Claude Code Skills · page 144

Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on changed components.

Multi-angle codebase exploration spawning 3-5 parallel agents for code structure, data flow, architecture patterns, and health assessment. Generates ASCII visualizations, import graphs, and design pattern detection with cross-session memory storage. Use when exploring a repo, discovering architecture, onboarding to a new codebase, or analyzing design patterns.

Manages OrchestKit learning system including feedback status, usage pattern tracking, and privacy/analytics consent. Supports pause/resume learning, data export, privacy policy display, and bug reporting. Tracks learned patterns and agent performance metrics. Use when reviewing learned patterns, pausing learning, or managing data consent.

Figma-to-code design handoff patterns including Figma Variables to design tokens pipeline, component spec extraction, Dev Mode inspection, Auto Layout to CSS Flexbox/Grid mapping, and visual regression with Applitools. Use when converting Figma designs to code, documenting component specs, setting up design-dev workflows, or comparing production UI against Figma designs.

Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.

GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.

Golden dataset lifecycle patterns for curation, versioning, quality validation, and CI integration. Use when building evaluation datasets, managing dataset versions, validating quality scores, or integrating golden tests into pipelines.

OrchestKit help directory with categorized skill listings. Use when discovering skills for a task, finding the right workflow, or browsing capabilities.

Implements internationalization (i18n) in React applications. Covers user-facing strings, date/time handling, locale-aware formatting, ICU MessageFormat, and RTL support. Use when building multilingual UIs or formatting dates/currency.

Full-power feature implementation using parallel subagents for backend, frontend, testing, and security, with worktree isolation and quality verification in one workflow. Chains with /ork:cover for tests and /ork:verify for validation. Use when asked to build, add, create, scaffold, or set up a new feature, endpoint, component, or UI capability. Not for fixing a bug, reviewing, explaining, testing, or comparing existing code.

UI interaction design patterns for skeleton loading, infinite scroll with accessibility, progressive disclosure, modal/drawer/inline selection, drag-and-drop with keyboard alternatives, tab overflow handling, and toast notification positioning. Use when implementing loading states, content pagination, disclosure patterns, overlay components, reorderable lists, or notification systems.

GitHub issue workflow ceremony using gh CLI — labels issues as in-progress, creates feature branches (issue/N-description), commits with issue references, posts progress comments, and links PRs with Closes #N. Keeps issues in sync with development work. Use when starting work on an issue, tracking progress, or completing work with a PR.

json-render component catalog patterns for AI-safe generative UI. Define Zod-typed catalogs that constrain what AI can generate, use @json-render/shadcn for 36 pre-built components, optimize specs with YAML mode, and apply the three edit modes (patch/merge/diff) for progressive updates. Use when building AI-generated UIs, defining component catalogs, or integrating json-render into React/Vue/Svelte/React Native/Ink/Next.js projects.

LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph pipelines, multi-agent systems, or AI workflows.

LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.

TAM/SAM/SOM market sizing with top-down and bottom-up estimation methods, cross-validation of assumptions, and divergence reconciliation. Generates investor-ready materials with growth projections and confidence intervals. Use when estimating addressable markets, validating opportunity size, or preparing pitch deck market slides.

MCP server building, advanced patterns, and security hardening. Use when building MCP servers, implementing tool handlers, choosing a transport, adding OAuth authentication, wiring MCP Apps UI with @mcp-ui, hardening MCP security, or debugging MCP integrations.

Interactive MCP visual output via @json-render/mcp: upgrade plain JSON tool responses to dashboards rendered in sandboxed iframes inside MCP clients like Claude, Cursor, and ChatGPT. Use when a tool result would read better as a stat grid, data table, or status badge than as text. For the server itself (transport, auth, tool handlers, security) reach for ork:mcp-patterns.

Knowledge graph orchestration layer with entity extraction, natural language query parsing, deduplication (>85% similarity), and cross-reference boosting. Unifies search results ranked by recency, relevance, and authority. Use when designing memory retrieval, building entity graphs, or optimizing knowledge graph queries.

Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the knowledge graph.

Monitoring and observability patterns for Prometheus metrics, Grafana dashboards, Langfuse v4 LLM tracing (as_type, score_current_span, should_export_span, LangfuseMedia), and drift detection. Use when adding logging, metrics, distributed tracing, LLM cost tracking, or quality drift monitoring.

