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...
midnight-node-node-rpc-api
by devrelaicomMidnight node RPC API, WebSocket, port 9944, midnight_contractState, midnight_zswapStateRoot, midnight_ledgerStateRoot, midnight_apiVersions, midnight_ledgerVersion, systemParameters RPC, sidechain RPC, system_health, chain_getBlock, state_getStorage, author_submitExtrinsic, grandpa_roundState, beefy RPC, mmr RPC, rpc.discover, OpenRPC, subscribe, subscription, query contract state, submit transaction to node, connect to Midnight RPC, subscribe to block headers, check node sync status.
compact-core-compact-standard-library
by devrelaicomThis skill should be used when the user asks about the Compact standard library (CompactStandardLibrary), stdlib types (Maybe, Either, JubjubPoint, MerkleTreeDigest, MerkleTreePath, ContractAddress, ZswapCoinPublicKey, UserAddress), deprecated stdlib names (CurvePoint, NativePoint, CoinInfo), stdlib constructor functions (some, none, left, right), elliptic curve functions (ecAdd, ecMul, ecMulGenerator, hashToCurve, jubjubPointX, jubjubPointY, constructJubjubPoint), Merkle tree path verification (merkleTreePathRoot, merkleTreePathRootNoLeafHash), or when the user needs to verify which functions exist in the standard library or prevent hallucination of non-existent stdlib functions.
midnight-cq-dapp-connector-testing
by devrelaicomThis skill should be used when the user asks to test DApp Connector API integration, test wallet connection, test makeTransfer, test balanceTransaction, test submitTransaction, mock ConnectedAPI, stub wallet for tests, test wallet errors, test PermissionRejected, test Disconnected handling, test progressive enhancement, write wallet integration tests, test DApp Connector error codes, test wallet discovery, test window.midnight, test apiVersion, test signData, or test DApp Connector security.
midnight-verify-verify-zkir
by devrelaicomZKIR claim classification and method routing. Determines what kind of ZKIR claim is being verified and which verification method applies: WASM checker (accept/reject testing), circuit inspection (compiled structure analysis), or source investigation. Handles claims about opcode semantics, constraint behavior, field arithmetic, transcript protocol, and compiled circuit properties. Loaded by the /midnight-verify:verify command alongside the hub skill.
midnight-node-node-validator
by devrelaicomThis skill should be used when the user asks about running a Midnight validator end-to-end — generating validator session keys, becoming a permissioned (federated) or registered (staked) candidate, how the committee is selected via the D-parameter and Ariadne, committee rotation per Cardano epoch, producing blocks with --validator, and testing a validator locally with the mock main-chain follower. Covers "how do I run a validator", "become a block producer", "permissioned vs registered candidate", "validator committee selection", "validator not producing blocks", and "register as a Midnight validator".
midnight-verify-verify-ledger
by devrelaicomLedger/protocol claim classification and method routing. Determines what kind of ledger claim is being verified and which verification methods apply: source investigation (primary), type-checking (pre-flight for TypeScript API), compilation/execution (secondary for testable claims), or ledger-v8 execution (secondary for API behavioral claims). Handles claims about transaction structure, token mechanics (Night/Zswap/Dust), cost model, on-chain VM, contract execution, cryptographic primitives, well-formedness rules, and the @midnight-ntwrk/ledger-v8 TypeScript API. Loaded by the /midnight-verify:verify command alongside the hub skill.
midnight-tooling-release-notes
by devrelaicomThis skill should be used when the user asks about "Midnight release notes", "what changed in version X", "latest release", "changelog", "show me the changelog", "what's new in Midnight", "component versions", "list versions", "compact release notes", "ledger release notes", "wallet release notes", "proof server release notes", "node release notes", "lace release notes", "midnight-js release notes", "indexer release notes", "breaking changes", "latest version of X", viewing release history, checking component update details, or comparing versions of any Midnight Network component.
midnight-status-codes-status-codes
by devrelaicomUse when an agent encounters a Midnight error code, error message, or error type and needs to identify what it means, what component produced it, and how to fix it. Routes to the correct reference file based on error source and characteristics. Covers numeric node error codes (0-255), TypeScript SDK error classes, Effect tagged wallet errors, Compact compiler diagnostics, ZK proof errors, ledger validation errors, proof server HTTP errors, indexer GraphQL errors, and DApp Connector API errors.
core-concepts-tokenomics
by devrelaicomThis skill should be used when the user asks about Midnight tokens, NIGHT token, DUST resource, token distribution, Glacier Drop, Scavenger Mine, block rewards, tokenomics whitepaper, STAR denomination, token economics, dual-token model, MEV resistance, token supply, or how transaction fees work in Midnight.
midnight-wallet-managing-test-wallets
by devrelaicomThis skill should be used when the user asks to create a test wallet, fund a wallet, get tNight from a faucet, register DUST, monitor wallet balance, transfer NIGHT or shielded tokens, derive a wallet from a seed or BIP-39 mnemonic, set up wallets for tests, watch an address for incoming funds, generate dust, fund their DApp's test fixtures, or run end-to-end test scenarios that need real wallets on the local devnet or a public testnet.
compact-core-compact-transaction-model
by devrelaicomThis skill should be used when the user asks about Midnight transaction execution, guaranteed vs fallible phases, kernel.checkpoint(), transaction composition, state conflicts, DUST fees, gas limits, proof verification, partial transaction success, transaction merging, atomic swaps, or how Compact circuits map to on-chain execution. Also triggered by mentions of "transaction semantics", "fallible phase", "guaranteed phase", "checkpoint", "well-formedness", "Impact VM", or "Zswap offers".
compact-core-compact-tokens
by devrelaicomThis skill should be used when the user asks about Midnight tokens, token types (NIGHT, DUST, shielded, unshielded), minting and burning tokens, token transfers, token colors and domain separators, the zswap protocol, ShieldedCoinInfo, QualifiedShieldedCoinInfo, Kernel mint operations, contract token patterns (FungibleToken, NonFungibleToken, MultiToken), the account model vs UTXO model for tokens, sendShielded, receiveShielded, sendUnshielded, mintShieldedToken, mintUnshieldedToken, unshieldedBalance, OpenZeppelin Compact token contracts, or choosing between shielded and unshielded token approaches.
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.