style-analysis
How to analyze prose style and produce style reference files. Use when creating, updating, or evaluating style files: the reference documents that capture a project's voice patterns for writer and critic agents.
What this skill does
# Style Analysis How to analyze a project's prose and produce style reference files that writer and critic agents can use. ## Style Has Dimensions Style varies independently along multiple axes: some bound to a character, some to a scene type, some to both, some that cross everything. The first job is identifying what dimensions exist in *this* project, not arriving with a predetermined taxonomy. Look at the text: what varies independently? If a character's narration voice changes by scene type, that's two dimensions interacting. If action pacing stays consistent regardless of narrator, that's scene-bound. The text tells you where the boundaries are. ## File Splitting Style files are the unit of context selection: an orchestrator passes individual files to writers via `-f`. Every file boundary is a context decision: would an agent ever need this chunk without that chunk? Split where a caller would plausibly want one part without the other. A character with distinct dialogue and narration modes might need separate files. A character with a simple, consistent voice needs one. A scene type that works the same regardless of POV is its own file. ## What to Analyze Dimensions worth investigating: the text determines which matter: - **Sentence patterns**: length distribution, rhythm, how it shifts with emotional intensity. Fragment usage, compound tendencies. - **Interiority**: depth of internal monologue. Direct thought, indirect thought, stream of consciousness: when each activates. - **Vocabulary and register**: recurring word choices, domain language, register shifts. - **Dialogue patterns**: how characters sound distinct. Tag frequency, action beats, subtext delivery. - **Humor mechanics**: techniques, timing, what's played for laughs vs what's sacred. - **Emotional approach**: physical manifestation vs named emotions, how much space emotional moments get. - **Sensory detail**: privileged senses, how density shifts by scene type. - **Pacing and paragraph rhythm**: how paragraph length and whitespace shift between scene types. ## File Structure Each style file teaches a voice through principles, not catalogs: - **Principle**: the core insight in a few sentences. What's the pattern? Why does it work? - **Representative examples**: one or two with chapter citations showing the principle in action. - **Chapter pointers**: where to see more of the pattern in context. A writer who internalizes the principle produces natural variation. A writer following an exhaustive checklist produces something mechanical. Each file should be self-describing: a caller reading it should understand what it covers and when to load it. ## Patterns vs Problems Intentional patterns go in style files: the voice a writer should reproduce. Unconscious tics and inconsistencies go in the issues directory: problems for the critic to watch for and the author to address in revision. The test: would the author want a writer agent to reproduce this? If "for a moment" appears 29 times across 17 chapters, that's a tic. If an emotional technique works in chapters 2 and 15 but is absent from chapter 11, that's an inconsistency to log as an issue. ## Quality Tests 1. **Voice test**: could a writer, reading only this file and a scene brief, produce prose the author recognizes as their voice? 2. **Brevity test**: could a writer internalize this file in one read? If they need to keep it open as reference while drafting, it's over-prescribed.
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.