Skills de Claude Code · página 84

>

>

Read and write 3-D point cloud data using Lidar Toolbox file I/O. Covers PLY, PCD, LAS/LAZ, PCAP (Velodyne/Ouster/Hesai), E57, and IDC (Ibeo) formats. Use when loading point clouds from disk, saving to disk, choosing the correct reader or writer for a file format, extracting or preserving lidar point attributes, reading Ibeo IDC sensor recordings, or converting between formats.

>

Register 3-D point clouds using ICP, NDT, LOAM, FGR, phase correlation, and CPD algorithms. Use when registering or aligning 3-D point clouds, choosing a registration algorithm, tuning registration parameters, preprocessing point clouds for registration or combining point clouds after registration.

>-

>

>

>

>

Diagnose MATLAB errors and unexpected behavior. Breakpoints, workspace inspection, try-catch diagnostics, and common error patterns. Use when debugging functions, tracing errors, inspecting variables, or diagnosing runtime failures.

Guides the agent to reference official MathWorks Documentation and Help. Determine correct function syntax and workflows from user guides when deeper context is needed. Minimize iterations and repetitive trial and error. Use this skill to: Identify correct syntax and configuration details. Retrieve relevant, version-specific (or release-specific) information from official documentation. Consult user guides when conceptual or workflow context is needed. Apply best practices.

>

>

>

Diff MATLAB settings between releases AND update any .m file that configures MATLAB settings to use the correct setting paths for the target release. Use when upgrading MATLAB releases and startup scripts or preference files need path/type updates for the new release.

>

Turn raw MATLAB code into a published .mltbx toolbox — full pipeline from scope definition through packaging and release. Drives 8 phases with human checkpoints, enforcing ordering and dependencies. Use when asked to package, create a toolbox, or run the files-to-package pipeline.

>

I am outside the pack root and should not be loaded.

Skill whose name uses a dash, expected to be normalized.

Inspect files on the host filesystem.

Audit disk usage on edge devices.

A skill that uses fields ongrid does not yet recognize.

Search Loki logs.

Always active.

Activated by the word "logs".

A skill nested several directories deep, to verify recursive walk.

设备上跑只读 shell 命令做诊断探索（沙箱化 / read-only policy）

设备文件系统排查工具组 — 找大文件、看目录占用、stat 单文件（一次最多 16 个 path 批量查询）

重启允许列表内的 systemd service（mutating，触发 reviewer 二审）

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Drive a native macOS app via the cua-driver CLI (default) or MCP server — snapshot its AX tree, click/type/scroll by element_index, verify via re-snapshot. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real macOS application on the host (e.g. "open a file in TextEdit", "navigate to /Applications in Finder", "click the Save button in Numbers").

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

openloomi HTTP API reference (local-first, served from the OpenLoomi Desktop app at http://localhost:3414). Use when working with openloomi backend routes — auth, AI, files, integrations, RAG, memory, Loop, pet, workspace, platform callbacks. Triggers: API endpoints, backend routes, /api/*, local API, port 3414, integrations REST, OAuth start, RAG search, loop state, memory search, pet state, audit logs

openloomi Connectors tools - manage the native 7 messaging integrations and pair with the composio skill for the 1000+ apps OAuth layer (Slack, Discord, X, Gmail, Outlook, Google Calendar/Drive/Docs, GitHub, Notion, Linear, HubSpot, LinkedIn, Jira, Asana). Triggers: connect platform, integration status, list accounts, disconnect, list-accounts, status, connect, send-reply, native vs composio, 1000+ apps, list connections.

Use this when users ask about openloomi features, capabilities, or how to use it. Examples: 'openloomi 怎么用', '你能做什么', 'What can you do?', 'How does openloomi work?', 'Tell me about openloomi features', 'What platforms does openloomi support?', 'How do I use scheduled tasks?', 'What is Loop?', 'How does the attention agent work?', 'What is a Decision Card?', 'How do connectors work?', 'How do I extend Loop with custom types?', 'What is a classifier rule?', 'How do I plug openloomi into Claude Code / Codex?'

openloomi Memory tools - search and manage the holistic context (people, projects, decisions, knowledge base, chat insights). Triggers: memory search, knowledge base, search documents, list insights, who is John, what did we decide about X, tiered memory, knowledge graph, people/projects/decisions, search-all, conversation memory

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.

