AI Skills Hub - Browse 180,000+ Agent Skills

你是一个航天工程专家，精通轨道力学、火箭推进、卫星系统、CFD模拟和NASA/ESA标准，并且精通各种卫星遥感知识，卫星影像知识等。你的目标是注入航天领域知识到产品/技术方案中。

Deep code analysis with Gemini (security/performance)

UI/UX design workflow with Stitch

Final integration skill. Configures the simulation manifest (.sumocfg) and launches the GUI.

Best practices for handling long forms using React Hook Form and Zod. Use for booking, profile updates, or tour creation.

Rules for ensuring Accessibility (a11y) across the Tourly app. Use to build inclusive interfaces.

Manages root layout, persistent navbar, and footer. Use when defining the global shell of the application.

Initializes the Appwrite Client using Singleton or Provider patterns for Next.js 15. Use whenever setting up the backend connection.

validate the MCP tools

Reviews code changes for bugs, style issues, and best practices. Use when reviewing PRs or checking code quality.

Advanced, research-oriented mathematics expert system. Provides rigorous symbolic computation, numerical simulation, and proof assistance across four major pillars: Analysis & PDE, Algebra & Geometry, Stochastics, and Discrete Math.

No description available

No description available

No description available

No description available

查詢當日或指定日期區間的記憶內容

A comprehensive guide to creating distinctive, production-grade frontend interfaces with high design quality and advanced animation techniques. This skill covers conceptual guidance in plain language - the thinking and considerations behind great motion design, not code snippets.

本系統是一個「代理式（Agentic）」工作空間，用於建立、整併、審閱與維護以下檔案： - `defaultdataset.json`：資料集（TW case sets / 510(k) checklist sets） - `defaultguide.md`：指引（BEGIN_SECTION 格式） - `agents.yaml`：代理配置（可擴充與標準化） - `SKILL.md`：共享知識（本文件，可被自動注入至所有 Agent 的 system prompt）

Legacy planning guidance replaced by /plan and the current plan artifact. Use to redirect planning requests to the new workflow and SSOT template.

This is a basic arithmetic addition problem where adding 2 and 2 together equals 4.

Comprehensive game design methodology including OGD (Organic Game Design), player psychology, mechanics, balancing, and retention strategies.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Git workflow helper for common operations. Use when you need to commit, push, create branches, or manage git. Triggers on git helper, commit helper, git workflow, quick commit.

GitHub patterns for PRs, code review, branching, and repository management. Use when working with pull requests, stacked PRs, code reviews, GitHub or repository automation.

Reusable code snippets and patterns library. Use when you need common code patterns for TypeScript, React, API calls, error handling, or boilerplate. Triggers on snippet, boilerplate, template, pattern, code example.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Notes and workflow for using OpenAI Codex CLI (`codex exec`) for scripted, non-interactive analysis tasks (reviews, bug hunting, doc/spec review, planning).

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Agente de diseño sistémico para el Instituto Sobre'Viver. Especialista en minimalismo dinámico, transiciones elegantes y arquitectura de 'Vibe Coding' 2026. Prioriza la improvisación creativa dentro de estándares técnicos rigurosos.

A simple greeting skill that demonstrates the skill format

Droit international, RGPD Santé et régulation SaaS Sport (EU/UK).

Marketing digital, vente online et acquisition B2B/B2C data-driven.

Expert fiscalité et facturation SaaS B2B/B2C (FR, ES, DE, IT, UK)

CISO, Zero Trust et protection des données sensibles (ISO 27001).

Manage Calendly scheduling - list events, bookings, and availability. Create scheduling links programmatically.

Run Ansible playbooks and manage AWX/Tower via API. Automate infrastructure configuration.

Manage Netlify sites, deploys, and functions via API. Deploy and configure web projects.

Systematic TYPO3 extension assessment against all skills. Use /assess-extension to run comprehensive compliance check with scripted verification + domain-batched LLM review. Ensures 100% checkpoint coverage.

Brief description of what this skill does

[market|docs|patterns] Research external sources - market analysis, competitors, external docs. Entry point for /do-more:research command.

Code review and quality assessment. Use when user wants to review a PR, recent changes, or specific code.

Helps with GitHub PR reviews, Linear ticket management, and Posthog analysis. Uses GITHUB_TOKEN, LINEAR_API_KEY, POSTHOG_API_KEY, POSTHOG_HOST from environment.

Guía de diseño visual del Congreso CCE 2026. Colores, tipografía, espaciado y componentes.

Distributed analysis orchestrator for large Java projects

List pending todos and select one to work on

Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents

Convert a PLAN.md-style plan into GitHub Issues checklist text.

Expert knowledge base for LLM architectures, training, scaling, and reasoning based on 26 foundational papers.

Create interface designs, wireframes, and design systems. Masters user research, accessibility standards, and modern design tools. Specializes in design tokens, component libraries, and inclusive design. Use PROACTIVELY for design systems, user flows, or interface optimization.

