Explore AI Agent Skills & Claude Prompts
Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.
Enter through keywords, occupations, creators, and GitHub sources to see what kinds of skills are emerging across domains.
Use the same catalog through the API
Connect 381,784 public skills to your own search, analytics, or agent workflow with the REST API.
Querying local SQLite index...
ember
by j4flmaoUse this skill when the user says 'Ember.js', 'Ember app', 'Ember setup', 'Ember CLI', 'Ember Data', 'Ember Octane', 'Ember component', 'Ember route', 'Ember service', or when building ambitious web applications with Ember.js. This skill enforces: convention over configuration, Ember CLI for code generation, Ember Data for state management, Octane patterns (glimmer components, tracked properties, native classes). Requires package.json with ember-source or ember-cli. Do NOT use for: React/Vue/Angular projects, vanilla JS, or non-Ember projects.
backend-caching
by j4flmaoUse this skill when the user says 'cache', 'Redis', 'Memcached', 'CDN', 'cache-aside', 'read-through', 'write-through', 'write-behind', 'cache invalidation', 'TTL', 'cache stampede', 'thundering herd', 'cache warming', 'LRU', 'LFU', 'cache hit ratio', 'cache strategy', or when designing a caching layer. This skill enforces consistent caching strategies: layer selection, read/write patterns, invalidation, stampede prevention, and monitoring. Applies to any backend stack. Do NOT use for: message queue design, database schema design, or frontend state caching.
data-schema-registry
by j4flmaoUse this skill when asked about Schema Registry, Avro, Protobuf, schema evolution, compatibility, Confluent Schema Registry, Apicurio, serialization, deserialization, or schema validation. This skill enforces: Schema Registry architecture and deployment, Avro/Protobuf/JSON Schema definition, compatibility modes (BACKWARD, FORWARD, FULL, NONE), schema evolution best practices, SerDe (serialization/deserialization) patterns, and CI/CD integration for schema governance. Do NOT use for: data contract enforcement, data catalog management, or database schema design.
blockchain-ethereum
by j4flmaoUse this skill when asked about Ethereum internals, EVM deep dive, Ethereum consensus layer, execution clients, staking, EIPs, layer-2 scaling, account abstraction, PBS/MEV-Boost, EVM opcodes, and Ethereum protocol development. Languages: Go, Rust, C#, C++, Solidity. Covers EVM architecture (opcodes, gas metering, memory/storage model, EOF), execution clients (geth, reth, Nethermind, Erigon), consensus layer (Casper FFG, LMD-GHOST, beacon chain, attestation), staking and validators (32 ETH, withdrawal credentials, MEV-Boost, DVT, ePBS), account abstraction (ERC-4337, EntryPoint, paymasters, UserOp mempool), critical EIPs (1559, 4844, 4337, 3529, 2718), and L2 scaling (Optimism, Arbitrum, ZKsync, StarkNet, validium, data availability). Do NOT use for: Bitcoin protocol (use blockchain-bitcoin), non-EVM blockchains (use blockchain-core), or smart contract development (use blockchain-application).
blockchain-cryptography
by j4flmaoUse this skill when asked about cryptographic primitives in blockchain, elliptic curve cryptography, hash functions, Merkle trees, digital signatures, zero-knowledge proofs, key derivation, BIP standards, and blockchain-specific crypto implementations. Languages: C++, Rust, Go, Python. Covers secp256k1, BN254, BLS12-381, Ed25519, SHA-256, Keccak-256, BLAKE2, Poseidon, Merkle trees (binary, Patricia, sparse, Verkle), ECDSA, Schnorr, BLS, threshold signatures (FROST, GG20), zk-SNARKs/STARKs/Bulletproofs, HD wallets (BIP-32/39/44), PSBT (BIP-174), and signature aggregation. Do NOT use for: general blockchain protocols (use blockchain-core), smart contract development (use blockchain-application), or standard web security cryptography outside blockchain.
mobile-ar-vr
by j4flmaoUse this skill when the user says 'AR', 'VR', 'augmented reality', 'virtual reality', 'ARKit', 'ARCore', 'Unity AR', '3D rendering', 'SceneView', 'AR scene', 'AR interaction', 'AR performance'. This skill enforces: platform-specific AR configuration (ARKit vs ARCore), scene setup with anchor management, optimal 3D model handling with LODs and compression, interaction patterns for gesture and placement, performance budgets (<60fps, <200MB), and VR integration considerations. Do NOT use for: general mobile UI/UX design, game engine tutorials unrelated to AR/VR, or 3D modeling software usage instructions.
