メニュー
Automatically generates and improves code documentation across Python, JavaScript/TypeScript, Java, Go, and Rust. Detects language conventions, applies appropriate docstring standards, and validates documentation quality.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/platxa/platxa-skill-generator --skill code-documenterコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Autonomous skill creator for Claude Code CLI. Use when the user asks to "create a skill", "generate a skill", or "build a new slash command". Uses multi-phase orchestrated workflow with Task tool subagents to research domains, design architecture, generate content, validate quality, and iteratively improve via eval infrastructure. Creates production-ready skills following the Agent Skills open standard and Claude Code extensions.
Generate conventional commit messages by analyzing staged git changes. Detects change type, suggests scope, and formats messages following the Conventional Commits specification.
Guide for structured error handling across Platxa stack. Covers error types, retry patterns with exponential backoff, logging, and HTTP response mapping for Python, TypeScript, and Go.
SKILL.md を表示中
SOC 職業分類に基づく
| name | code-documenter |
| description | Automatically generates and improves code documentation across Python, JavaScript/TypeScript, Java, Go, and Rust. Detects language conventions, applies appropriate docstring standards, and validates documentation quality. |
| allowed-tools | ["Read","Write","Edit","Glob","Grep","Bash","AskUserQuestion"] |
| metadata | {"version":"1.0.0","tags":["automation","documentation","developer-tools"]} |
| argument-hint | [file|directory] |
| user-invocable | true |
Automatically generate and improve code documentation following language-specific standards.
This skill automates documentation generation for development teams. It detects your codebase language, applies appropriate docstring standards (Google/NumPy for Python, JSDoc/TSDoc for TypeScript, Javadoc for Java, godoc for Go, rustdoc for Rust), and validates documentation quality.
What it automates:
| Language | Supported Styles | Generator Tool |
|---|---|---|
| Python | Google, NumPy, Sphinx | Sphinx + Napoleon |
| JavaScript/TypeScript | JSDoc, TSDoc | TypeDoc |
| Java | Javadoc | javadoc |
| Go | godoc conventions | pkgsite |
| Rust | rustdoc (CommonMark) | cargo doc |
First, I'll scan your codebase to identify:
I'll check current documentation status:
For undocumented code, I'll generate:
I'll verify documentation meets quality standards:
Run this skill when:
After running, I'll provide:
User: Document the functions in src/utils/helpers.py
Assistant: Analyzing src/utils/helpers.py...
Found 5 public functions, 2 already documented.
Generating documentation for 3 functions using Google style:
def calculate_discount(price: float, percentage: float) -> float:
"""Calculate discounted price.
Args:
price: Original price in dollars.
percentage: Discount percentage (0-100).
Returns:
Final price after applying discount.
Raises:
ValueError: If percentage is not between 0 and 100.
"""
[Continues for remaining functions...]
Coverage: 100% (5/5 functions documented)
User: Check documentation coverage in src/components/
Assistant: Scanning TypeScript files in src/components/...
Documentation Report:
- Total exports: 24
- Documented: 18 (75%)
- Missing: 6
Missing documentation:
1. src/components/Button.tsx: ButtonProps interface
2. src/components/Modal.tsx: useModal hook
3. src/components/Form.tsx: validateField, submitForm, resetForm
Would you like me to generate TSDoc comments for these?
User: Help us establish documentation standards for our Python project
Assistant: I'll analyze your current codebase and recommend a standard.
Current state:
- 3 files use Google-style docstrings
- 2 files use NumPy-style docstrings
- 5 files have no docstrings
Recommendation: Standardize on Google style (most common in your codebase).
I'll create:
1. Documentation style guide (CONTRIBUTING.md section)
2. Pre-commit hook to validate docstring format
3. Generate missing docs in Google style
Proceed? (y/n)
When multiple styles are valid, I'll ask which you prefer:
| Language | Options |
|---|---|
| Python | google, numpy, sphinx |
| TypeScript | jsdoc, tsdoc |
| Option | Effect |
|---|---|
| Public only | Document exported functions/classes only |
| Include private | Document all functions including internal |
| Specific files | Target only specified files/directories |
Running multiple times is safe:
All changes are made through standard file edits:
git diff to review changesgit checkout to revert if neededBefore considering documentation complete: