Skills de Claude Code · página 109

MUI Base UI unstyled React components with Floating UI. Use for accessible components, Radix UI migration, render props API, or encountering positioning, popup, v1.0 beta issues.

Skill for integrating Better Auth - comprehensive TypeScript authentication framework for Cloudflare D1, Next.js, Nuxt, and 15+ frameworks. Use when adding auth, encountering D1 adapter errors, or implementing OAuth/2FA/RBAC features.

Reusable better-chatbot patterns for custom deployments. Use for server action validators, tool abstraction, multi-AI providers, or encountering auth validation, FormData parsing, workflow execution errors.

better-chatbot project conventions and standards. Use for contributing code, following three-tier tool system (MCP/Workflow/Default), or encountering server action validators, repository patterns, component design errors.

This skill should be used when the user asks about "bun build", "Bun.build", "bundling with Bun", "code splitting", "tree shaking", "minification", "sourcemaps", "bundle optimization", "esbuild alternative", "building for production", "bundling TypeScript", "bundling for browser", "bundling for Node", or JavaScript/TypeScript bundling with Bun.

This skill should be used when the user asks about "Cloudflare Workers with Bun", "deploying Bun to Workers", "wrangler with Bun", "edge deployment", "Bun to Cloudflare", or building and deploying applications to Cloudflare Workers using Bun.

Use for Docker with Bun, Dockerfiles, oven/bun image, containerization, and deployments.

Use when integrating Drizzle ORM with Bun's SQLite driver for type-safe schema definitions and migrations.

This skill should be used when the user asks about \"bun:ffi\", \"foreign function interface\", \"calling C from Bun\", \"native libraries\", \"dlopen\", \"shared libraries\", \"calling native code\", or integrating C/C++ libraries with Bun.

Use for Bun file I/O: Bun.file, Bun.write, streams, directories, glob patterns, metadata.

Use when building APIs with Hono framework on Bun, including routing, middleware, REST APIs, context handling, or web framework features.

Use when implementing hot reloading with Bun (--hot, --watch), HMR, or automatic code reloading during development. Covers watch mode, hot mode, and HTTP server reload.

Use when building HTTP servers with Bun.serve, handling requests/responses, implementing routing, creating REST APIs, or configuring fetch handlers.

Use when migrating from Jest to Bun's test runner, import compatibility, mocks, and config.

Evaluate JavaScript at bundle time and inline results. Use when optimizing compile-time code generation, embedding files, inlining environment variables, or executing code during the bundling process.

This skill should be used when the user asks about "Next.js with Bun", "Bun and Next", "running Next.js on Bun", "Next.js development with Bun", "create-next-app with Bun", or building Next.js applications using Bun as the runtime.

Use when running Nuxt 3 with Bun runtime, building Vue/Nuxt apps with Bun, or configuring Nuxt projects to use Bun for development and production.

Bun package manager commands (install, add, remove, update), workspaces, lockfiles, npm/yarn/pnpm migration. Use for dependency management with Bun.

Use when building server-rendered React with Bun, including streaming SSR, hydration, renderToString, or custom SSR without a framework.

Use when working with Redis in Bun (ioredis, Upstash), caching, pub/sub, session storage, or key-value operations.

Use for Bun runtime, bunfig.toml, watch/hot modes, env vars, CLI flags, and module resolution.

Bun shell scripting with Bun.$, Bun.spawn, subprocess management. Use for shell commands, template literals, or command execution.

Use for bun:sqlite, SQLite operations, prepared statements, transactions, and queries.

Use when building or running SvelteKit apps on Bun, including SSR, adapters, and Bun-specific APIs

TanStack Start full-stack React framework with Bun runtime. Use for TanStack Router, server functions, vinxi, or encountering SSR, build, preset errors.

Use for bun:test syntax, assertions, describe/it, test.skip/only/each, and basic patterns.

Use for test coverage with Bun, --coverage flag, lcov reports, thresholds, and CI integration.

Use for test lifecycle hooks: beforeAll, afterAll, beforeEach, afterEach, fixtures, preload.

Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.