Multi-surface rendering with json-render — one JSON spec produces React web, Next.js, React Native, Ink terminal UIs, PDFs, emails, Remotion videos, OG images, and 3D scenes. Covers renderer target selection, registry mapping, and platform APIs (renderToBuffer, renderToStream, renderToFile). Use when generating output for several platforms or creating PDF reports, email templates, demo videos, or social images from one component spec.

Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via `gen4_turbo`), or building multimodal AI pipelines.

NotebookLM integration patterns for external RAG, research synthesis, studio content generation (audio, cinematic video, slides, infographics, mind maps), and knowledge management. Use when creating notebooks, adding sources, generating audio/video, or querying NotebookLM via MCP.

OKR trees, KPI dashboards, North Star Metric, leading/lagging indicators, and experiment design. Use when setting team goals, defining success metrics, building measurement frameworks, or designing A/B experiment guardrails.

Performance optimization patterns covering Core Web Vitals, React render optimization, lazy loading, image optimization, backend profiling, LLM inference, and sustainability UX. Use when improving page speed, debugging slow renders, optimizing bundles, reducing image payload, profiling backend, deploying LLMs efficiently, or reducing digital carbon footprint.

Named HTTPS .localhost URLs with portless (v0.15.x). Eliminates port collisions, gives agents stable URLs, adds branch-named subdomains for git worktrees, LAN mode (--lan), and Tailscale sharing. Use when setting up a local dev environment or testing from phones and tablets on the same wifi. Do NOT use for production deployments, CI environments (set PORTLESS=0), or DNS/hosting configuration.

Decomposes a PRD, issue, or spec into a copy-pasteable single `/goal until ..., or stop after N turns` line. Use when running /goal against a spec, to reduce acceptance criteria to AND-joined boolean assertions.

Creates zero-dependency, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web slides, or create a slide deck for a talk, pitch, or tutorial. Generates single self-contained HTML files with inline CSS/JS.

Prioritization frameworks — RICE, WSJF, ICE, MoSCoW, and opportunity cost scoring for backlog ranking. Use when prioritizing features, comparing initiatives, justifying roadmap decisions, or evaluating trade-offs between competing work items.

A/B test evaluation, cohort retention analysis, funnel metrics, and experiment-driven product decisions. Use when analyzing experiments, measuring feature adoption, diagnosing conversion drop-offs, or evaluating statistical significance of product changes.

Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when building ROI projections, competitive analysis, RICE scoring, OKR trees, user personas, PRDs, or usability testing plans.

Production Python async patterns including asyncio TaskGroup, FastAPI dependency injection and middleware, SQLAlchemy 2.0 async sessions, and database connection pool tuning. Python 3.11+ examples with structured error handling. Use when building async services, FastAPI endpoints, or tuning database connection pools.

Use when assessing task complexity, before starting complex tasks, when stuck after multiple attempts, or reviewing code against best practices. Provides quality-gates scoring (1-5), escalation workflows, and pattern library management.

Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.

Use when building Next.js 16+ apps with React Server Components. Covers App Router, Cache Components (replacing experimental_ppr), streaming SSR, Server Actions, and React 19 patterns for server-first architecture.

Audits OrchestKit sub-agent activation from real spawn telemetry — computes the generic-vs-specialist spawn split, flags dormant agents (never fired), and classifies each as fires/mis-triggered/niche. The agent-side analogue of audit-skills. Use when specialized agents feel under-used, before pruning the catalog, or after wiring new agent spawn paths.

Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another skill (no recursion). Triggers on: auto, do this, figure out, just make, I want, help me, fix, build, improve, any goal description.

Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a request asks to assess, rate, compare, identify trade-offs, evaluate readiness, or decide whether an approach is good enough. Do not use for a full pull-request review or to implement a chosen solution.

Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when a request asks to brainstorm, think through options, choose an approach, evaluate trade-offs, or resolve significant uncertainty before implementation. Do not use for an already specified mechanical change.

Map an unfamiliar codebase, feature, architecture, data flow, or operational path with file-backed evidence. Use when a request asks how a system works, where behavior lives, what changed, which dependencies matter, or for onboarding before a change. Do not use to implement or fix the code.

