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...
claude-mobile-validation-gate
by krzemienskiUse when executing validation gates 3A, 4A, or 6A-E, verifying phase completion with expo-mcp visual testing, or encountering test failures - automates gate execution with expo-mcp autonomous verification and HARD STOP enforcement
consensus-engine
by krzemienskiMulti-validator agreement gate. N independent validators against same feature; synthesize confidence-scored verdict.
consensus-engine
by krzemienskiMulti-validator agreement gate. N independent validators against same feature; synthesize confidence-scored verdict.
goal-condition-architect
by krzemienskiTransform any input into a single transcript-provable /goal completion condition. ALWAYS use when the user says "make a /goal", "set a goal", "goal condition", "transcript-provable end state", "airtight finish line", "design completion criteria", or "turn this into an autonomous run". Produces the four-part anatomy (end-state, checks, constraints, bound) and runs an adversarial harden pass before handing off.
plan-author
by krzemienskiLinear hierarchical plan author producing plan.md + phase-NN.md files. Plans-as-prompts framing — PLAN.md IS the prompt that executes the phase. ALWAYS use when the user says "plan this", "create plan", "implementation plan", "write a plan", "draft plan", or invokes /shannon:plan, /shannon:plan-author, /shannon:plan-author, /shannon:plan-deep, or /shannon:prd. Each phase has measurable transcript-provable success criteria and an embedded validation gate. Scope-atomic (2-3 tasks max per file).
playwright-validation
by krzemienskiUse for web feature validation via Playwright MCP — real browser interactions, cross-browser support (Chromium/Firefox/WebKit), screenshot + DOM snapshot evidence capture, form testing, responsive layouts, console/network error detection. Reach for it when you've picked Playwright as your browser tool (vs Chrome DevTools MCP), or on phrases like 'Playwright validation', 'validate with Playwright', 'browser feature test', 'cross-browser check', 'take DOM snapshot', 'browser automation for validation'. For performance-focused Chrome inspection use chrome-devtools; for the overall web-validation flow use web-validation.
ios-validation-runner
by krzemienskiUse for deep iOS validation of multi-step user flows where screenshots alone miss the timing — animations, loading states, state transitions, anything where the journey matters more than the endpoints. Runs a five-phase protocol (SETUP → RECORD → ACT → COLLECT → VERIFY) that captures video + logs in the background while you interact with the app, then analyzes everything together for a PASS/FAIL verdict. Reach for it when you need richer evidence than ios-validation-gate provides, when debugging state transitions, or when someone asks 'what actually happens between tap and result'.
consensus-engine
by krzemienskiUse when a single-validator PASS is not enough confidence — high-stakes features (payments, auth, data migrations, security surfaces), pre-ship release gates, regression review on large refactors, flake hunting, and audit trails for regulated work. Spawns N (≥2, default 3) independent validator agents against the same journey list, each with its own isolated evidence subdirectory, then synthesizes their per-journey verdicts into a single consensus verdict with a confidence score (UNANIMOUS → HIGH, MAJORITY → MEDIUM, SPLIT → LOW). Disagreements trigger root-cause investigation before the final verdict is emitted. Reach for it on phrases like 'consensus validation', 'multi-agent verdict', 'get a second opinion', 'validate with N agents', 'pre-ship gate', 'confidence-scored verdict', 'agreement-based review', or when you want to catch flaky behavior with parallel independent runs. Not for coverage fan-out (use parallel-validation or forge-team); not without a validation plan (run create-validation-plan first); n
consensus-engine
by krzemienskiMulti-validator agreement gate with 5-state synthesis and multi-round debate iteration. ALWAYS use when the user says "consensus validation", "validate with N reviewers", "agreement gate", "high-confidence validation", "consensus gate", or needs confidence-scored verdicts. Spawns ≥2 (default 3) independent validators in isolated evidence dirs, applies the 5-state synthesis table (UNANIMOUS_PASS / UNANIMOUS_FAIL / MAJORITY_PASS / MAJORITY_FAIL / SPLIT), and escalates SPLIT or borderline MAJORITY to up to 3 rounds of filesystem-mediated debate.
flutter-validation
by krzemienskiUse for validating Flutter apps on Android emulators, iOS simulators, and connected physical devices. Runs the protocol: flutter doctor check, pub get, analyze, build (APK/AAB for Android, .app/.ipa for iOS), install on device/emulator, launch, screenshot captures at key states, log streaming via flutter logs for os_log/adb logcat, crash detection via error markers in the log stream. Pairs with e2e-validate for orchestration or runs standalone for Flutter-only projects. Reach for it on phrases like 'validate my Flutter app', 'flutter run check', 'test on simulator', 'dart/flutter test failed', 'pub get validation', or before any Flutter release.
team-validation-dashboard
by krzemienskiUse for organization-wide visibility across multiple projects' validation health — not for a single project (use forge-benchmark for that). Aggregates posture scores, coverage %, regression trends, and journey ownership across all registered projects in a team's portfolio. Flags critical projects (score < 60) for attention. Reach for it on phrases like 'team dashboard', 'show validation across all projects', 'which projects need attention', 'quarterly validation review', 'who owns journey X', or for CI/CD reporting in multi-project orgs.
consensus-synthesis
by krzemienskiSynthesize N per-validator verdicts into a single consensus verdict with confidence scoring based on agreement level.
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.