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...
qplan
by 3awnyReview an implementation plan before any code is written — checks it against the actual codebase for missing steps, wrong assumptions, ignored existing patterns, and unhandled edge cases. Use after drafting a plan/TRD and before implementing; qship runs it as Step 6.
qauthtrailingslash
by 3awnyAudit API routes for the trailing-slash / 307-redirect auth bug — where a missing or extra trailing slash makes the server issue an HTTP 307 redirect and the client silently drops the Authorization header, causing intermittent 401s. Use when reviewing or debugging FastAPI/Starlette (or similar) routes, auth-token loss across redirects, or flaky authenticated endpoints.
qcheck
by 3awnyReview code changes for correctness, security, and convention adherence — the general-purpose code reviewer. Use on a diff or recent changes before committing or opening a PR to catch bugs, risky patterns, and style violations; the central review step in the qship pipeline.
qclean
by 3awnyReview a change for defensive/dead code that should be removed — unnecessary null-guards, speculative branches, leftover scaffolding, over-engineering. Use after implementing a feature to strip code that adds noise without adding value; qship runs it as Step 7.4.
qdirectory
by 3awnyReview where new files/modules were placed — do they sit in the right directory, follow the repo's layering and naming conventions, and avoid creating parallel structures. Use after adding files to confirm the change fits the existing architecture; qship runs it as Step 7.3.
qmemory
by 3awnyCapture a durable lesson from this work into persistent memory — a non-obvious gotcha, a confirmed convention, or feedback worth re-applying on future tasks. Use when you learn something that should outlive the session; qship runs it as Step 11.7 to record review/bug lessons.
qshipmaster
by 3awnyEpic-level orchestrator for qship. Takes a Jira Epic ID, builds a topologically-sorted wave plan from its children, spawns one qship-persist.sh per ticket per wave in parallel, merges each wave into a consolidated epic branch, runs a lightweight wave-gate after each wave (migration check + targeted tests + 2 bug hunters + qbcheck, blocks only on Critical) and ONE full epic-level Phase 2 review after the last wave on the cumulative diff, and ships ONE consolidated PR per repo. Two engine knobs — `provider=claude|codex` chooses the Step 7 implementer (default Opus 4.7 1M, medium), and `reviewer=claude|codex` chooses the Phase 2 reviewer (default Claude). The diversified combo `provider=claude reviewer=codex` runs Opus implementing + gpt-5.5 high reviewing for different-family second opinion. Set `QSHIP_PER_WAVE_REVIEW=full` to restore full Phase 2 per wave, or `=none` to skip per-wave review entirely. Resumable, state-driven, idempotent.
qbug
by 3awnyHunt for the root cause of a bug — trace symptoms back to the underlying defect and report findings, without applying fixes (hunt-only, so you stay in control of the change). Use when investigating a failure, unexpected behavior, or a flaky test and you want the true cause rather than a surface patch.
qspinuplocal
by 3awnySpin up your primary service locally against a local Postgres DB for testing — env wiring, optional migrations, health check. Single-service by design; adapt the start command to your stack.
configure
by 3awnyOne-time interactive configurator for the qship skill catalog. Run this immediately after installing the qship plugin (the SessionStart hook will remind you on first use). Walks through a short questionnaire (7 rounds, ~two dozen questions) plus a per-repo loop (1 repo or 100, the configurator doesn't care), renders the full skill set into your ~/.claude/skills/ tree, then verifies the install and required external plugins. Idempotent — re-runnable any time you want to change a value (added a service, new Jira project key, opted into a previously-skipped integration).
qbcheck
by 3awnyValidate candidate bugs before reporting them — an adversarial second pass that confirms each finding is real (reproducible, correctly root-caused) and filters out false positives. Use after a bug hunt or code review to gate which findings are worth surfacing; qship runs it as the Step 10 quality gate before any bug is acted on.
qcheckf
by 3awnyReview a single function in depth — signature, parameters, edge cases, error handling, and whether it does one thing well. Use when you want a focused critique of one function (not a whole diff), e.g. a complex or hot-path routine you're about to ship.
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.