emotion-metaphor-image-prompting
Craft and iteratively refine image-generation and image-edit prompts that turn subtle feelings, idioms, pressure, or social dynamics into concrete visual metaphors. Use when a user can describe the emotion but not the picture yet, when a generated image is close but not exact, or when Codex needs to preserve style while correcting one visible signal at a time.
What this skill does
# Emotion Metaphor Image Prompting ## Overview Turn a vague emotional description into a concrete visual scene, then tighten the image through targeted edit prompts. Prefer visual mechanics over abstract mood words: identify what the viewer must literally see. ## Workflow 1. Extract the emotional mechanics. - Identify the subject, the pressure source, the forced action, and the contradiction. - Translate idioms into visible objects, body positions, and scene dynamics. 2. Build the first prompt from visible signals. - Specify subject, setting, props, action, expression, and emotional duality. - Add style only after the scene is concrete. 3. Refine with preserve-style edits. - Start each edit prompt by naming what must remain unchanged. - State one key correction in plain language. - Add hard visual constraints that the model cannot plausibly miss. - Add negative constraints for the common failure mode you just saw. 4. Diagnose failures visually. - Replace vague feedback like "not the right feeling" with concrete mismatches like "the duck is still standing" or "the rope is blending into the speech letters." ## Prompt Rules - Prefer "the viewer must immediately understand X" over "make it feel more X." - Specify body mechanics when tension matters: stretched neck, dangling legs, feet off ground, shadow gap, taut rope. - Separate physical objects from symbolic effects. If both a rope and floating letters matter, state that they must be visually distinct. - Use preserve-style edit prompts once the image is close. Do not rewrite the whole scene unless the generation is fundamentally wrong. - Change one core visual signal per edit pass unless the current image is far from the intended metaphor. - Name failure-prevention constraints explicitly: "no human figure," "do not replace the rope with glowing lines," "do not let the feet touch the stage." - Preserve emotional duality. Many strong metaphor images need two tones at once, such as painful and funny, pressured and brave, awkward and sincere. ## Edit Strategy When a user says "this is close, but not yet," do this: 1. Keep a short list of preserved elements at the front of the prompt. 2. Describe the single incorrect visual fact. 3. Convert that fact into measurable geometry or material detail. 4. Add one or two "must not" lines based on the last failure. 5. Keep the same emotional tone so the fix does not flatten the image. ## References - Read `references/prompt-patterns.md` for reusable first-pass and edit-pass templates, common failure patterns, and the worked German-practice duck example.
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.