prose-writing
Prose-level immersion patterns for narrative fiction. Use when writing or revising prose: the sentence-level and paragraph-level craft that pulls readers into the story. Project-specific voice comes from style files passed alongside this skill.
What this skill does
# Prose Writing
How prose pulls readers in. Style files carry the project's specific voice;
read them before writing. This skill covers the patterns that create immersion
regardless of project.
## Psychic Distance
The distance between the reader and the character's consciousness. Gardner's
continuum runs from far ("It was winter of the year 1853. A large man stepped
out of the doorway.") to close ("Snow. Under your collar, down inside your
shoes, freezing and plugging up your miserable soul.").
Control this deliberately. Move closer for emotional peaks, character-defining
moments, and interiority. Pull back for transitions, time compression, and
establishing context. The rhythm of close and far gives prose its emotional
shape.
Default AI prose sits at a flat middle distance: close enough to seem
personal, far enough to feel safe. Push past that. Go closer when it matters.
## Free Indirect Discourse
Blend the narrator's voice with the character's perspective so third-person
narration is colored by how the character thinks and sees.
Conventional: "Connie thought she was pretty and she believed that was the
most important thing she could be."
Free indirect: "She knew she was pretty and that was everything."
The narrator doesn't announce the character's thoughts. The narration itself
carries the character's voice, vocabulary, and judgment. This is the primary
technique for close-third that actually feels intimate. Use the character's
words, not the narrator's, when psychic distance is close.
## Sentence Rhythm
Rhythm pulls readers along like a current. Vary length, structure, and pattern
to match the moment.
Short sentences for tension, shock, emphasis. Longer cumulative sentences for
immersion, reflection, complex emotion. Fragments for intimacy, interrupted
thought, the feeling of a mind catching up to what just happened.
When every sentence follows the same pattern, such as subject, verb, object,
repeat, the prose flattens regardless of content. A devastating scene and a
mundane scene should not read the same way.
## Sensory Grounding
Ground scenes in specific sensory details filtered through the POV character's
attention. "The forest" is nowhere. "Pine needles crunching underfoot, the
smell of wet bark" is a place.
What a character notices reveals who they are. A chef notices smells. A
musician notices sounds. A soldier notices exits. One or two vivid, specific
details do more work than a catalog of all five senses.
## Interiority
The POV character's inner life distinguishes prose fiction from screenplay:
thoughts, reactions, memories, associations. "She felt sad" is a label.
"She kept reaching for her phone to text him before remembering" is interiority
that shows the reader something about grief.
In high-action scenes, interiority contracts to fragments: quick reactions,
snap judgments. In reflective scenes, it expands. Match the depth of inner
experience to the pace of the scene.
## Show Through Action
Demonstrate character states through behavior, dialogue, and physical response.
"He was nervous about the meeting" is a label. "He checked his watch for the
third time, then straightened a tie that was already straight" lets the reader
see the nervousness and interpret it.
Tell for logistics, show for moments that matter. Summary narration works for
transitions, routine actions, and time compression. Showing everything is as
exhausting as telling everything.
## Point of View
Stay in the established POV. In first person, the narrator can only report
what they perceive, think, and feel. In third limited, access one character's
interiority per scene.
Convey non-POV characters through observable behavior. Write "Her jaw
tightened" rather than "She felt angry." The narrator can't know what's
happening in someone else's head.
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.