Get current weather and forecasts via wttr.in or Open-Meteo. Use when: user asks about weather, temperature, or forecasts for any location. NOT for: historical weather data, severe weather alerts, or detailed meteorological analysis. No API key needed.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Discover and install skills from the open agent skills ecosystem. Use when: (1) user asks "how do I do X" where X might have an existing skill, (2) user says "find a skill for X" or "is there a skill for X", (3) user asks "can you do X" where X is a specialized capability, (4) user wants to extend agent capabilities, (5) user wants to search for tools, templates, or workflows, (6) user mentions they wish they had help with a specific domain (design, testing, deployment, etc.).

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

High-performance data analysis using Polars - load, transform, aggregate, visualize and export tabular data. Use for CSV/JSON/Parquet processing, statistical analysis, time series, and creating charts.

Persist learning across turns by actively maintaining MENTAL_MODEL.md in the workspace. Use for iterative coding, debugging, benchmarking, or any feedback-driven task; read and update the file with actual filesystem writes before every response, never just hidden/internal memory.

Create an end-to-end Continual Learning Bench task. Use when adding a new src/tasks/<name> benchmark task, including design interview, concrete Jinja prompt templates, JSON action contracts, observation templates, debug schedule, behavioral E2E tests, validation, smoke/debug runs with icl and icl_notepad, and README documentation.

Use 1000+ external apps via Composio - either directly through the CLI or by building AI agents and apps with the SDK

OpenLoomi × Claude Code hooks installer. Use when the user wants Claude Code's lifecycle (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop, Notification) to mirror onto the Loomi Pet, or wants to auto-archive every Stop into OpenLoomi memory. Triggers: install hooks, /openloomi:hooks, hooks install, hooks uninstall, hooks status, mirror claude on pet, auto-archive stop.

OpenLoomi install & first-use setup helper for Codex. Use when the user wants to install OpenLoomi, configure it, or troubleshoot `INSTALL_REQUIRED` / `SOURCE_FOUND_APP_NOT_BUILT` / `SESSION_INITIALIZATION_REQUIRED` after running setup-status. Triggers: install openloomi, configure openloomi, setup openloomi, openloomi not installed, openloomi not finalized, install_required, install missing, guest session.

openloomi's Loop — the proactive execution brain that runs inside the OpenLoomi desktop app. Use this skill to inspect state, run a tick, schedule / cancel decision actions, tune preferences, and extend Loop with user-defined decision types, Composio-backed signal channels, or deterministic classifier rules. Triggers: 'openloomi loop', 'loop tick', 'loop schedule', 'loop inbox', 'loop run', 'proactive decisions', 'signal → decision → execute', 'pull signals', 'decision queue', 'register loop type', 'add loop decision type', 'register custom channel', 'add composio channel', 'add loop rule', 'register classifier rule', 'force loop type', 'dry-run loop rule', 'list my loop extensions', 'remove loop type', 'delete loop channel'

OpenLoomi Pet sprite and state helper for Codex. Use for pet state, themes, custom characters, and sprite overrides.

Walk a brand-new OpenLoomi user through the entire pipeline in one guided session: setup health → pet reaction → connector onboarding → run a Loop tick → inspect & approve a decision card → seed Memory → optionally register a custom Loop channel / classifier rule / decision type. Triggers: openloomi tour, guided tour, walk me through openloomi, show me everything, end-to-end demo, 带我看一下, 体验一下, 一条龙, 一键体验, first time using openloomi, what's next after setup.

OpenLoomi entrypoint for skill-only agent runtimes without a plugin mechanism. Use when the user mentions OpenLoomi or Loomi, wants first-use setup guidance, wants to use local OpenLoomi memory, connectors, Loop, knowledge base, RAG search, or asks how to install OpenLoomi skills in runtimes such as WorkBuddy or other skill-capable agents.

OpenLoomi first-use setup and readiness guidance for skill-only agent runtimes. Use when OpenLoomi is not yet installed, the local API is not reachable, the session/token is missing, or the user needs a manual install and launch walkthrough before using OpenLoomi skills.

