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...
audit
by matthewmackesIntegrity sweep of the MAP2 Audio Platform (Python FastAPI backend, JUCE/C++ engine, React/Carbon frontend, device-packs): find dead/unreachable code, stubs, mockups passing as features ("Coming Soon" cards, placeholder tabs), convention violations (raw hex vs Carbon tokens, unregistered routes, stale OpenAPI pins, untracked migrations), and doc/worklist drift — each finding gets a FINISH-or-REMOVE verdict. TRIGGER when the user asks to "audit", "evaluate compliance", "check for dead code/stubs", or "find what's not really done". Produces a findings table; it does NOT fix things unless asked.
plan
by matthewmackesDesign-thinking + survey + worklist-scoping skill for the MAP2 Audio Platform. Use when the user asks to scope an epic, run an N-question AskUserQuestion survey, lock a non-trivial design decision, audit the worklist for drift, rescue dead modules, lift design-doc actions into worklist tasks, or draft a design document — i.e. PLAN before any code lands (CLAUDE.md Plan-First Meta Rule). Defers to map2-worklist-management for the canonical task schema. Sister skills: ship (drains the queue), audit (integrity sweep), build-installer-rpm (the RPM cut).
ship
by matthewmackesAutonomously drain the MAP2 worklist: a rescue pass to catch dead/mock code, then implement open tasks fully (no stubs), gating each (pytest · jest · typecheck · web build · cmake for engine changes), committing + dual-pushing (origin + gitlab) + rebuilding/restarting port 3000 as you go. TRIGGER when the user says "ship it", "execute", "continue", "drain the worklist", or "work through the backlog". Do NOT use for a single scoped edit (just do it) or a release/RPM cut (use /build-installer-rpm).
build-installer-rpm
by matthewmackesBuild a production-grade MAP2 Audio Platform installer RPM. Creates a clean build workspace outside the source repository, improves packaging artifacts inside the repo (spec, .gitattributes, config files, map2-setup wizard), then runs rpmbuild and produces a distributable RPM. The original source repository is never deleted from, restructured, or broken.
complete-remaining-work
by matthewmackesExecute remaining project tasks from the canonical worklist with aggressive parallelization, completeness-first implementation, and explicit tech-debt capture. Use when the user asks to continue work, complete remaining steps, move quickly, bundle tasks, or proceed without repeated confirmation.
juce-random-effects-soak
by matthewmackesRun a full JUCE callback-path soak using 10 random native effects at once, rotating serial/parallel flow topologies and blend strategies between flows while collecting xrun, jitter, and CPU evidence. Use when validating engine stability after graph/device/lifecycle changes, reproducing post-start_audio regressions, or generating release-grade performance proof.
licencing
by matthewmackesTrack and enforce MAP2 licensing posture as full-project AGPLv3 for MAP2-owned code, with third-party license overrides preserved, including compliance audits, documentation checks, and required remediation task creation in docs/PROJECT_WORKLIST.md. Use when changing code, preparing releases, updating README/legal docs, or answering licensing-status/compliance questions.
map2-copilot-instructions
by matthewmackesMAP2 Copilot-specific collaboration rules and user preferences, especially git workflow requirements. Use when handling commit/push/sync requests, applying user workflow preferences, or following .github/copilot-instructions.md behavior in this repository.
map2-gemini-instructions
by matthewmackesMAP2 Audio core engineering guidance and memory protocol. Use when working in this repository on architecture, coding standards, build/test/deploy commands, server management, performance and latency constraints, and when asked to remember new fixes or patterns.
map2-worklist-management
by matthewmackesEnforce a single canonical project worklist with strict task schema, status tracking, and restart-safe handoffs. Use when planning, executing, or reporting project work; when adding new ideas, bugs, or features; when coordinating parallel subtasks across AI threads/humans; and when the user asks to apply the Cortex AL worklist rule.
revisit-map2-installer-rpm
by matthewmackesReassess and modernize MAP2 installer and packaging on Fedora Server by auditing a current MAP2 host against a documented stock Fedora baseline, computing evidence-backed deltas, and generating an idempotent verbose installer plus RPM/repository scaffolding. Use when revisiting full installer builds, updating Fedora deployment automation, validating AVB/TSN readiness, or preparing MAP2 package and repo release workflows.
release
by matthewmackesExecute the `cut release X.Y.Z` 7-step shorthand once operator types the trigger — version bump (4 files), CHANGELOG entry, smoke test, `make rpm`, commit, tag, push (dual-remote), and watch the GitHub workflow. **Will refuse to run if any HW carve-out item targeting the release version is still `[ ]` Open per CLAUDE.md §0.15 (Q69 lock).** Use ONLY when operator types `cut release X.Y.Z` or `cut release` shorthand. New 2026-05-25 per Q87 of the 100-Q tightening survey. Sister skills: `plan` (design first), `ship` (execute the queue first).
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.