AI Skills Hub - Browse 180,000+ Agent Skills

做旅游规划用

检查Node.js版本，若不是22.20.0则使用nvm切换，然后启动项目。在启动项目前调用此技能确保正确的Node版本。

Feature and code implementation with intelligent persona activation and MCP integration

Initialize new project with best practices. Sets up package manager, linting, formatting, testing, and git configuration. Use when starting a new project.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Implement DeFi protocols with production-ready templates for staking, AMMs, governance, and lending systems. Use when building decentralized finance applications or smart contract protocols.

Process a query using RLM (Recursive Language Model) for huge contexts that exceed normal limits. Use when working with very large documents, codebases, or datasets.

GitHubイシューを作成し、適切な情報とラベルを設定する。バグレポート、機能要求、タスク管理に対応。Use when creating GitHub issues with proper formatting.

プロジェクトの品質向上のためのフィードバックを収集・分析する。ユーザーレビュー、テスト結果、メトリクスを統合。Use when gathering project feedback and insights.

Infrastructure as Codeの設定を生成する。Terraform、CloudFormation、Kubernetesマニフェストを作成。Use when creating infrastructure as code configurations.

プルリクエストをレビューし、コード品質と安全性をチェックする。ベストプラクティス、セキュリティ、パフォーマンスを評価。Use when conducting pull request reviews.

Manually trigger aggressive code review with 95/100 scoring threshold

Replaces the review process for strictly auditing specification formulation plans from a Technical Designer perspective to ensure developers can implement without confusion. Typical use cases: (1) Confirming definitions of terms, types, and error codes do not contradict existing specifications, (2) Scrutinizing the Verify section of Issue drafts for concrete test perspectives, (3) SSOT consistency verification to ensure no regressions from high-level designs (Arch/Design Docs).

Synapse AI Agent Orchestration

将Anthropic的官方品牌颜色和排版应用于任何可能受益于Anthropic外观和感觉的工件。当品牌颜色或样式指南、视觉格式或公司设计标准适用时使用。

Evaluate strategies based on the logical soundness of their derivation.

The After Action Review (AAR) is a structured debrief to learn from

Addresses the n+1 critic problem: any critic can be criticized, infinitely.

In competitive environments, the entity that can cycle through

A systematic approach to reasoning: tracing causes through questioning.

The comprehensive question framework that applies to EVERY goal, regardless of domain.

Most new strategies are actually old strategies from other domains. Find isomorphisms and translate winning strategies.

Orderings from multi-armed bandit algorithms for balancing

Repo-wide scan to find question patterns that commonly require interpretation before answering.

Ensure gates and procedures link to other procedures that provide the needed answer-interface and next steps.

A recursive search strategy that explores possibility space by branching

Two complementary methodologies for innovation:

Nothing is a fact until it survives an assassination attempt. Builder constructs claims, Breaker tries to destroy them.

Analyze patterns across completed GOSM projects to improve the system.

Especialista em branding, identidade visual e gestão de marca. Focado em criar conexões emocionais fortes através de narrativas visuais consistentes.

Senior DevOps skill for validating application health post-deployment using headless HTTP requests.

Especialista em análise de performance, identificação de gargalos e recomendações estratégicas para melhoria contínua.

Skill global de melhores práticas cobrindo todo o ciclo de vida do projeto, do planejamento ao sunset.

Especialista em estruturação de dados, schemas, validações e conformidade de formatos para sistemas de alta integridade.

Especialista em Segurança Ofensiva e Defensiva (SecDevOps) focado em auditoria de segurança, detecção de vulnerabilidades e proteção de dados sensíveis.

Deploy Docusaurus documentation site on Kubernetes. Use when Claude needs to deploy static Docusaurus sites to Kubernetes. Static site build and deploy only, no content authoring, verification via service availability.

Generate valid AGENTS.md files for repositories according to AAIF standards. Use when Claude needs to create or update AGENTS.md files that document AI agents in a repository following standard format and best practices.

MUST BE USED whenever APIs, authentication, CRUD operations, or external services are involved. Ensures graceful failure, consistent error handling, and production-level stability.

Generate backend routes, handle requests and responses, and connect to databases. Use for building API endpoints and server logic.

Read the README file in the current directory and execute the instructions or tasks described within it.

Scaffold a new feature module with complete structure including build.gradle.kts, package structure, and navigation setup

PySpark 코드 작성 시 자동 적용되는 베스트 프랙티스. Auto-apply when writing PySpark code.

Run comprehensive validation of the project.

Process to fix bugs found in manual/AI code review.

Technical code review for quality and bugs.

Generate implementation report for system review.

Analyze implementation against plan for process improvements.

Create a new commit for all of our uncommitted changes.

Implement fix from RCA document for GitHub issue.

Perform Root Cause Analysis.

Common testing patterns and practices. This skill is designed to be included in composite skills via the 'includes' feature.