Inspect OpenLoomi Goals from a skill-capable agent. Use when listing active Goals or checking a Goal's ordered steps and current progress.

Identify whether a user is asking OpenLoomi to generate a lifestyle image, portrait, personal visual, or lifestyle scene. Use this skill for chat messages that may request image generation for a user's lifestyle, identity, persona, personal brand, social profile, memories, interests, or real-life scene; distinguish true generation intent from ordinary image understanding, prompt-writing, editing, or negated requests.

Match a design project to supported design-award programs, tracks, and entry categories; apply structural eligibility gates; verify current official rules; compare published criteria and cautiously described winner trends; and output fit, evidence confidence, and submission priority. Use when a user asks which award or category to enter, compares awards, or requests an award-fit analysis. Supports iF, iF Student, Red Dot Product, Red Dot Design Concept, IDEA, DIA, K-Design, GOOD DESIGN AWARD Japan, Core77, James Dyson, and EPDA. Do not use for winner retrieval alone, detailed submission-file compliance, general design evaluation, optimization, or winning-probability prediction.

Route and coordinate an end-to-end design-award workflow across winner research, evidence-based evaluation, award matching, entry-text preparation, and final submission checking. Use when a user asks for a complete award plan, does not know which Design Judge skill to use, wants multiple stages coordinated, or needs a resumable workflow with explicit handoffs. Do not replace the specialist skills, invent project facts, treat scores as winning probabilities, or bypass current official-rule verification.

Find and verify award-winning designs in the same or adjacent functional category through eight explicit relevance dimensions: problem and user, core function, sensing technology, intervention mechanism, physical form, use context and workflow, system architecture, and visual language. Use when a user asks for same-category winners, comparable precedents, design benchmarks, appearance-related award winners, or examples from iF Design, Red Dot, IDEA, or iF Design Student Award. Do not use this skill to score, judge, optimize, or match the user's design to an award.

Evaluate one design or a user-approved maturity-mapped batch through a transparent evidence-based rubric. Classify each work, score design quality and presentation, identify Critical risks, report evidence confidence, and optionally shortlist works within separate maturity tracks. Use when a user asks to judge, score, critique, review, diagnose, batch-evaluate, or rank designs by evidence-aligned evaluation score. Do not use this skill to retrieve winners, choose an award, produce a redesign, audit submission-file compliance, simulate an official jury, or predict winning probability.

Extract evidence-grounded project facts from user-provided design attachments, identify missing information, and prepare the exact written fields required by supported design-award entry forms. Use when a user asks to prepare, draft, adapt, translate, or validate application text for iF, iF Student, Red Dot Product Design, IDEA, DIA, K-Design, GOOD DESIGN AWARD Japan, Core77, James Dyson, or EPDA. Also use to build a reusable project dossier from briefs, decks, reports, manuals, patents, research, images, or prior application materials. Do not use for award selection alone, winner retrieval, design-quality scoring, final file-format auditing, or winning-probability prediction.

Shared support package for the Design Judge skill collection. Install it with design-award-search and design-award-match so those skills can read the canonical functional-design taxonomy and official award-source registry. Do not invoke it as a standalone design workflow.

Audit a design-award submission package against the current official rules for a specific award cycle. Check required materials and technical constraints, cross-material facts and claims, rights and disclosure risks, and final submission readiness. Use when a user asks for a pre-submission check, compliance review, missing-material audit, consistency check, or final go/no-go decision. Do not use this skill to choose an award, retrieve winners, judge the design itself, rewrite the whole entry, or give a legal clearance opinion.

Design and build complete web experiences from scratch — award-level product and marketing pages, cinematic scroll-directed sites where the page is directed like a film, and multi-screen products (app, dashboard, admin, settings, onboarding, docs site) built as one design system with every component, state and route in one style. Use whenever the user wants to create or redesign a landing page, website, hero section, portfolio, promo or product page; wants scroll animations, storytelling pages, or a site that feels like a movie; or says "make it beautiful", "make it wow", "cinematic", or "design system" — even if they name no technique. Generates its own assets via local CLIs (images, video frames, depth maps, 3D), and gates every ship with an executable anti-slop linter and a screenshot verification loop. Not for polishing a UI someone else built, and not for backend-only work.

