autoresearch
Automatically research and reverse-engineer a technique, visual effect, algorithm, or codebase. Given a reference (image, video, URL, library name, description, or existing code), Claude researches how it works, reverse-engineers the approach, and produces a structured findings document. Use when you want to understand "how is this made", "reverse engineer this effect", "research this technique", or "figure out how X works so I can implement it".
What this skill does
# Autoresearch Given a reference target, automatically research it and produce a reverse-engineering report with implementation guidance. ## Input (via $ARGUMENTS or conversation context) The target can be any of: - A visual reference — image path, screenshot, video frame - A URL — article, repo, shader toy link, paper - A library or tool name — "how does pixelmatch work" - A description — "that liquid metal refraction effect" - An existing codebase or file — reverse-engineer undocumented code - A combination of the above ## Research phases ### 1. Identify the target Clarify what's being researched: a visual technique, an algorithm, an architecture, a library internals. If ambiguous, ask one focused question before proceeding. ### 2. Collect evidence - **Visual refs**: analyze images/screenshots with vision tools — describe what's happening geometrically, mathematically, temporally - **Code refs**: read source files — identify core algorithms, data structures, key functions - **Web research**: search for papers, shader implementations, blog posts, prior art - **Existing project context**: scan `refs/`, `docs/`, `reference/`, `CLAUDE.md`, `README.md` in the working directory for related material already gathered ### 3. Reverse engineer Break the technique into layers: - What is the high-level effect or behavior? - What mathematical/algorithmic primitives drive it? - What are the key parameters and how do they interact? - What are the non-obvious parts (the "tricks")? - What constraints apply (platform, performance, compatibility)? ### 4. Implementation map Translate findings into actionable implementation notes for the current project: - Language/platform fit (GLSL ES 1.00, Metal MSL, TypeScript, etc.) - Suggested implementation order (scaffold → core → details) - Known pitfalls from the research ## Output Save a Markdown report to `refs/research-<topic>-<YYYY-MM-DD>.md` if a `refs/` folder exists, otherwise to the current directory as `research-<topic>-<YYYY-MM-DD>.md`. ```markdown # [Topic] — Autoresearch _Date: YYYY-MM-DD | Source: [reference used]_ ## What it is One paragraph: the effect/technique/system in plain terms. ## How it works ### Core mechanism ### Key mathematical primitives ### Parameters & controls ### The non-obvious parts ## Prior art & references - [link or file] — what it contributes ## Implementation map ### Platform notes ### Suggested approach ### Pitfalls ## Open questions - [ ] ... ``` ## Behavior 1. Identify the target from `$ARGUMENTS` or conversation context. 2. Run all relevant research phases in parallel where possible. 3. Synthesize into the report structure above — omit empty sections. 4. Save the file and confirm path to user. 5. Optionally: if the project has a `todo.md` or `tasks.md`, offer to append a follow-up implementation task. $ARGUMENTS
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.