ワンクリックで
wf-doc-a
Generate or update standard code documentation — docstrings, rustdoc, API references, READMEs
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Generate or update standard code documentation — docstrings, rustdoc, API references, READMEs
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
Cross-repo visibility for agent loops. Lists running, completed, and crashed loops. Reads the registry and per-repo tracking logs. Shows tmux attach commands. Use when checking what loops are active, what ran recently, or loop details.
Capture feedback about wf, util, or vault plugins and file it as a GitHub issue for improvement. Use after any session where the tooling fell short — wrong agent behavior, missing skill coverage, misleading prompts, workflow friction, or convention gaps. Only for generic plugin improvements that would help ANY project, not repo-specific config. Files to JSai23/claude-tooling with the plugin-feedback label.
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
| name | wf-doc-a |
| description | Generate or update standard code documentation — docstrings, rustdoc, API references, READMEs |
| metadata | {"source-plugin":"wf","source-skill":"doc-a"} |
Action skill — Generate and update standard code documentation: docstrings, rustdoc, API refs, how-tos.
$ARGUMENTS
Generate or update standard code documentation. This is user-facing documentation that lives alongside the code — not agent design docs (those live in design-docs/).
Every line must earn its place. Documentation that doesn't get read is useless. Cut ruthlessly.
Auto-generated from code. Your job is to ensure the source annotations are complete and correct — not to write separate docs.
/// doc comments on public items. Include # Examples sections for non-obvious usage. //! for module-level docs.What makes good API docs:
What to skip:
get_name doesn't need "Gets the name"Scannable steps with contracts. Written for humans who want to accomplish a specific task.
Structure:
Place near the code they describe. A README.md in the relevant package/directory, or a dedicated docs/ folder for multi-step workflows.
High-level system maps for orientation. These describe what exists and how it connects — not why (that's in design-docs/).
Keep current or delete. Stale architecture docs are worse than none.
Assess what's needed based on arguments:
api — Audit and improve inline documentation (docstrings, doc comments) for the specified scope. Add missing docs on public APIs, fix inaccurate descriptions, add examples where useful.howto — Create or update a how-to guide for the specified topic. Scan existing code to extract the actual steps.arch — Create or update architecture documentation. Read the actual code structure, don't guess.