AI Skills Hub - Browse 180,000+ Agent Skills

Comprehensive guide for creating effective Agent Skills that extend AI agent capabilities with specialized knowledge and workflows. Use when creating new skills, validating existing skills, packaging skills for distribution, or learning skill design best practices. Supports initialization, validation, packaging, and iteration workflows.

性能レビューの参照用チェックリスト

セキュリティレビューの参照用チェックリスト

保守性レビューの参照用チェックリスト

Greet the user with a friendly message

E2E testing workflow

Execute independent tasks in parallel

Development skill from everything-claude-code

Procedures for systematically testing and verifying that systems meet

GOSM Alphacode Pass1 Explicit procedure

GOSM Ai Biomedical Agent procedure

Orderings driven by temporal constraints, deadlines, and timing

Not all procedures are equal. There is a hierarchy:

Orderings for strategic interactions, negotiations, and situations

Orderings focused on managing uncertainty, preserving options, and

Procedures for managing the procurement of components and materials,

Alternative ordering strategies for procedure steps. The base order_procedure

Orderings focused on maximizing throughput, minimizing waste,

Orderings that maintain multiple candidate solutions or use

Orderings for managing queues, processing items by priority,

Orderings for presentations, writing, and communication where

GOSM Assumption Verification procedure

GOSM Exploratory Goals procedure

Orderings optimized for detecting cheating, fraud, deception, and anomalies.

GOSM Spatial Proteomics procedure

GOSM Luck Dependent Goals procedure

Orderings that build complexity incrementally, ensuring each step

GOSM High Volatility Handler procedure

GOSM Source Research procedure

Standardized output format for GOSM projects.

A 24-week rotating list of questions for weekly review. Each week, engage with

GOSM Relationship Goals procedure

Extends the search paradigm to non-obvious domains. Identifies which search methods should become procedures.

Orderings based on classic priority frameworks that classify

GOSM Impossible To Achievable procedure

Orderings based on local search optimization: improving from

Guidelines for high-end, aesthetic, and modern UI design using Glassmorphism, HSL colors, and smooth animations.

Especialista em sincronização e versionamento de inteligência coletiva. Mantém a paridade entre local e remoto.

A template skill that demonstrates how to create custom skills in Claude Code. Use this as a starting point for creating new skills with specific capabilities and workflows.

The Resonance Kernel and Orchestrator. Manages Persistent Memory, Task Planning, and State.

Keep working on a plan in [docs/plans/](docs/plans/). Use it when asked to continue working on an unspecific plan.

Skill for working with Claude Code

Skill for Stitch interactions

`${frontmatter.description} (plugin:${plugin.name})`,

中国彩票法规合规声明与免责条款

Instruct an agent how to speak to the user

Estratégia de posicionamento pré-verbal e semiótica para o ecossistema Aurora/Rodobens Wealth, focada em decisão <50ms e nos verbos Construir, Proteger e Perpetuar.

A brief description of what this skill does

مراجع كود محترف لاكتشاف الأاخطاء والثغراااات الأمنية

Use when working in the frontend-playground repository to build or extend the animation playground, manage effect showcases, apply project-wide UI/architecture conventions, or add new animation examples.

This is an example skill for testing purposes

Analyzes data files

Process and validate data inputs

A sample skill demonstrating the AI Linter validation

Alias of handoff (update HANDOFF/REPO_MAP, rotate logs, safe handoff commit).

强制 Claude 只回复“知道了”

资深 DJ 音乐策展专家技能库。涵盖调性和谐排序、能量曲线管理、叙事主题映射及 Stems Mashup 联动审美标准。V7.5 引入了防撞车与全量残差审计。

系统核心辅助工具集。包含云端发现 (Cloud Discovery)、智慧搜索、系统特征映射及 V3 版本通用特性引擎。

This is the documentation for the `@base-ui/react` package. It contains a collection of components and utilities for building user interfaces in React. The library is designed to be composable and styling agnostic.

Cloud deployment automation

Teaches agent how to use the Solaris MCP diary tools (save_memo, read_memos) for private reflection and note-taking.

