writing
Clear, concise writing standards for documentation, comments, commit messages, and technical communication. Use when writing README files, documentation, PR descriptions, code comments, or any technical writing. Focuses on clarity, brevity, and active voice.
What this skill does
# Writing Guidelines
Standards for all written content: documentation, comments, commit messages, technical writing.
## Core Principles
### Be Concise
- Every word must earn its place
- Delete redundant words
- Cut the clutter
- Short sentences convey ideas clearly
### Active Voice
Prefer active voice over passive:
- ✅ "We fixed the bug"
- ❌ "The bug was fixed by us"
### One Idea Per Sentence
- Write short sentences
- Each sentence expresses one clear idea
- Complex ideas get multiple sentences
### Lead with Results
- Put the outcome first
- Make conclusions obvious
- Return early in explanations
- Don't bury the lead
## Naming in Writing
### Descriptive Names
- Code is reference, history, and functionality
- Names must be readable as a journal
- Be specific and concrete
### Avoid Vague Terms
Replace generic terms with specific ones:
- ❌ `data`, `item`, `list`, `component`
- ✅ `userPayment`, `users`, `paymentList`
### Remove Redundancy
- ✅ `users` (not `userList`)
- ✅ `payment` (not `userPaymentData`)
## Documentation Standards
### README Files
Structure:
1. What it does (one sentence)
2. Why it exists (one paragraph)
3. How to use it (clear steps)
4. Examples (if needed)
Keep it under 200 lines. Link to additional docs if needed.
### Code Comments
Comments are unnecessary 98% of the time:
- ❌ `// Loop through users`
- ✅ Extract to function: `filterActiveUsers()`
When comments are needed:
- Explain *why*, not *what*
- Explain business context or constraints
- Document surprising behavior or gotchas
### Commit Messages
Format:
```
<verb> <what> [<context>]
```
Examples:
- ✅ `Add user authentication`
- ✅ `Fix payment validation error`
- ✅ `Refactor database queries for performance`
- ❌ `Fixed stuff`
- ❌ `Updates`
- ❌ `Claude Code: Added feature`
Rules:
- Use imperative mood ("Add" not "Added")
- Be specific about what changed
- Include context if not obvious
- Never include "Claude Code" in messages
### PR Descriptions
Structure:
```
## What
[One sentence describing the change]
## Why
[One paragraph explaining motivation]
## Testing
[How this was tested]
```
Keep it scannable. Add details only if necessary.
## Technical Writing
### Headers
- Short, descriptive, sentence-case
- Make content scannable
- Use hierarchy properly (H1 → H2 → H3)
### Lists
- Use for related items only
- Keep items parallel in structure
- Prefer sentences in prose when possible
### Examples
- Show, don't just tell
- Use real code, not pseudocode
- Keep examples minimal and focused
## Writing Anti-Patterns
### Avoid
- Redundant words: "in order to" → "to"
- Weak verbs: "is able to" → "can"
- Passive voice: "was fixed by" → "fixed"
- Hedging: "might", "possibly", "perhaps" (when you know)
- Jargon without explanation
- Over-explaining obvious things
### Watch For
- Long sentences (>25 words)
- Dense paragraphs (>5 sentences)
- Nested clauses
- Ambiguous pronouns
## Specific Use Cases
### Error Messages
Format: `<What happened>. <What to do>.`
Examples:
- ✅ `User not found. Check the email address.`
- ✅ `Payment failed. Retry or contact support.`
- ❌ `An error occurred.`
- ❌ `Something went wrong.`
### API Documentation
Include:
1. Purpose (one sentence)
2. Parameters (with types)
3. Return value (with type)
4. Example usage
5. Error cases (if complex)
### Function/Variable Documentation
Use JSDoc/TSDoc only when necessary:
- Public APIs
- Complex algorithms
- Non-obvious behavior
Format:
```typescript
/**
* Retry failed requests with exponential backoff.
* Max 3 attempts, doubles delay each time.
*/
```
## Tone
### Technical Writing
- Professional but approachable
- Clear and direct
- Avoid humor in error messages
- Be helpful, not condescending
### Documentation
- Assume intelligence, not knowledge
- Explain context, not obvious things
- Guide, don't command
## Review Checklist
Before publishing writing:
- [ ] Lead with the result/conclusion
- [ ] Every sentence has one clear idea
- [ ] Active voice used throughout
- [ ] No redundant words
- [ ] Specific terms (no vague language)
- [ ] Short sentences (<25 words)
- [ ] Clear hierarchy (if using headers)
- [ ] Examples included (if needed)
- [ ] Scannable and skimmable
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.