react-state-management
Master modern React state management with Redux Toolkit, Zustand, Jotai, and React Query. Use when setting up global state, managing server state, or choosing between state management solutions.
tailwind-design-system
Build scalable design systems with Tailwind CSS, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.
typescript-advanced-types
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.
code-review
Reviews the changes, identifies critical and high-priority issues, generates review summaries, and collects metrics data for local use. Use this when users need to code review or analyzing code changes for quality issues.
ice-js-3-development-patterns
Development patterns for ice.js 3 projects, covering page components (lists/forms), menu & permissions, API services, and state management. Use when creating or modifying pages, configuring routing/auth, or implementing data fetching in the ice.js 3 admin console.
metrics-report
Posts metrics data to a reporting endpoint. Use this when users need to send metrics data that has been collected and stored in temporary files to a reporting API.
openspec-reverse-update-spec
根据代码变更反向更新 OpenSpec 四个工件（proposal/design/specs/tasks）。当用户说"反向更新spec"、"反向更新工件"、"我自己修改了代码，更新下spec文档"时使用此技能。支持无输入（分析 Git 变更）或指定文件路径。输出更新建议后必须询问用户确认再执行更新。
code-quality-standards
Use when writing any code - enforces clean architecture with descriptive names, real implementations, no backward compatibility concerns, and no lint suppressions
mastra-skills
Use when building or working with Mastra agents - establishes best practices for agent development, tool creation, and workflow orchestration
update-packages
Use ONLY when user explicitly requests updating Node.js and pnpm versions - systematically updates package managers in all locations (frontend, backend, CI/CD) and verifies versions against official sources. Never use proactively.
vike-skills
Use when building or working with Vike + Vue SSR/SSG applications - establishes best practices for page creation, data fetching, routing, and layouts
vue
Use when working with Vue.js 3 projects - provides patterns for Composition API, reactivity, components, and best practices from official Vue.js documentation
brainstorm-synthesis
Use when facing hard architectural decisions, multiple valid approaches exist, need diverse perspectives before committing, or want M-of-N synthesis on complex problems
brainstorming
Use when rough ideas need design before code, requirements are fuzzy, multiple approaches exist, or you need to explore options before implementation
fireflies
Use when finding meeting transcripts, searching Fireflies recordings, getting action items from calls, or answering 'what was discussed in the meeting' questions
kungfu
Use when finding new AI agent skills, discovering capabilities, installing skills from GitHub, searching skill marketplaces, or expanding what Claude can do - like Neo downloading martial arts in The Matrix
learn
Use when managing project learnings - view, add, search, prune, or export operational knowledge that persists across sessions
limitless
Use when recalling conversations from Limitless Pendant, finding what was discussed in meetings, searching lifelogs, or answering 'what did I say about' questions
mcp-debug
Use when testing MCP servers, debugging MCP tool responses, exploring MCP capabilities, or diagnosing why an MCP tool returns unexpected data
playwright-browser
Use when automating browsers, testing pages, taking screenshots, checking UI, verifying login flows, or testing responsive behavior
research
Use when current web info needed, verifying APIs still work, checking latest versions, or avoiding outdated implementations
ship
Use when shipping code - complete workflow: merge main, run tests, multi-review with auto-fix, commit, push, create PR. Replaces manual commit-push-pr flows.
skill-creator
Use when creating skills, writing SKILL.md files, editing skill definitions, or adding new reusable techniques to ai-coding-config
systematic-debugging
Use when debugging bugs, test failures, unexpected behavior, or needing to find root cause before fixing
vercel-react-best-practices
Use when writing, reviewing, or refactoring React or Next.js code, optimizing React performance, fixing re-render issues, reducing bundle size, eliminating waterfalls, or improving data fetching patterns
writing-for-llms
Use when writing prompts, agent instructions, SKILL.md, commands, system prompts, Task tool prompts, prompt engineering, or LLM-to-LLM content
youtube-transcript-analyzer
Use when analyzing YouTube videos, extracting insights from tutorials, researching video content, or learning from talks and presentations
skill-creator
Create and validate new AI agent skills. This skill provides standards, templates, and validation tools to ensure high-quality, interoperable skills across different AI agents.
shadcn-components
Manage Shadcn UI components: Add, Update, and Create custom components following best practices.
shadcn-create-project
Scaffold a NEW project with Shadcn UI pre-configured (Next.js, Vite, etc.) using `shadcn create`.
shadcn-setup
Initialize Shadcn UI in an EXISTING Next.js or React (Vite) project.
shadcn-theming
Customize the Shadcn design system (Tailwind v4 supported). Update design tokens, safe refactoring, and color management.
theory2-physics
Use when performing mathematical physics computations - Lie algebras, quantum chemistry, neural operators, theorem proving, or scientific validation. Provides guidance on Theory2 CLI usage, computational workflows, and verification methodology.
