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...
github-repo-setup
by schuettcUse when bootstrapping a new repo's GitHub-side setup — branch protection / rulesets, deploy environments, environment secrets, OIDC cloud auth, or required reviewers — or whenever deploy workflows reference secrets.* / environment: that don't exist yet. Captures the repo settings that make the feat → dev → main promotion model *enforced* rather than convention, and scopes deploy credentials to the environment that gates them.
feature-status
by schuettcDisplay project status and backlog overview. Use when user asks about current status, what's in progress, what to work on next, or wants a summary of the backlog. Read-only skill that formats DASHBOARD.md into a clear dashboard view.
guarding-scope
by schuettcCheck if requested changes are within current feature scope. Use when user requests new functionality or changes during implementation that might be scope creep. Compares requests against feature requirements and suggests adding out-of-scope items to backlog.
tracking-progress
by schuettcUpdate feature progress log and check off completed tasks. Use when user completes implementation tasks, makes commits, or indicates work is done. ASKS BEFORE MODIFYING files. Updates plan.md progress log section and implementation step checkboxes.
branch-promotion-model
by schuettcUse when bootstrapping a new repo's CI, setting up deploy workflows, deciding what branch a feature PR should target, or whenever someone proposes "auto-deploy prod on every main merge". Captures the feat → dev → main promotion model with separate Deploy Dev (push to dev) and Deploy Prod (push to main), and links the templates that implement it.
project-init
by schuettcApply project-workflow standards to a repo — feat → dev → main promotion model + CI gate, GitHub repo setup (branch protection, environments, secrets, OIDC), and the quality stack (skylos/fallow via lefthook + a shared justfile, run identically in CI). Detects current state and applies only the *missing* patterns, so it works on both new repos and existing ones. Use when setting up a new project or bringing an existing one up to standard.
quality-stack-setup
by schuettcUse when setting up a repo's lint / static-analysis / test tooling — wiring lefthook git hooks (pre-commit auto-fixers + pre-push full verify) and a justfile that is the single source of truth both the hooks and CI call, so local checks and CI can't drift. Language-agnostic: ruff/skylos for Python, prettier/eslint/fallow for TS/JS, same pattern for any language. Installs the tooling; ongoing operation lives in quality-workflow (/quality-audit, /quality-unblock, /quality-verify-hook) and the standing suppression rule in suppression-discipline.
quality-audit
by schuettcRead-only static-analysis snapshot. Runs skylos (Python) and fallow (TS/JS) full audits, writes a fingerprinted snapshot to .claude/quality-snapshots/YYYY-MM-DD.json, and renders a grade card plus delta vs the previous snapshot (NEW / RESOLVED / PERSISTING findings). Use when the user asks "what's my code health?", "run skylos", "run fallow", "audit quality", "snapshot quality", or after a cleanup pass to confirm wins.
quality-unblock
by schuettcTriage a failing pre-commit hook (skylos or fallow). For each finding, look up the rule in the day-1 playbook and present three options — fix in code, suppress with a required
suppression-discipline
by schuettcThe rule for suppressing static-analysis findings in any language — every suppression carries an inline rationale, and bare suppressions are a quality failure to fix. Use when someone adds or proposes a lint/analysis ignore (# skylos: ignore, # noqa, # type: ignore, # fallow-ignore, // eslint-disable, @ts-ignore, #[allow(...)], //nolint, etc.), proposes bypassing hooks with --no-verify, or when reviewing code that contains suppressions. Complements /quality-unblock, which triages a failing hook and enforces the per-PR cap.
sprint-assign
by schuettcGenerate a structured team assignment message from the current sprint plan. Produces a copy-pasteable message for Slack, email, or team chat with per-person assignments, context blocks, and key ground rules. Use after sprint-plan to share assignments.
sprint-audit-specs
by schuettcAudit all assigned feature specs for completeness. Checks that every developer has enough information to work independently — domain context, file paths, code maps, realistic examples, and clear deliverables. Flags gaps and offers to fix them. Use after sprint-plan, before sharing assignments.
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.