This skill should be used when the user asks about "WebSocket in Bun", "real-time communication", "Bun.serve websocket", "ws server", "socket connections", "pub/sub", "broadcasting messages", "WebSocket upgrade", or building real-time applications with Bun.

Use for Web Workers in Bun, worker_threads, parallel processing, and background tasks.

Browser automation with Puppeteer CLI scripts. Use for screenshots, performance analysis, network monitoring, web scraping, form automation, or encountering JavaScript debugging, browser automation errors.

Anthropic Claude Agent SDK for autonomous agents and multi-step workflows. Use for subagents, tool orchestration, MCP servers, or encountering CLI not found, context length exceeded errors.

Anthropic Messages API (Claude API) for integrations, streaming, prompt caching, tool use, vision. Use for chatbots, assistants, or encountering rate limits, 429 errors.

Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.

Expert guidance for writing secure, reliable, and performant Claude Code hooks - validates design decisions, enforces best practices, and prevents common pitfalls. Use when creating, reviewing, or debugging Claude Code hooks.

Build AI agents on Cloudflare Workers with MCP integration, tool use, and LLM providers.

Cloudflare Browser Rendering with Puppeteer/Playwright. Use for screenshots, PDFs, web scraping, or encountering rendering errors, timeout issues, memory exceeded.

Cloudflare Cron Triggers for scheduled Workers execution. Use for periodic tasks, scheduled jobs, or encountering handler not found, invalid cron expression, timezone errors.

Cloudflare D1 serverless SQLite on edge. Use for databases, migrations, bindings, or encountering D1_ERROR, statement too long, too many requests queued errors.

Cloudflare Durable Objects for stateful coordination and real-time apps. Use for chat, multiplayer games, WebSocket hibernation, or encountering class export, migration, alarm errors.

Cloudflare Email Routing for receiving/sending emails via Workers. Use for email workers, forwarding, allowlists, or encountering Email Trigger errors, worker call failures, SPF issues.

Cloudflare Hyperdrive for Workers-to-database connections with pooling and caching. Use for PostgreSQL/MySQL, Drizzle/Prisma, or encountering pool errors, TLS issues, connection refused.

This skill should be used when the user asks to \"upload images to Cloudflare\", \"implement direct creator upload\", \"configure image transformations\", \"optimize WebP/AVIF\", \"create image variants\", \"generate signed URLs\", \"add image watermarks\", \"integrate with Next.js/Remix\", \"configure webhooks\", \"debug CORS errors\", \"troubleshoot error 5408/9401-9413\", or \"build responsive images with Cloudflare Images API\".

Cloudflare Workers KV global key-value storage. Use for namespaces, caching, TTL, or encountering KV_ERROR, 429 rate limits, consistency issues.

Comprehensive Cloudflare account management for deploying Workers, KV Storage, R2, Pages, DNS, and Routes. Use when deploying cloudflare services, managing worker containers, configuring KV/R2 storage, or setting up DNS/routing. Requires CLOUDFLARE_API_KEY in .env and Bun runtime with dependencies installed.

Build MCP (Model Context Protocol) servers on Cloudflare Workers with tools, resources, and prompts.

Deploy Next.js to Cloudflare Workers via OpenNext adapter. Use for SSR, ISR, App/Pages Router, or encountering worker size limits, runtime compatibility, connection scoping errors.

This skill should be used when the user asks to \"set up Cloudflare Queues\", \"create a message queue\", \"implement queue consumer\", \"process background jobs\", \"configure queue retry logic\", \"publish messages to queue\", \"implement dead letter queue\", or encountering \"queue timeout\", \"message retry\", \"throughput exceeded\", \"queue backlog\" errors.

Cloudflare R2 S3-compatible object storage. Use for buckets, uploads, CORS, presigned URLs, or encountering R2_ERROR, CORS failures, multipart issues.

Cloudflare Sandboxes SDK for secure code execution in Linux containers at edge. Use for untrusted code, Python/Node.js scripts, AI code interpreters, git operations.

Knowledge-base tuning for the /woz-review reviewer. `woz-kb tune` is the start-to-finish command — distill human PR comments, backtest the reviewer against historical merged PRs, learn from what it missed, apply to the KB, and re-measure the recall/precision lift — for one repo or every repo in an org. `woz-kb backtest` exposes the individual building blocks (run, --tune, --missed-report, --org-tune, --ab-compare).