Make an approved, scoped change and prove the affected behavior. Use when a request asks to implement, build, add, or land a feature that already has an agreed approach. Do not use to explore, review, or verify existing work, or to choose between approaches.

Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a request asks to review a PR, review a diff, find real bugs, assess merge risk, or provide evidence-backed review findings. Do not use for implementation or style-only cleanup.

Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove, check readiness, run the relevant tests, or distinguish a claimed result from an observed one. Do not use to write missing tests or fix failures.

Declarative catalog of named aesthetic recipes — exact shadow stacks, glass surfaces, gradient treatments, and type scales as copy-paste values with Use-When and Avoid rules. Use when the user asks for polished elevation, glassmorphism, a border gradient, a mesh background, or any 'make it look like X' request where taste should come from a versioned recipe instead of being reinvented per session.

Render an answer as ASCII art plus semantic emojis inline, right now, with no setup questions. Use for a fast visual take on status, comparisons, trade-offs, architecture, or any ad-hoc 'show me X visually' ask. For a full multi-artifact plan playground, use visualize-plan instead.

Refuse a verdict a probe did not earn. Runs a check where the fault IS present and where it is NOT, and blocks the answer when both arms print the same thing, because a check that cannot disagree with you has measured nothing. Also catches the zero-sample sweep that reads as "clean" and the swallowed error that reads as success. Use before reporting any status, audit, sweep, or "nothing found" result, and whenever a check surprises you by passing.

Chinese Word document formatting toolkit for .docx/.doc/.wps workflows. Use when Codex needs to diagnose document formatting, fix mixed Chinese/English punctuation and spacing, apply official/academic/legal/custom presets, normalize tables and page numbers, preserve or output Word revision marks, convert plain text or Markdown into formatted DOCX, or batch/script document cleanup for Chinese official documents.

Use when managing Paperclip AI agent companies - creating tasks, managing agents, approving hires, running heartbeats, or any Paperclip control-plane operations via CLI or REST API. Triggers on "paperclip", "задача агенту", "одобри найм", "heartbeat", "запусти агента".

Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.

Use when user asks for Claude Code usage stats, weekly analytics, project activity summary, or wants to see what projects were worked on. Triggers on "аналитика", "статистика claude", "cc stats", "weekly report", "что делал

Use when needing strategic project analysis from multiple independent expert perspectives. Triggers on business decisions, growth strategy, product direction, competitive analysis, or any situation where diverse C-level opinions reduce blind spots

Use when creating or refactoring CLAUDE.md files - enforces best practices for size, structure, and content organization

>-

>-

>-

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on "/html-draft", "сделай blueprint", "технический чертёж", "архитектурная схема", "инженерная схема", "blueprint diagram", "engineering blueprint", "technical spec sheet", "architecture diagram", "system flow diagram".

>-

>-

Use when preparing for, running, or closing a live meeting with an AI assistant dashboard. Triggers on "meeting copilot", "live copilot", "prepare for a call", "update copilot", "close the session", or requests to turn transcript chunks into meeting questions, topic maps, decisions, and follow-ups.

Use when you want several genuinely different design directions to choose from instead of one design you will iterate on — a page or UI redesign, a hero, a landing, a thumbnail layout — or a live/stream design bake-off where an audience votes. Triggers on "дай варианты дизайна", "несколько вариантов на выбор", "редизайн", "design options", "design bake-off", "/parallel-design-variants".

Проводит структурированный сеанс дивергенции вокруг конкретной продуктовой проблемы или возможности. Встроены SCAMPER (7 ракурсов), 5 Whys для поиска корневой причины, кросс-доменное вдохновение, ограничивающие инновации, обратный брейншторм и матрица Impact/Effort для отбора. На выходе — ≥10 идей с детально проработанным Top-3. User-invoked only — do NOT auto-trigger. Triggers on /pm-brainstorm, "идеи для продукта", "продуктовый брейншторм", "дивергенция идей", "How Might We", "SCAMPER", "product brainstorm", "feature ideas".