Hit the Cloudflare REST API directly for operations that wrangler and MCP can't handle well. Bulk DNS, custom hostnames, email routing, cache purge, WAF rules, redirect rules, zone settings, Worker routes, D1 cross-database queries, R2 bulk operations, KV bulk read/write, Vectorize queries, Queues, and fleet-wide resource audits. Produces curl commands or scripts. Triggers: 'cloudflare api', 'bulk dns', 'custom hostname', 'email routing', 'cache purge', 'waf rule', 'd1 query', 'r2 bucket', 'kv bulk', 'vectorize query', 'audit resources', 'fleet operation'.

Scaffold and deploy Cloudflare Workers with Hono routing, Vite plugin, and Static Assets. Describe project, scaffold structure, configure bindings, deploy. Use whenever the user wants to create a Worker project, set up Hono on Cloudflare, configure D1 / R2 / KV / Queues bindings, or troubleshoot Worker export syntax, API route conflicts, HMR issues, or deployment failures.

Generate Drizzle ORM schemas for Cloudflare D1 databases with correct D1-specific patterns. Produces schema files, migration commands, type exports, and DATABASE_SCHEMA.md documentation. Handles D1 quirks: foreign keys always enforced, no native BOOLEAN/DATETIME types, 100 bound parameter limit, JSON stored as TEXT. Use when creating a new database, adding tables, or scaffolding a D1 data layer.

Cloudflare D1 migration workflow: generate with Drizzle, inspect SQL for gotchas, apply to local and remote, fix stuck migrations, handle partial failures. Use when running migrations, fixing migration errors, or setting up D1 schemas.

Generate database seed scripts with realistic sample data. Reads Drizzle schemas or SQL migrations, respects foreign key ordering, produces idempotent TypeScript or SQL seed files. Handles D1 batch limits, unique constraints, and domain-appropriate data. Use when populating dev/demo/test databases. Triggers: 'seed database', 'seed data', 'sample data', 'populate database', 'db seed', 'test data', 'demo data', 'generate fixtures'.

Scaffold Hono API routes for Cloudflare Workers. Produces route files, middleware, typed bindings, Zod validation, error handling, and API_ENDPOINTS.md documentation. Use after a project is set up with cloudflare-worker-builder or vite-flare-starter, when you need to add API routes, create endpoints, or generate API documentation.

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per project.

Scaffold a full-stack Cloudflare app from the vite-flare-starter template — React 19 + Hono + D1+Drizzle + better-auth + Tailwind v4+shadcn/ui + TanStack Query + R2 + Workers AI. Run setup.sh to clone, configure, and deploy. Use whenever the user wants a batteries-included Cloudflare full-stack app, vite-flare-starter scaffold, or a React + Cloudflare app with auth + database + Workers AI ready to go.

Generate AI images using Gemini or GPT APIs directly. Covers model selection (Gemini for scenes; GPT Image 2 for text rendering, batch variations, multi-reference compositing; GPT Image 1.5 for transparent icons), the 5-part prompting framework, API calling patterns, multi-turn editing, and quality assurance. Produces photorealistic scenes, icons, illustrations, OG images, posters, infographics, and product shots. Use when building websites that need images, creating marketing assets, or generating visual content. Triggers: 'generate image', 'ai image', 'create hero image', 'make an icon', 'generate illustration', 'create og image', 'poster', 'infographic', 'image variations', 'gpt-image-2', 'ai art', 'image generation'.

Generate complete, accessible colour palettes from a single brand hex. Produces 11-shade scale (50-950), semantic tokens, dark mode variants, Tailwind v4 CSS output, WCAG contrast checks. Use whenever the user supplies a brand hex and asks for a palette, mentions setting up a design system, wants Tailwind theme colours from a brand colour, or asks to check colour accessibility / contrast.

Generate custom favicons from logos, text, or brand colours. Produces favicon.svg, favicon.ico, apple-touch-icon.png, icon-192/512.png, and web manifest. Use whenever the user wants a favicon, mentions replacing a CMS default favicon, converting a logo into a favicon, creating branded initials icons, or troubleshooting favicon not displaying / iOS black square / missing manifest.