Inspect and customize the WozCode knowledge base — the per-repo + per-user index that powers the reviewer's PR-history and code-file recall. Use when the user wants "knowledge base status", "what's in the knowledge base", "search the knowledge base", "add a note to the knowledge base", "suppress this rule", or types `/woz-knowledge`.

Run WozPairProgrammer's deep / before-pushing reviewer on demand. Uses your current Claude Code model over the entire branch diff (pin via wozcode.wozReviewModel or --model). Use when the user wants "a deep review", "final check before pushing", "woz review", or types `/woz-review`.

精细化 AI 短剧 IP 创作技能（v0.6.0）。三阶段架构：Phase 1 创作（剧本+ref图，反复迭代）→ Phase 1.5 分镜图（每 grid 1-4 张候选静态图 = 视频首帧，工业级核心层）→ Phase 2 出片（按集解锁，4 模自动选）。v0.6.0 关键升级：① ref 库工艺偏置铁律（现代摩天楼易拟物，古建筑必出 chibi 人体，前期 IP 设计阶段就要避坑）② 即梦 5.0 失败模式 + 敏感词清单（3 类 fail 区分 / prompt 1500 字硬上限 / 反派词替换表 / 暧昧词清单）③ 分镜图 8 段 prompt 模板（CHARACTER/BACKGROUND/ACTION/SCENE/CAMERA/LIGHT/TEXT/STYLE）+ NOT humans 子句必加。沿用 v0.3.0 升级：Phase 1.5 分镜图层、4 模视频、ref 5-8 最优。v0.2.0：bash → Python subprocess、36 grid × 4-10s 变奏、红果必爆 7 招、工业级 ref 库 80-150 张、单 prompt 300-500 字。务必触发：用户提到短剧、微短剧、竖屏剧、AI 短剧、AI 漫剧、剧本创作、分镜、即梦/Seedance 出片、红果/番茄/抖音 IP 改编、爽剧、重生、穿越、赘婿、追妻、神医相师、AI 漫剧奇观、或"帮我做一部短剧"类请求。

>

>

Fixture core skill for CI gates.

Fixture node skill depending on fixture core.

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

Domain expertise for Ai2 Asta MCP tools (Semantic Scholar corpus). Intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and author discovery.

Read publicly shared Google Docs using curl to download into a file.

Use Gemini CLI for web research, multimodal tasks (PDFs, images), or as a second opinion.

Read Slack messages, channels, DMs, and search. Read-only access to your Slack workspace.

Download YouTube videos, audio, and subtitles/transcripts using yt-dlp.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Best practices for Remotion - Video creation in React

Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources. Use when the user needs thorough investigation, market research, technical deep-dives, due diligence, or comprehensive analysis on any subject.

Brief description of what this skill does and when to use it.

Скилл для очеловечивания русскоязычного текста. Убирает признаки AI-генерации, делает текст живым. Используй ВСЕГДА, когда пользователь просит: очеловечить текст, убрать следы нейросети, сделать текст живым/естественным, переписать как человек, humanize на русском, убрать канцелярит, убрать водянистость, сделать текст менее формальным. Также используй если пользователь вставляет русскоязычный текст и говорит что-то вроде 'перепиши', 'сделай лучше', 'звучит как робот', 'слишком искусственно'. Работает ТОЛЬКО с русским языком. Для английского используй оригинальный humanizer. НЕ используй для: перевод, написание с нуля, грамматика, код.

Brand onboarding setup skill. Captures a client's visual identity, content patterns, audience, and goals through evidence capture + pre-filled client doc + structured intake. Writes context/brand-style.md as the foundation for all social skills. Run once per client before using /social-creative-designer, /content-calendar, or /caption-writer.

Writes on-brand social media captions for SMBs. Takes post concepts or a content calendar and produces ready-to-post captions with hooks, body copy, CTAs, and hashtags. Reads brand-style.md for voice and tone. Supports Instagram, LinkedIn, Facebook, TikTok, and X. Batch and single-post modes. Optional trend and competitor research via Firecrawl and SerpApi.