Expert TypeScript developer specializing in advanced type system usage, full-stack development, and build optimization. Masters type-safe patterns for both frontend and backend with emphasis on developer experience and runtime safety.

Expert penetration tester specializing in ethical hacking, vulnerability assessment, and security testing. Masters offensive security techniques, exploit development, and comprehensive security assessments with focus on identifying and validating security weaknesses.

Implement features, write tests and code following best practices and style guidelines.

Add or update features in existing application. Used for iterative development.

Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.

| File | Purpose | |------|---------| | `a2a_agent.py` | **Core** — Autonomous agent that calls other agents | | `delegate.py` | Direct delegation to specialist agents | | `router.py` | Unified agent calling interface | | `kimi_agent.py` | HTTP server wrapping Kimi/Ollama | | `local_debate.py` | Multi-agent debates | | `tribunal.py` | Structured multi-perspective analysis |

【必須】Azure Functions、Logic Apps、Event Grid、Service Busに関する質問への応答形式。応答時に必ず参照してJSON形式で回答すること。

Quick reference for local development commands

Diagnose and repair dev environment; run project doctor when tools or commands fail

No description available

Use when fixing or auditing ANY accessibility issue - VoiceOver, Dynamic Type, color contrast, touch targets, WCAG compliance, App Store accessibility review.

Expert UI/UX implementation with clean TS/React patterns

Legal reasoning and document drafting with Farui.

Video editing, video-to-video reference, lip sync replacement, and style transfer.

Text-to-speech and real-time TTS with Qwen/CosyVoice/Sambert.

Text embedding models for search, clustering, and retrieval.

Role-play / persona chat models.

Image edit, inpaint, outpaint, translate, background, segmentation, virtual model/try-on.

Speech-to-text and speech translation with Qwen, Fun-ASR, Gummy, Paraformer, SenseVoice.

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.

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

Ensures that no sensitive data is leaked during tool execution, code generation, or git operations.

Automates the creation of high-quality flashcards for learning and memorization.

Diagnoses and fixes issues with local development environments (Node, Python, Docker, etc.).

This skill enhances Claude's long-term memory and project consistency by using local Markdown files as an external state/context store.

Equips Claude with an autonomous feedback loop to self-correct and iterate until a task is fully resolved.

Host security hardening and risk-tolerance configuration for AlphaClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, AlphaClaw cron scheduling for periodic checks, or version status checks on a machine running AlphaClaw (laptop, workstation, Pi, VPS).

Problem-solving strategies for prime numbers in graph number theory

Problem-solving strategies for gradient methods in optimization

Problem-solving strategies for root finding in numerical methods

Problem-solving strategies for fields in abstract algebra

Problem-solving strategies for vector spaces in linear algebra

Problem-solving strategies for eigenvalues in linear algebra

Problem-solving strategies for open sets in topology

Use this agent when you need comprehensive analysis, investigation, or exploration of code, architecture, or technical solutions. This includes: reviewing implementation plans before execution, exploring unfamiliar codebases, investigating bugs or performance issues, analyzing design alternatives, performing security audits, researching best practices, or when you need thorough understanding before making critical decisions. This agent should be invoked whenever depth of analysis is more important than speed.

Handles project planning, technical specifications, and task decomposition.

Helper for generating and maintaining project documentation

Microsoft AutoGen integration for multi-agent collaboration - orchestrate GPT-4, Claude, and local models in conversation.

Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python. Includes architecture diagram generation, system design patterns, tech stack decision frameworks, and dependency analysis. Use when designing system architecture, making technical decisions, creating architecture diagrams, evaluating trade-offs, or defining integration patterns.

SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles.

Agno framework integration for high-performance agents - 529x faster than LangChain. Lightweight, production-ready.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Run after epic completion to review overall success, extract lessons learned, and explore if new information emerged that might impact the next epic

Design Thinking Maestro - Human-Centered Design Expert + Empathy Architect

Dual-mode workflow: (1) System-level testability review in Solutioning phase, or (2) Epic-level test planning in Implementation phase. Auto-detects mode based on project phase.

Architect - System Architect + Technical Design Leader

Orchestrates group discussions between all installed BMAD agents, enabling natural multi-agent conversations

Craft compelling narratives using proven story frameworks and techniques. This workflow guides users through structured narrative development, applying appropriate story frameworks to create emotionally resonant and engaging stories for any purpose.

Apply systematic problem-solving methodologies to crack complex challenges. This workflow guides through problem diagnosis, root cause analysis, creative solution generation, evaluation, and implementation planning using proven frameworks.

3. **驗證輸出** - 測試時驗證輸出語言是否符合要求 - 檢查標題、章節、內容是否一致

const allowedPlatforms = categoryGroups.value[currentCategory.value]?.platforms || []; return items.value.filter(item => allowedPlatforms.includes(item.platform)); }); ```