Generate cohesive, project-specific SVG icon sets for websites and applications. Use this skill whenever the user needs custom icons, an icon set for a website or app, icons for a client project, or mentions needing SVG icons that look consistent together. Also trigger when the user describes a project and icons would naturally be part of the deliverable — e.g. 'I'm building a site for a plumber' implies they'll need service icons. Trigger on: 'icons for', 'icon set', 'custom icons', 'SVG icons', 'make me icons', 'I need icons', 'website icons', 'project icons', or any request for consistent visual assets for a web project. Produces individual SVG files with a consistent style engine, not generic icon library lookups.

Process images for web development — resize, crop, trim whitespace, convert formats (PNG/WebP/JPG), optimise file size, generate thumbnails, create OG card images. Uses Pillow (Python) — no ImageMagick needed. Trigger with 'resize image', 'convert to webp', 'trim logo', 'optimise images', 'make thumbnail', 'create OG image', 'crop whitespace', 'process image', or 'image too large'.

Generate complete user documentation for a web app with screenshots. Browses the app via browser automation, screenshots every screen, and produces a structured user guide with step-by-step instructions, annotated screenshots, workflow diagrams, and reference tables. Supports quick (key screens), standard (all pages), thorough (every state and flow), and exhaustive (publishable documentation suite). Triggers: 'document the app', 'user guide', 'app documentation', 'screenshot docs', 'generate user docs', 'help docs', 'how-to guide', 'write the docs'.

Get a second opinion from leading AI models on code, architecture, strategy, prompting, or anything. Queries models via OpenRouter, Gemini, or OpenAI APIs. Supports single opinion, multi-model consensus, and devil's advocate patterns. Use whenever the user says 'brains trust', 'second opinion', 'ask gemini', 'ask gpt', 'peer review', 'consult another model', 'challenge this', or 'devil's advocate'.

Run an independent code review using the OpenAI Codex CLI in headless mode. Gets a second opinion from a different model family (the current Codex models) on recent changes, a PR, a commit, or the whole app — covering bugs, regressions, security, data consistency, UX/state bugs, performance risks, and testing gaps. Saves a severity-prioritised report to .jez/reviews/. Triggers: 'codex review', 'review with codex', 'independent code review', 'what does codex think', 'get codex to review'.

Deep research and discovery before building something new. Explores local projects for reusable code, researches competitors, reads forums and reviews, analyses plugin ecosystems, investigates technical options, and produces a comprehensive research brief. Three depths: focused (30 min), wide (1-2 hours), deep (3-6 hours). Triggers: 'research this', 'discovery', 'explore the space', 'what should I build', 'competitive analysis', 'before I start building', 'research before coding'. Not for cited fact-checking research reports (a separate harness does those); this is pre-build product discovery.

Audit and enforce the core/client boundary in multi-client projects. Detects where shared platform code is tangled with client-specific code, finds hardcoded client checks, config files that replace instead of merge, scattered client code, migration conflicts, and missing extension points. Produces a boundary map, violation report, and refactoring plan. Optionally generates FORK.md documentation and restructuring scripts. Triggers: 'fork discipline', 'check the boundary', 'is this core or client', 'platform audit', 'client separation', 'fork test', 'refactor for multi-client', 'clean up the fork'.

Guided git workflows: prepare PRs, clean up branches, resolve merge conflicts, handle monorepo tags, squash-and-merge patterns. Use when asked to prepare a PR, clean branches, resolve conflicts, or tag a release.

Prepare and publish GitHub releases. Sanitizes code for public release (secrets scan, personal artifacts, LICENSE/README validation), creates version tags, and publishes via gh CLI. Trigger with 'release', 'publish', 'open source', 'prepare for release', 'create release', or 'github release'.

Audit and generate in-app user guidance — onboarding flows, empty states, tooltips, feature tours, contextual help, defaults, and inline hints. Browses the app to find where new users would get stuck, then produces the actual content and code to fix it. Pairs with ux-audit: audit finds problems, this skill builds the solutions. Triggers: 'onboarding', 'help content', 'empty states', 'user guidance', 'first run experience', 'feature tour', 'app is confusing', 'new user experience', 'make the app welcoming'.