ai-cost-optimization
by j4flmaoUse this skill when reducing AI inference costs: token optimization, prompt compression, caching for LLM, semantic cache, KV cache, quantization, model routing, cost optimization, batching, token counting, context window management, model distillation, budget governance, chargeback, cost monitoring, FinOps for AI. This skill enforces: token budget tracking, cache strategy with hit ratio targets, quantization selection, model routing rules, batching configuration, cost monitoring setup, budget enforcement with fallback, cost allocation per team/user. Do NOT use for: model training cost optimization (see ai-training), infrastructure/GPU cost optimization (see devops-finops), embedding storage cost at scale (see ai-embeddings).
frontend-remix-architecture
by j4flmaoUse this skill when the user says 'Remix', 'Remix architecture', 'Remix routing', 'Remix loader', 'Remix action', 'Remix form', 'Remix server', 'Remix session', 'Remix deployment', 'Remix Vite'. This skill enforces: file-based colocation, nested routes with Outlet, layout routes for shared UI, loaders for data, actions for mutations, session storage strategies, and deployment per runtime. Requires Remix + Vite (package.json with @remix-run/*). Do NOT use for: Next.js, TanStack Router, or React Router alone.
frontend-remix-patterns
by j4flmaoUse this skill when the user says 'Remix pattern', 'Remix form validation', 'Remix optimistic UI', 'Remix error boundary', 'Remix SEO', 'Remix caching', 'Remix PWA'. This skill enforces: server-side form validation with Zod, route-level error boundaries, meta exports for SEO, Cache-Control strategies, optimistic updates with useFetcher, and service workers for offline support. Requires existing Remix project (package.json with @remix-run/*). Do NOT use for: React-only validation, client-side-only forms.
circleci
by j4flmaoUse this skill when the user says 'CircleCI', 'circleci config', 'orb', 'workflows', 'jobs', 'steps', 'executors', 'Docker executor', 'machine executor', 'CircleCI runner', 'pipeline', 'context', 'store_artifacts', 'save_cache', 'restore_cache', 'parallelism', 'circleci local', 'SSH debug'. Covers: CircleCI configuration (config.yml), executors, jobs, workflows, caching, orbs, matrix builds, contexts, parallel execution, self-hosted runners, pipeline parameters, triggers, artifacts, test splitting, SSH debug. Do NOT use for: GitHub Actions, GitLab CI, Jenkins, or other CI systems.
helm-patterns
by j4flmaoUse this skill when the user says 'helm', 'helm chart', 'helm template', 'helm install', 'helm upgrade', 'helm rollback', 'helmfile', 'helm secrets', 'helm values', 'helm dependency', 'helm repository', 'helm plugin', 'helm unittest', 'helm lint', 'helm package', 'helm registry', 'oci helm', 'helm hooks', 'helm tests', 'helm subchart', 'helm global values', 'helm library chart', 'helm umbrella chart', 'helm postrender', 'helm diff', 'helmfile', 'helm values schema', 'helm crd', 'chart museum', 'chart repo', 'helmfile environment'. Covers: Helm chart development, templating, dependency management, testing, CI/CD integration, security, advanced patterns, and operational best practices.
devops-pulumi
by j4flmaoPulumi Infrastructure as Code using real programming languages (TypeScript, Python, Go, C#). Covers: Pulumi CLI, stack management, state backends, AWS/Azure/GCP providers, Kubernetes provider, component resources, Automation API, secrets, policy as code, migration from Terraform. Do NOT use for: Terraform, CloudFormation, or other IaC tools not using Pulumi.
Browse Agent Skills by Occupation
23 major groups · 867 SOC occupations
Browse by Category
Explore agent skills organized by their primary use case
Explore the agent skills ecosystem by occupation and creator
SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.
Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.
Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.
01 Map a field
Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.
02 Follow creators
Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.
03 Search with sources
Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.
Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.
Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)
In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.
Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.
The Structure of a Professional SKILL.md File
A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:
- Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
- Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
- System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
- Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
- Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.
Optimizing Agent Workflows for Modern LLMs
Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.
Exploring by SOC Occupations and Creator Profiles
What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.
SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.
Frequently Asked Questions
A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.