content.

Read docs/TOOLING.md when gathering source or validating changes. tools.json identifies reviewed releases. Distinguish those releases from installed tools, local main and inspected architecture snapshots. Tool facts belong in their repositories; the portal's messenger folders are generated sync outputs. Preserve uncommitted work and incoming URLs/anchors.

Use targeted searches for narrow questions. For broad review/handoff, run pnpm docs:pack from cli-docs with the repository, release ref and topic you need. This stages an allowlisted snapshot before Repomix reads files; check its manifest and verify claims against original source. Do not run unrestricted packers on repositories containing private account artifacts.

CodeWiki is an optional research workflow for a requested generation/comparison task. Its bounded trial uses the existing Codex login and separate source/output directories. Generated pages are draft evidence, not public docs or proof of implemented behavior. Record missing dependencies and inferred claims. Never publish or overwrite maintained pages automatically.

For public edits, improve the existing home of a user task before adding pages. Use fictional examples and released commands. Run localization and pnpm docs:check with refreshed pnpm docs:contracts; examine the report's reference gaps, invalid examples, unsupported syntax and unmapped task families separately. These checks do not prove prose facts or task success. Use isolated fixtures for behavioral checks; this workflow does not authorize live sending.

For Mermaid, keep editable fenced source, localized labels, a caption and a prose equivalent. Run relevant build/export/browser checks so graphics do not disappear from Markdown twins. Follow the existing reviewed-release workflow for translations and publication.

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.

Check your setup, free