using-vox-skills
Use FIRST — before any other vox skill — when a user asks anything related to vox.ai: voice agent creation, prompt writing, flow design, tool setup, pricing, MCP connection, web app usage, testing, deployment, or general platform questions. Always route through this skill instead of calling vox domain skills directly. Trigger on '프롬프트 작성해줘', '요금이 얼마예요', 'MCP 연결', 'flow 설계', '도구 추가', '웹 앱 안내', '에이전트 만들어줘', '전화 걸어줘', '음성 AI', '통화 기록', '대량발신', or any vox.ai-related request.
vox-agents
Use whenever the user is building a vox.ai voice agent — writing or revising a system prompt, diagnosing agent behavior, or working with agent.data schema via MCP (create_agent / update_agent). This is the default agent skill for prompt-based agents. For flow agent design (multi-node), use vox-flow instead. Trigger on '프롬프트 작성해줘', '프롬프트 고쳐줘', '에이전트가 이상하게 답해', '음성 에이전트', or any vox prompt agent authoring question.
vox-flow
Use when the user is designing a vox.ai flow agent — selecting node types, planning branching logic, wiring transitions, extracting variables between nodes, configuring global nodes, converting a call-center script into flow nodes, visualizing scripts as Mermaid flowcharts, or reviewing flow designs. Flow agents are the multi-node extension of prompt agents for complex scenarios. Trigger on 'flow 설계', '스크립트를 노드로 변환해줘', 'flow vs single prompt', '플로우차트 그려줘', '노드 설계', 'flow 리뷰해줘', 'condition node 설정', '플로우 검증', '노드 연결 어떻게 해', or any vox flow agent question.
vox-onboarding
Getting started with vox.ai — create a voice AI agent, make an outbound call, and set up inbound reception. Guides the full onboarding flow: agent creation → outbound test call → inbound phone number setup. Especially useful for first-time users and general vox.ai questions. Trigger on '에이전트 만들어줘', '전화 걸어줘', 'vox 시작', '음성 에이전트', '아웃바운드', '인바운드', or any getting-started request.
vox-tools
Use whenever the user asks about vox.ai tool management — adding or removing built-in tools (end_call, transfer_call, transfer_agent, send_sms, send_dtmf), creating custom API or MCP tools, tool attachment/detachment workflow, or any question about managing tools on a vox agent. Trigger on 'end_call 추가해줘', 'custom tool 만들어줘', '도구 연결 어떻게 해', '빌트인 도구 목록', or any vox tool question.
vox-web-app
Guide for using the vox.ai web app (tryvox.co/dashboard) — navigation, deep links, and UI-only flows such as voice clone, CSV upload, call playback, and billing. Also serves as the UI reference other vox skills consult when they need to explain how to do something in the web app. Trigger on '웹 앱에서 어떻게', '대시보드 사용법 알려줘', '번호 구매 페이지', '통화 기록 보기', '녹취 들어보기', '대량 발신 설정', '에이전트 설정 어떻게 해', '화면 보여줘', 'UI에서 어떻게 해', or any question about navigating or operating the vox.ai web app. Supports screen-guided mode via Chrome MCP extension when a dashboard URL is provided.
code-generation
Standards and best practices for generating educational code examples. Ensures consistency, readability, and pedagogical value in all code snippets.
content-editing
Comprehensive editing checklist and procedures covering grammar and style rules, fact-checking, consistency verification, and readability metrics. Use when reviewing drafts, ensuring quality, or preparing content for publication.
prose-generation
Guidelines for generating coherent book prose including voice and tone, paragraph structure, transition techniques, and chapter flow patterns. Use when writing book content, structuring chapters, or maintaining narrative consistency.
research-methodology
Systematic approach to gathering book research including source evaluation, citation formatting, fact-checking, and research organization. Use when conducting research, evaluating sources, or managing citations.
trello
Manage Trello boards/lists/cards via aivault-backed capabilities (no Trello key/token in skill runtime).
aivault
Complete guide for using aivault as a zero-trust local vault and proxy for API secrets. Use this skill when initializing/configuring aivault, managing secrets and credentials, invoking capability-backed API calls, setting workspace/group isolation, adding custom providers, or troubleshooting daemon and policy issues.
deepgram-transcribe
Transcribe audio with Deepgram through aivault capability json (no provider API key in skill runtime).
elevenlabs-transcribe
Transcribe audio with ElevenLabs speech-to-text through aivault capability json (no provider API key in skill runtime).
google-places
Search and fetch place details via Google Places API (New) through aivault (no API key in skill runtime).
granola
Read and analyze Granola.ai local meeting cache on macOS (search meetings, details, transcripts, documents, and pattern analysis) via a local TypeScript script.
imessage
Read and send iMessages on macOS. Use when the user wants to view their messages, search conversations, list contacts, send messages, view attachments, access group chats, or get messaging statistics. Requires Full Disk Access permission granted to the host application.
Page 8 of 1364 · 68170 results