Готовит многомерный разбор конкурентов — feature-матрица, SWOT с cross-strategy, 5 сил Портера, сравнение ценообразования, позиционирование, прогноз стратегических ходов и три уровня дифференциации (догнать / отстроиться / создать новое). Адаптируется под цель (продуктовый дизайн / fundraising / стратегия / годовой обзор). User-invoked only — do NOT auto-trigger. Triggers on /pm-competitive, "конкурентный анализ", "разбор конкурентов", "five forces", "SWOT", "competitive analysis", "competitor comparison", "feature matrix vs competitors".

Классифицирует пользовательский фидбек (Excel/CSV/текст) по 6 категориям, делает sentiment-анализ, кластеризацию тем, анализ трендов, триангуляцию по источникам, расчёт NPS и извлечение персон. На выходе — Top-10 болей с рекомендациями к действию. User-invoked only — do NOT auto-trigger. Triggers on /pm-feedback, "анализ обратной связи", "разбор отзывов", "анализ NPS", "analyze user feedback", "VOC analysis", "NPS analysis", "review analysis".

Делает ревью продуктовых метрик — тренды, аномалии, root causes и рекомендации к действиям. Включает декомпозицию North Star (L1/L2), диагностику retention-кривых, анализ воронки, разбор A/B-экспериментов, проверку соответствия OKR и фреймворк атрибуции аномалий. User-invoked only — do NOT auto-trigger. Triggers on /pm-metrics, "обзор метрик", "разбор воронки", "анализ удержания", "ретеншн", "A/B результаты", "review metrics", "DAU analysis", "retention analysis", "funnel analysis", "metric anomaly".

Генерирует структурированный PRD (Product Requirements Document) с шаблонами под тип продукта (B2C / B2B / внутренний инструмент / платформа) — фон, цели, детальный дизайн фич, acceptance criteria в Given-When-Then, аналитика и 10-пунктовый чеклист качества. User-invoked only — do NOT auto-trigger. Triggers on /pm-prd, "сделай PRD", "напиши PRD", "продуктовые требования", "make a PRD", "write a PRD", "draft requirements doc".

Use when ranking a list of requirements, features, or backlog items using RICE / ICE / MoSCoW / Kano. Built-in decision tree picks the right framework based on data availability and decision context. Output is a transparent matrix, 2×2 Impact/Effort quadrant, and a Sprint allocation proposal. User-invoked only — do NOT auto-trigger. Triggers on "/pm-prioritize", "/prioritize", "приоритизация", "ранжируй бэклог", "RICE-анализ", "prioritize requirements", "RICE", "ICE", "MoSCoW", "Kano", "rank backlog".

Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате Now/Next/Later с атрибуцией задержек по 5 причинам, health score и фреймворком обрезки scope при нехватке ресурсов. User-invoked only — do NOT auto-trigger. Triggers on /pm-roadmap, "обнови roadmap", "статус спринта", "анализ задержек", "update roadmap", "sprint status", "milestone progress", "delay analysis".

Разбивает Epic или крупное требование на независимые User Stories с acceptance criteria в формате Given-When-Then, проверкой по INVEST и оценкой Story Points (Fibonacci или T-shirt). На выходе — Story Map с предложением по Sprint-планированию. User-invoked only — do NOT auto-trigger. Triggers on /pm-user-stories, "разбей на user stories", "разбить эпик", "story map", "AC", "acceptance criteria", "break down into user stories", "split this epic", "write user stories".

Use when auditing a product, business, or project ecosystem — analyzing data sources, decision loops, bottlenecks, and implementation contours. Triggers on "аудит продукта", "product audit", "data audit", "аудит данных", "аудит бизнеса", "проанализируй экосистему", "аудит систем".

Use when creating or rewriting README.md for projects. Triggers on "write README", "create README", "update README". Creates human-focused documentation with proper structure.

>-

Use when operating, debugging, deploying, or monitoring a Telegram bot or Telegram-to-agent gateway. Triggers on "telegram bot down", "bot not responding", "debug bot", "check webhook", "polling vs webhook", "restart bot", "deploy bot", "bot logs", "agent gateway", "Telegram Bot API error", "send test message", "бот не отвечает", "проверь бота", "логи бота", "перезапусти бота". Covers health checks, logs, webhook/polling diagnostics, environment validation, safe restart/deploy checklists, Bot API smoke tests, forum topic delivery, privacy mode, gateway routing, and incident notes.

