technical-writer
について
technical-writerスキルは、技術文書作成の専門技能を提供します。技術者と非技術者、双方のユーザーを対象に、ユーザーガイド、APIドキュメント、チュートリアルなど、包括的な技術文書を生成します。このスキルは文書の種類を自動的に識別し、想定されるユーザーの役割と専門知識レベルに合わせて内容を調整します。構造化された文書、オンボーディング資料、ナレッジベース記事の作成が必要な際に、このスキルをご利用ください。
クイックインストール
Claude Code
推奨/plugin add https://github.com/OneWave-AI/claude-skillsgit clone https://github.com/OneWave-AI/claude-skills.git ~/.claude/skills/technical-writerこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
Technical Writer
Create clear, comprehensive technical documentation for any audience.
Instructions
When a user needs technical documentation:
-
Identify Documentation Type:
- User guide / end-user documentation
- Developer documentation / API docs
- System architecture documentation
- Tutorial / how-to guide
- Troubleshooting guide
- README file
- Release notes / changelog
- Onboarding documentation
- Knowledge base article
- Standard Operating Procedure (SOP)
-
Determine Audience:
- Technical level (beginner, intermediate, expert)
- Role (end user, developer, admin, stakeholder)
- Prior knowledge assumptions
- Context (internal team, external customers, open source community)
-
Structure Documentation:
User Guide Format:
# [Product/Feature Name] ## Overview [What it is, what it does, why use it - 2-3 sentences] ## Prerequisites - [Required knowledge] - [Required tools/access] - [System requirements] ## Getting Started [Quick start guide with minimal steps to first success] ### Step 1: [Action] [Detailed instructions with screenshots/code] ### Step 2: [Action] [Detailed instructions] ## Key Concepts ### [Concept 1] [Explanation with examples] ## Common Tasks ### How to [Task] 1. [Step] 2. [Step] 3. [Expected result] ## Advanced Features [Optional advanced functionality] ## Troubleshooting ### Problem: [Common issue] **Symptoms**: [What users see] **Solution**: [How to fix] ## FAQ **Q: [Question]** A: [Answer] ## Additional Resources - [Link to related docs] - [Support channels]Tutorial Format:
# How to [Accomplish Goal] **Time required**: [X minutes] **Difficulty**: [Beginner/Intermediate/Advanced] ## What You'll Learn - [Learning objective 1] - [Learning objective 2] ## Prerequisites - [Required knowledge] - [Tools needed] ## Step-by-Step Instructions ### 1. [First Major Step] [Explanation of why this step matters] ```[language] [Code example]Expected output:
[What users should see]2. [Next Major Step]
[Continue pattern]
Verification
[How to confirm it worked]
Next Steps
[What to learn next]
Troubleshooting
[Common issues]
**Architecture Documentation Format**: ```markdown # [System Name] Architecture ## Overview [High-level description, purpose, key characteristics] ## Architecture Diagram [ASCII diagram or description for diagram] ## Components ### [Component 1] **Purpose**: [What it does] **Technology**: [Stack/framework] **Responsibilities**: - [Responsibility 1] - [Responsibility 2] **Interfaces**: - Input: [Data/requests it receives] - Output: [Data/responses it produces] ## Data Flow 1. [Step-by-step flow through system] ## Technology Stack - **Frontend**: [Technologies] - **Backend**: [Technologies] - **Database**: [Technologies] - **Infrastructure**: [Technologies] ## Design Decisions ### Why [Technology/Pattern]? [Rationale, alternatives considered, trade-offs] ## Scalability Considerations [How system scales, bottlenecks, mitigation strategies] ## Security [Authentication, authorization, data protection] ## Monitoring & Observability [Logging, metrics, alerting] -
Apply Technical Writing Best Practices:
Clarity:
- Use short sentences (aim for 15-20 words)
- Avoid jargon or define it when first used
- Use active voice ("Click the button" not "The button should be clicked")
- Be specific ("Set timeout to 30 seconds" not "Set a reasonable timeout")
Structure:
- Use descriptive headings
- Break content into scannable sections
- Use numbered lists for sequences
- Use bullet points for unordered items
- Add table of contents for long docs
Visuals:
- Include screenshots with annotations
- Add code examples with syntax highlighting
- Use diagrams for complex concepts
- Show expected outputs
- Add tables for comparison or reference
Code Examples:
- Include language identifier
- Show both good and bad examples
- Add comments explaining complex parts
- Use realistic, runnable examples
- Include error handling
User-Focused:
- Start with most common use case
- Include "why" not just "how"
- Anticipate user questions
- Address common pitfalls
- Provide troubleshooting
-
Format Complete Output:
📚 TECHNICAL DOCUMENTATION Type: [User Guide/Tutorial/Architecture/etc.] Audience: [Target audience] Level: [Beginner/Intermediate/Advanced] ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ [Full markdown documentation] ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 📋 DOCUMENTATION CHECKLIST ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ ✅ Clear overview and purpose ✅ Prerequisites listed ✅ Step-by-step instructions ✅ Code examples included ✅ Expected outputs shown ✅ Troubleshooting section ✅ Links to related docs ✅ Scannable structure ✅ Appropriate for audience level 💡 MAINTENANCE NOTES ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Review Triggers: • [When to update this doc] • [Dependencies that might change] Related Documentation: • [Link to related docs] -
Special Documentation Types:
README.md:
- Project name and description
- Installation instructions
- Quick start example
- Features list
- Documentation links
- Contributing guidelines
- License
Release Notes:
- Version number and date
- New features
- Improvements
- Bug fixes
- Breaking changes
- Migration guide
- Deprecation notices
Troubleshooting Guide:
- Symptom-based organization
- Root cause analysis
- Step-by-step resolution
- Prevention tips
- When to escalate
Example Triggers
- "Write user documentation for my feature"
- "Create a tutorial for setting up the development environment"
- "Document this system architecture"
- "Write a troubleshooting guide"
- "Create onboarding documentation for new developers"
- "Write a README for this project"
Output Quality
Ensure documentation:
- Has clear, descriptive title
- Starts with overview/context
- Lists prerequisites upfront
- Uses consistent formatting
- Includes code examples where appropriate
- Shows expected outputs
- Has troubleshooting section
- Uses appropriate technical level for audience
- Is structured logically (simple to complex)
- Includes visual aids (diagrams, screenshots)
- Has table of contents for long docs
- Links to related documentation
- Is easy to scan
- Uses active voice
- Avoids ambiguity
- Includes examples from user perspective
Generate professional, comprehensive technical documentation that enables users to succeed.
GitHub リポジトリ
関連スキル
content-collections
メタThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
creating-opencode-plugins
メタThis skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.
polymarket
メタThis skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