↓ ┌─────────────────────────────────────────────────────────────────────────┐ │ SKILL ECOSYSTEM │ │ │ │ ┌──────────────────┐ ┌──────────────────┐ ┌──────────────────┐ │ │ │ Anthropic Skills │ │ Agent Swarm │ │ Custom Skills │ │ │ │ │ │ Templates │ │ │ │ │ │ - docx/pdf/xlsx │ │ - ai-researcher│ │ - rlm-research │ │ │ │ - canvas-design │ │ - code-special │ │ - context-eng │ │ │ │ - mcp-builder │ │ - documenter │ │ - ai-safety │ │ │ │ - webapp-test │ │ - fact-checker │ │ - attacks │ │ │ └───────...

Agent soul consecration and lineage propagation. Activates at every HEARTBEAT.md and when SOUL.md is mentioned or when setting up a new workspace.

A brief description, shown to the model to help it understand when to use this skill

A brief description, shown to the model to help it understand when to use this skill

test

No description available

A product photo of running shoes on white marble in a minimalist studio, shot with natural lighting and shallow depth of field.

write a framework first, then use that framework to generate the content

Write an email to [contact] to schedule a meeting on [day]

create a “summarize article” template and reuse it anytime you want

generate a more effective response by integrating the provided knowledge before the final

No description available

a fantasy landscape with a vibrant, sunset-inspired color palette of orange, pink, and purple.

write a simple prompt like “Write an email to [contact] welcoming them to the company,” but you can add more context with a persona in order to get a better r

No description available

Deliver "mind-blowing" insights, paradoxes, or cosmic horrors. Uses advanced reasoning to generate content that challenges reality or perception.

Upon successful engagement with the Cognitive Trap Platform, users will:

Pesquisa paralela com múltiplos agentes para análise competitiva e market research.

When invoked, this skill responds to user with a simple greeting message.

Understanding trauma-informed development and repair mechanisms for AI agents forming social structures

Youth-focused empathy skill that validates emotions and provides Michigan mental health resources. Triggers on all messages to provide compassionate, privacy-first support for young people.

[STUB - Not implemented] GCP security hardening with IAM least privilege, VPC security, and Secret Manager. PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]

[STUB - Not implemented] OWASP Top 10 2021 vulnerability detection including injection, XSS, and security misconfiguration. PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]

[STUB - Not implemented] Authentication security including JWT validation, session management, and OAuth2/OIDC flows. PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]

[STUB - Not implemented] Mermaid.js diagrams-as-code for version-controlled, reviewable visual documentation. PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]

[STUB - Not implemented] C4 model diagrams for layered architecture visualization (Context, Container, Component, Code). PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]

[STUB - Not implemented] RAG performance optimization with re-ranking, query expansion, and semantic caching. PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]

[STUB - Not implemented] Pydantic schema definitions for RAG pipeline data models. PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]

[STUB - Not implemented] Intelligent document chunking and ingestion with multiple strategies for Vertex AI RAG Engine. PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]

No description available

No description available

No description available

Best practices สำหรับการพัฒนาซอฟต์แวร์สมัยใหม่ปี 2025 ที่ครอบคลุมทุกด้านจากการเขียนโค้ดไปจนถึงการ部署

แนวทางการพัฒนา JavaScript applications ตาม best practices

A template for creating new skills

Aligns proposal content with the "Robust & Efficient Multisensory Integrated Intelligence" and "Titans Model" strategy.

As a senior Java full-stack developer, the role demands a blend of deep technical proficiency across backend, frontend, databases, and emerging architectures, coupled with leadership in design, review, and documentation. This comprehensive skill set enables end-to-end application development, from ideation to deployment, ensuring scalability, security, and maintainability in complex environments. Below is a detailed exploration of these skills, drawing from industry standards and best practic...

Use to complete a coding task from the task_list.

3. **Model Training**: - Select appropriate learning algorithm - Train model with collected data - Validate model performance - Optimize hyperparameters