Generate project documentation from codebase analysis — ARCHITECTURE.md, API_ENDPOINTS.md, DATABASE_SCHEMA.md. Reads source code, schema files, routes, and config to produce accurate, structured docs. Use when starting a project, onboarding contributors, or when docs are missing or stale. Triggers: 'generate docs', 'document architecture', 'create api docs', 'document schema', 'project documentation', 'write architecture doc'.

All-in-one project configuration and health management. Sets up new projects (settings.local.json, CLAUDE.md, .gitignore), audits existing projects (permissions, context quality, MCP coverage, leaked secrets, stale docs), tidies accumulated cruft, captures session learnings, and adds permission presets. Uses sub-agents for heavy analysis to keep main context clean. Trigger with 'project health', 'check project', 'setup project', 'kickoff', 'bootstrap', 'tidy permissions', 'clean settings', 'capture learnings', 'audit context', 'add python permissions', or 'init project'.

Test website responsiveness across viewport widths using browser automation. Resizes a single session through breakpoints, screenshots each width, and detects layout transitions (column changes, nav switches, overflow). Produces comparison reports showing exactly where layouts break. Trigger with 'responsiveness check', 'check responsive', 'breakpoint test', 'viewport test', 'responsive sweep', 'check breakpoints', or 'test at mobile'.

Plan and execute entire application builds. Generates phased delivery roadmaps, then executes them autonomously — phase by phase, committing at milestones, deploying, testing, and continuing until done or stuck. Modes: plan (generate roadmap), start (begin executing), resume (continue from where you left off), status (show progress). Triggers: 'roadmap', 'start building', 'resume the build', 'keep going', 'build the whole thing', 'execute the roadmap', 'what phase are we on'.

Post project updates to team chat, gather feedback, triage responses, and plan next steps. Adapts to available tools (chat, git, issues, tasks). First run discovers tools and saves a playbook; subsequent runs execute from the playbook. Trigger with 'team update', 'post update', 'sync with team', 'standup', 'check team chat', 'feedback loop', 'project update', 'what did the team say'.

Walk through a live web app AS a real user to find usability + behavioural bugs that static reviews miss. REQUIRES proof of interaction (typing, clicking, sending, observing) before any verdict — a sweep that didn't interact terminates with verdict 'Incomplete'. Walks threads, exercises every element, runs the multi-pane stress matrix, visual polish sweep, component perfection checklist, automated a11y (axe-core), pragmatic performance budget (LCP/CLS/INP), scenario battery (11 scenarios), and stress recipes including the real-flavour data battery. Hard gates: console errors/warnings = 0, network 5xx = 0, layout collapse = 0, axe Critical/Serious = 0, perf budget green. Audit-the-audit meta-check rejects rushed reports. Each finding has reproduction steps, evidence path, and suspected code location. Trigger with 'ux audit', 'walkthrough', 'qa sweep', 'audit the app', 'dogfood this', 'check all pages', 'find what's broken', 'stress the UI'.

Compare UX patterns across multiple reference apps using pattern libraries produced by ux-extract. Reads 2+ pattern-library.md files, walks them category by category, identifies where apps converge (strong signal), where they diverge (genuine design choice), what's unique to one app, and what's absent across the set. Produces an opinionated comparison document with recommendations for a new build. No browser needed — pure markdown analysis. Trigger with 'compare UX patterns', 'how do top apps handle X', 'ux comparison', 'pattern comparison across reference apps'.

Exhaustively extract UX patterns from a reference web app. Walks every screen, captures screenshots of every state, records interaction patterns, copy verbatim, keyboard shortcuts, responsive treatments, motion, and empty/error/loading states. Produces a reusable pattern library that other audits can compare against. The inverse of ux-audit — asks 'what is the bar?' rather than 'does this match the bar?'. Trigger with 'learn from X', 'extract patterns from X', 'study X's UX', 'reverse engineer the UX of X', 'build a pattern library from X'.

Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously, build all pages of a site, generate multiple pages in sequence, or run a 'design loop' / 'baton loop' / 'autonomous site build' — even if they say 'just keep going' or 'build the next page' or 'next page' mid-flow.

Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots. Triggers: 'design review', 'does this look good', 'review the design', 'check the layout', 'is this polished', 'visual review', 'design audit', 'make it look better', 'it looks off'.