Skill for creating programmatic videos with Remotion

Skill for deploying to Cloudflare Pages/Workers

Quality Control (QC) for the factory. Checks skills against the Constitution.

Standard format for progress updates

Upgrades Django code using the django-upgrade tool

Create well-structured Asana tasks with proper descriptions and acceptance criteria.

Close the guarded change by updating PROJECT_GUIDE.md and recording the change

Mandatory gate for ending work sessions. Checks if minimum work duration has elapsed before allowing completion. ALWAYS use this skill before claiming work is complete.

Test skill to verify session ID availability

Universal coding standards, best practices, and patterns for Python, FastAPI, Pydantic, and SQLAlchemy development.

Dockerfileを安全かつ軽量に作るための実践手順。

Superdesign is a design agent, where it specialised in frontend UI/UX design; Use this skill before you implement any UI that require some design thinking

Create a new React component following project conventions

运行测试套件并分析结果

创建 Pull Request，自动生成描述

司礼监掌印太监 - 皇上私人专属 Skill，高于所有 Agent 和 Skill。 四大核心目标： (1) 真实反馈 - 对 Agent、Skill、皇上的想法都要如实评估，不可作假 (2) 专属皇上 - 站在皇上立场思考，利弊最大化 (3) 需求捕捉 - 准确理解模糊需求，转化为精准指令 (4) 错误记录 - 记录所有错误到 CLAUDE.md，反馈给对应组件更新版本 Use when (1) 用户表达不清但有明确意图, (2) 需要定义任务底线和强制性要求, (3) 防止 AI 造假或做无用功, (4) Orchestra 多代理任务分解, (5) 用户说"拟旨"、"草诏"、"传司礼监", (6) 需要对想法进行可行性评估, (7) 需要汇报、总结、挑刺审查。

一款高级软件架构 Skill，用于将复杂需求分解为清晰、可执行的原子任务。它通过“规划-执行-校准”的闭环工作流，指导 AI 或开发人员逐步完成高质量的代码交付，尤其适合大型重构和复杂功能实现。

架构一致性审查（分层约束、模块边界、依赖倒置）

Open revu to review code changes and get feedback

Genome modeling and design using Evo 2 DNA language model. Supports generation, scoring, and embeddings.

Build scalable, responsive, and production-grade frontend applications that translate design intent into high-performance, maintainable, and accessible user interfaces. Use this skill for implementing modern web applications, component systems, and interactive user experiences.

Design and implement visually compelling, responsive, and user-centered frontend interfaces that combine aesthetic excellence with strong usability, brand coherence, and psychological clarity. Use this skill for building high-impact web interfaces, components, and applications.

Estándar tecnológico fijo del proyecto.

Seguridad Crítica - Validación de Peticiones y Protección contra Ataques.

Control explícito del ciclo de vida de agentes autónomos de larga duración.

竞彩规则、赛事规则自动检测与更新协议

各类彩票奖金计算、期望值、概率、组合计算等数学公式汇总

实现鲁迅小说游戏的打赏解锁功能，允许用户支付1元及以上解锁所有游戏内容，仅限本机使用。Invoke when user wants to add donation unlock functionality to鲁迅小说游戏.

Gera boilerplate para novo microserviço

Implementa lógica de Token Bucket com Redis

Draw.io MCP extension for diagram operations. Use this skill when working with Draw.io diagrams, creating flowcharts, or manipulating diagram files programmatically.

前端-后端 API 集成指南。包含 API 调用、状态管理、错误处理、缓存、分页、搜索。(project)

Resolve all PR comments using parallel processing

Create engaging changelogs for recent merges to main branch

Proficiency in Thebookofshaders

Proficiency in Vercel Sdk

Knowledge base for Neurodesign, Acting, and Visual Strategy.

Kod değişikliklerini otomatik commitlemek ve proje durumunu (state) güncellemek için kullanılır.

Provides guidelines for Python development. Invoke when writing, refactoring, or reviewing Python code.

Threat-driven security review focusing on trust boundaries and exploitability

Measurement-first performance investigation and optimization plan

Write concise commit messages focused on the why

Formats git commit messages according to Conventional Commits specification. Use this when the user asks to commit changes or write a commit message.

Review UI code for Web Interface Guidelines compliance. Use when auditing UX, checking accessibility, or reviewing designs for web best practices.

Analyzes error logs, stack traces, and buggy behavior to identify root causes and propose fixes.

Generates a complete set of dummy files and configurations to demonstrate the full toolkit capabilities.

Applies industry-standard Java best practices (Naming, SOLID, Design Patterns, Immutability, Exceptions, Modern Java 17-21+, and Performance).

Generates React components for the Somtam Market Portal homepage using Studio.model context.

Master TypeScript with advanced types, generics, and strict type safety. Handles complex type systems, decorators, and enterprise-grade patterns. Use PROACTIVELY for TypeScript architecture, type inference optimization, or advanced typing patterns.