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...
02-verify-plan
by Math-Data-Justice-CollaborativeVerifies product plan documents by breaking them into provable statements, risk-classifying each (high/medium/low confidence), auto-approving high-confidence statements derived from user's own answers, and presenting medium/low confidence statements for user review. Includes embedded consistency checking across all spec documents. Produces audit report and decision log.
05-verify-tech
by Math-Data-Justice-CollaborativeVerifies technical plan documents by breaking them into provable statements, risk-classifying each, and presenting medium/low confidence statements for user review. Includes embedded consistency checking between technical plan and product plan. Runs a consistency agent in the background while the user reviews statements.
audit-docs
by Math-Data-Justice-CollaborativeAudits doc-planner output by breaking each document into provable (falsifiable) statements and walking the user through each one for approval, denial, or modification. Produces a document audit report, a decision log, and tracks progress with persistent state management. Runs after doc-planner and before build-planner. Use when the user wants to verify specs, audit documentation claims, validate statements in generated docs, or review doc-planner output before implementation.
15-service-health
by Math-Data-Justice-CollaborativeInvestigates a deployed Vecinita RAG service in two layers: platform infra health (API up, DB migrations, secrets, deploy drift, GitHub main CI green via H0ci) and live behavior (ingest smoke, query smoke, E2E tiers). AskQuestion-driven depth and budget before running checks. Test-driven on user failures (repro test red → confirm → investigate → fix via 14-hotfix). Opens docs/bug-reports/BUG-*.md for code bugs. Use for production health, ambiguous API/DB errors, periodic ops, post-deploy verification, or confirming main CI passes after merge/hotfix.
13-deploy-smoke
by Math-Data-Justice-CollaborativeExecutes the deployment, runs API smokes (H1–H3) plus browser connectivity gates (H4–H5: CORS + frontend bundle wiring), health checks, changelog, and monitoring baseline. Final pipeline stage. Blocking — user must approve deployment results.
06-tech-tooling
by Math-Data-Justice-CollaborativeCreates development tooling: Cursor hooks for linting, formatting, typechecking, and testing; rules for spec-adherence, TDD, atomic commits, and build execution; and tool configuration files. Blocking stage — must complete before build execution begins.
11-verify-impl
by Math-Data-Justice-CollaborativeOverall verification that the implementation matches what the user wanted. Collects results from 09-qa and 10-e2e, performs feature-level completeness checking against the product plan, and walks the user through approval of each feature area. Produces targeted patches for flagged issues (fix in place, no phase re-runs).
17-retrospective
by Math-Data-Justice-CollaborativeReviews Cursor agent conversation logs and pipeline skills 00-16 against project artifacts, then interviews the user with batched AskQuestion prompts to capture what went well, what to improve, and brainstorm process fixes. Ends with an interactive skill-update workshop (proposed patches per SKILL.md, user approves via AskQuestion). Produces a retrospective report and prioritized action backlog. Use after milestones, phase completions, hotfix cycles, evolve cycles, or when the user asks for a retrospective, lessons learned, or pipeline improvement — not for bug fixes (14-hotfix) or feature work (16-evolve).
08-verify-build
by Math-Data-Justice-CollaborativeRuns quality checks at milestone boundaries during the build. Auto-corrects lint and format issues without blocking. Only blocks on test failures, type errors, or security issues that require user decisions. Invoked by 07-build at milestone and phase boundaries, not as a separate pipeline step.
09-qa
by Math-Data-Justice-CollaborativePost-build quality assurance. Runs full lint, format, typecheck, security, dependency, data-staging, Modal workspace, and cross-file checks on the entire codebase. Writes docs/qa-report.md with blocking vs advisory findings. Runs in parallel with 10-e2e; results consumed by 11-verify-impl. Advisory remediation is a separate user-requested pass (spawn parallel agents) — not part of the default 09 run.
14-hotfix
by Math-Data-Justice-CollaborativeSurgical post-deployment edits: bug fixes, patches, small behavioral changes, and dependency updates applied to a deployed codebase without re-running the pipeline. Test-driven investigation: one bug = docs/bug-reports/BUG-*.md (logs + investigation MD), tests/bugs/test_bug_*.py (red then green), one fix. AskQuestion interviews at each gate, including Phase 5 prevention/countermeasures and optional Cursor rule creation. See bug-investigation skill. Interview, verification plan, spec checks, main CI parity before PR and gh run on main after merge, deploy only with user approval. Never re-runs entire phases.
07-build
by Math-Data-Justice-CollaborativeExecutes the implementation plan task-by-task following TDD ordering, spec-adherence rules, and atomic commit conventions. Orchestrates parallel agents for independent tasks, manages branches and PRs, invokes 08-verify-build at milestone boundaries, and keeps the execution plan in sync with progress. Supports delta mode for feature addition via evolve cycles. Use when implementing tasks or adding features to an existing app (with active evolve cycle).
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.