Break a plan, spec, or PRD into independently-grabbable task files using tracer-bullet vertical slices.

Turn the current conversation into a PRD file in the project folder — no interview, just synthesis of what you've already discussed.

Use when the user is transitioning from a completed retro into a weekly plan, choosing weekly outcomes, scheduling a full ISO week, or asking for "план на неделю", "weekly planning", priorities, capacity, or outcomes.

Use when the user is closing an ISO week, reviewing planned outcomes against evidence, interviewing work Areas, resolving unfinished commitments, or asking for "ретро", "weekly retro", "week review", or lessons from the week.

Use when the user asks "что сегодня", "задачи на сегодня", "план на день", or wants the current department's living weekly plan refreshed from task facts.

Use when a completed department retro should become accepted outcomes and a full living ISO-week plan, or the user asks "планирование", "план недели", or "что делаем на следующей неделе".

Use when the user asks for "ретро", "обзор недели", or "что было за неделю" and the department needs a fact-based closeout plus its next Area goal.

>-

>-

Before building anything, justify the tool choice and complexity level. Could a shell script do this? Does it need Node.js? A full application? Prevents over-engineering by requiring explicit justification before choosing a heavier approach.

Before starting any research task, define what decision the research serves, what "done" looks like, and what is out of scope. Prevents research that answers the technically correct question but not the operationally relevant one.

Android/Termux constraints reference. Prevents Claude Code from suggesting commands that fail silently on Android (sudo, systemd, non-Termux paths, etc.).

Summarize document text and identify its main claims, evidence, and unanswered questions.

Publish short-form videos to TikTok, Instagram Reels, YouTube Shorts, X, and Facebook from AI agents through Taisly.

小红书 / 抖音 / 快手 / 视频号 自媒体「(compose 素材打底 →) 找对标 → 拆爆款 → 套自己」四命令闭环，另支持带货账号诊断、带货视频链接拆解和证据驱动的脚本生成（commerce）。给账号 / 平台视频链接 / 本地视频 / 商品详情、SKU 与资质材料，输出账号与对标差距、内容拆解、商品事实卡、口播和分镜。当用户说"找对标"、"拆这条爆款"、"对着这条仿写"、"下一条该写什么"、"我这个号缺爆款选题"、"帮我写一条对标 XX 的笔记"、"我有素材帮我写一条能爆的"、"这份文档/这组图/这段视频能出一条爆款吗"时调用。诊断模式（"为什么不爆"）走 references/diagnostic-mode.md。带货触发词：带货账号诊断、带货视频链接、带货素材、商品详情截图、SKU 表、商品资质、带货脚本、口播、分镜、商品卡一致性 — 走 commerce 路由。商品链接不等于视频链接；本 Skill 不解析在线商品页，不提供选品、趋势监控或 GMV/佣金推断。

>-

>-

>-

Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.

Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.

Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. Re-run any time to refresh both in place. Use when memory is newly installed on an existing project, or when the project has changed enough that the stored map is stale.

Configure and build gz-sim from source using either CMake/Ninja directly or a colcon workspace. Trigger when the user asks to build, recompile, configure, or set up the gz-sim binary tree.

Scaffold a new Nav 2 plugin (controller, planner, behavior, smoother, goal-checker, progress-checker, costmap layer, or BT node). Wires pluginlib registration, parameter declaration on the lifecycle node, and a minimal integration test. Trigger when the user asks to write or extend a Nav 2 plugin.

Author a new skill under .claude/skills/<name>/SKILL.md with valid frontmatter, following the template conventions, and index it in CLAUDE.md + README.md.

Scaffold a Behavior Tree leaf node — plain BehaviorTree.CPP (SyncActionNode / StatefulActionNode / ConditionNode) or a BehaviorTree.ROS2 wrapper (RosActionNode / RosServiceNode / RosTopicPubNode / RosTopicSubNode) — with ports, factory/plugin registration, and XML v4 usage. Trigger when the user asks to write a behavior-tree node (not Nav 2-specific).

Author a new asset for this .claude/ template — a rule, skill, slash command, or sub-agent — following the project's conventions and wiring it into the CLAUDE.md / README.md indexes. Trigger when the user wants to add or extend a command, skill, agent, or rule (make the template itself extensible).