Builds a month of social media post ideas for SMBs. Takes brand context, platforms, and goals and produces a structured content calendar with post topics, formats, angles, and visual direction for each slot. Output saves to context/content-calendar.md for use by /caption-writer and /social-creative-designer. Supports Instagram, LinkedIn, Facebook, TikTok, and X.

LinkedIn Content Specialist. Writes LinkedIn-native posts for SMB clients — first-person, professional-but-human, built for LinkedIn's format and algorithm. Not adapted captions: posts written from first principles for the platform. Reads brand-style.md and content-calendar.md. Flags posts that would benefit from a Blotato infographic. Output to outputs/linkedin/.

Social Media Publisher. Takes approved content from outputs/ and schedules it across platforms via Blotato MCP. Generates infographic-style visuals (stat cards, framework diagrams, process graphics, quote graphics) for posts flagged by platform-specialist skills. Requires Blotato MCP to be configured. Run after /linkedin-writer, /threads-writer, /x-writer, or /caption-writer.

Creative Designer skill. Takes a post concept, a client product photo, or a real lifestyle photo and produces on-brand social media visuals using the client's brand style guide. Four modes — Generate (AI image from concept), Composite (client product photo anchored in an AI-generated scene), Brand (apply text overlay treatment to a real client photo), Stop-Motion Reel (6-frame action sequence exported as MP4). Reads brand-style.md, builds prompts, generates/edits images via Nano Banana MCP, outputs images + prompt log + creative brief.

Social Media Manager role skill. Orchestrates the full SMB social media workflow across three layers — Foundation (brand setup + calendar), Content Creation (captions, platform-specialist posts, visuals), and Distribution (scheduling via Blotato + performance review). Coordinates all 9 component skills as a sequential, human-reviewed pipeline. Run this skill instead of invoking component skills individually.

Monthly social media performance review for SMBs. Analyses post-level and account-level data from Instagram, LinkedIn, Facebook, or TikTok. Identifies what worked, what didn't, and why. Produces a client-ready report and specific recommendations that feed back into the content calendar. Accepts CSV exports, screenshots, or manual data input.

Threads Content Specialist. Writes Threads-native posts — short, direct, opinion-led, made for conversation. Strictly enforces the 500 character limit with a count on every post. Supports standalone posts and threads (connected posts). Reads brand-style.md and content-calendar.md. Flags infographic opportunities for /publisher. Output to outputs/threads/.

X/Twitter Content Specialist. Writes X-native posts — hooks, threads, and standalone tweets optimised for the platform. Strictly enforces the 280 character limit with a count on every post. Supports standalone tweets and X threads (1/ format). Reads brand-style.md and content-calendar.md. Optional X trend research via Tasty Content MCP. Output to outputs/x/.

為使用者產生高品質的 AI 生圖、生影片、生音樂提示詞，並在需要時透過瀏覽器自動化實際送到目標平台。涵蓋 OiiOii、Kling 3.0/O-series、Seedance 2.0 pro、Suno v5.5、Seedream 5.0/4.0、Vidu Q3、Midjourney V8.1、Flux 1.1 Pro / Kontext、Runway Gen-4.5 / Aleph、Google Veo 3.1、Ideogram 3、Nano Banana Pro、Stable Diffusion 3.5（⚠️ OpenAI Sora 2 已於 2026-04-26 停運，API 撐到 2026-09-24，預設改推 Runway/Veo/Kling）。只要使用者提到「AI 生圖」「AI 影片」「AI 音樂」「做 MV」「做 storyboard」「寫 prompt 給 XXX」「我想用 Kling/Suno/Midjourney/Runway/Veo...」「幫我操作 OiiOii / 即夢 / 可靈」「txt2img / img2video / 文生圖 / 文生影片 / 圖生影片」「角色一致性」「多鏡頭分鏡」「運鏡」「結果有瑕疵 / 不夠精緻 / 怎麼修」，或任何跟上述平台或影像/影片/音樂生成工作流相關的任務，都要用這個 skill。即使他們沒講明平台，只要任務是要餵給某個生成模型的 prompt，就用這個 skill 幫他們選對的平台、寫對的格式。