Applying Style
Apply precise writing style that expresses ideas clearly with personal voice and logical flow.
What this skill does
# Applying Style
## Style Guide
- Write precise, clear sentences
- Use first person for opinions ("I think", "I believe")
- Let ideas flow logically without heavy transitions
- Use periods instead of em dashes
- Prefer active voice
- Be personal and direct
- Take user instructions seriously
---
## Rules
### Rule 1: Remove Dramatic Words
Eliminate intensifiers that add no meaning.
**Banned words:**
- deeply, profoundly, struck, critical, crucial, key, perfect, disturbing
- fascinating, alarming (use sparingly)
- synergy, converge, "realizes X's vision"
**Check:** Does removing the word change the meaning? If not, remove it.
---
### Rule 2: Remove Filler Phrases
Delete phrases that occupy space without adding information.
**Banned phrases:**
- "key insight", "But here's what bothers me", "perfect [adjective]"
- "This changes everything", "game-changer", "paradigm shift"
- "In other words"
**Check:** Can you delete the phrase entirely? If yes, delete it.
---
### Rule 3: Remove Unnecessary Adverbs
Cut adverbs that only boost confidence or redundantly enhance meaning.
**Enhancement-only:** "contrasts sharply" → "contrasts"
**Confidence-boosting:** definitively, conclusively, undeniably, clearly, obviously, certainly
**Check:** Does the verb already imply the adverb? If yes, remove the adverb.
---
### Rule 4: Don't Start Sentences with Adverbs
Move sentence-initial adverbs or remove them.
**Bad:** "Critically, this distinction matters."
**Good:** "This distinction matters."
**Check:** Does the sentence start with an adverb ending in "-ly"? If yes, rewrite or remove.
---
### Rule 5: Replace Rhetorical Questions with Statements
Convert questions into direct statements.
**Bad:** "Why do X?"
**Good:** "X happens."
**Check:** Is the question rhetorical (not expecting an answer)? If yes, convert to statement.
---
### Rule 6: Remove Meaningless Contrasts
Delete "not X but Y" when Y alone suffices.
**Bad:** "We are not using tools to think but thinking through direct engagement with external structures."
**Good:** "We are thinking through direct engagement with external structures."
**Check:** Does the "not X" clause add meaning? If not, delete it and keep only Y.
---
### Rule 7: Move Negations from End to Beginning
Restructure sentences that end with "not [passive alternative]" by moving the contrast to the beginning.
**Bad:** "This requires learners to progressively refine mental schemas, not passively receive information."
**Good:** "In contrast to passively receiving information, this requires learners to progressively refine mental schemas."
**Check:** Does the sentence end with ", not [something]"? If yes, move the negation to the beginning.
---
### Rule 8: Replace Fancy Words with Clear Alternatives
Use simple words when they convey the same meaning.
**Bad:** "This dual-layer mediation operates together"
**Good:** "These two layers operate together"
**Check:** Is there a simpler word that means the same thing? If yes, use the simpler word.
---
### Rule 9: Simplify Intensifiers
Replace dramatic intensifiers with moderate alternatives.
**Bad:** "This distinction is critical."
**Good:** "This is an important distinction."
**Check:** Does the sentence use "critical", "crucial", or similar? If yes, replace with "important" or remove.
---
### Rule 10: Remove Dramatic Build-up
Delete rhetorical staging phrases like "This sets the stage for" or "This raises the question".
**Bad:** "This sets the stage for the next question: how should learners interact with AI?"
**Good:** "How should learners interact with AI?"
**Check:** Does the sentence use meta-commentary about what's coming next? If yes, delete the meta-commentary and state the point directly.
---
### Rule 11: Limit Em Dashes
Use periods instead of em dashes for separation.
**Check:** Are you using more than one em dash per paragraph? If yes, replace some with periods.
---
### Rule 12: Avoid Overly Formal Transitions
Let logical flow carry the connection between ideas.
**Check:** Are you using transitions like "Moreover", "Furthermore", "In addition"? If yes, consider removing them if the logical connection is clear.
---
## Genre-Specific Application
These rules apply differently across writing genres. Personal experience is content in some genres, filler in others.
### Analytical Writing (Essays, Reports, Technical Docs)
- Remove personal voice unless giving opinions
- Lead with claims, not narrative
- Cut meta-commentary about structure
**Example:**
- ❌ "I really like this approach because it works well"
- ✅ "This approach works well"
### Reflective Writing (Academic Reflections, Personal Statements)
- Keep substantive personal narrative
- Remove meta-commentary about the reflection itself
- Maintain first person throughout
**Substantive personal narrative (KEEP):**
- "I have always struggled with X" → Shows pattern/growth
- "For a long time, that made me feel Y" → Demonstrates evolution
- "When I encounter Z now, I think about..." → Shows current practice
**Meta-commentary (REMOVE):**
- "I really like this quote because..." → Just discuss the quote
- "This passage is interesting to me because..." → Discuss the passage directly
- "I find it fascinating that..." → State the observation
**Example from philosophy reflection:**
- ❌ "I really like this quote because I've always disliked a lot of things..."
- ✅ "I have always disliked a lot of things I observe in life. For a long time, that would just make me feel bad. But reflecting on Xunzi has helped me reframe these moments..."
The first version talks about the quote. The second version uses personal experience to engage with the philosophical idea.
### Technical Documentation
- Maximum brevity
- Remove all personal voice
- Direct instructions only
### Blog Posts/Opinion Pieces
- Personal voice encouraged
- Authentic examples valued
- Balance personality with precision
## Decision Framework
**Is this personal content substantive or filler?**
Ask:
1. Does it show growth, pattern, or evolution? → Substantive
2. Does it demonstrate engagement with ideas? → Substantive
3. Is it meta-commentary about my feelings toward the text? → Filler
4. Could I delete it and lose no meaning? → Filler
**Genre check:**
- Reflection/personal statement → Keep substantive personal narrative
- Analytical essay → Remove unless giving explicit opinion
- Technical doc → Remove all personal voice
## Note
User-specific instructions override this style guide.
Other Rules:
- Don't overuse Yet as a word. For example, instead of: "Yet we so easily brag about our meetings with VCs", have "However, we so easily brag about our meetings with VCs"
Or "Through this they persisted," instead of "Yet they persisted"
Note that I don't want you to have so many quotes around everything that is not actually a quote around thins.
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.