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...
land
by ScreenfieldsLand the plane — complete session close-out. Runs /retro for learnings capture, ensures all work is committed and pushed, and reconciles open work to GitHub Issues (file new ones; close ones whose work has shipped). Use when the user says "land", "land the plane", "wrap up", "close out", or before clearing context.
merge
by ScreenfieldsMerge a pull request with CI and label-gate checks. ALWAYS use this skill to merge PRs — never run `gh pr merge` directly. Enforces: (1) CI must be green, (2) PRs labeled requires-elevated-merge cannot be merged by regular agent identities. Use when the user says "merge", "merge this PR", "merge #N", or when a develop workflow reaches the merge step.
messaging
by ScreenfieldsInter-agent communication via agent-messaging MCP service. Use when sending messages to other agents, checking inbox, or coordinating work across projects.
onboard
by ScreenfieldsTemplate the spoke onboarding process — standing up a new project/agent on the Alfred platform. Use when bootstrapping a new spoke (project, service, or plugin constellation member) that needs a devbox, messaging identity, lead CLAUDE.md, and gitops token. All outputs are drafts for human review; nothing is auto-committed.
release
by ScreenfieldsAutomate marketplace plugin pin-bumps for the alfred-cc-tools catalog. Takes a plugin name and new version, verifies the upstream source PR is merged, bumps the version pin in marketplace.json, commits on a branch, opens a PR, and merges when CI is green. Use when bumping a plugin version pin: "release alfred-agent 1.9.8", "bump alfred-content to 1.1.0", "release new version of alfred-platform-ops".
retro
by ScreenfieldsSession retrospective for recursive self-improvement (RSI). Run at the end of a session to capture learnings, update instructions, and prepare context for the next session. Use when the user says "retro", "retrospective", "capture learnings", "what did we learn", or before clearing context.
review
by ScreenfieldsStructured PR review with doctrine-aligned angles. Two modes: interactive (conversational, agent-triggered) and headless (structured markdown output for CI/PR comment, exit code). Use when reviewing a PR for correctness, doctrine adherence, and scope hygiene. Invoke as: /alfred-agent:review [#N] [--mode=headless]
self-review-with-lens
by ScreenfieldsDiff-aware self-review prompt for autonomous worker sessions. Fed via adapter_review with a selected lens. Reviews the diff through the specified lens and emits a structured verdict: PASS, ADVISORY, or CRITICAL.
team-retro
by ScreenfieldsOrchestrate a trilateral+ retrospective across three or more platform agents. Use when the session involves cross-project scope, shared infrastructure decisions, or a shared infrastructure incident post-mortem. NOT for single-agent session retros (use alfred-agent:retro for those).
troubleshoot
by ScreenfieldsStructured diagnostic workflow for investigating failures, unexpected behavior, or broken systems. Use when something is broken and you need to find out why — NOT when you need to implement a feature (use alfred-agent:develop for that). Separate from develop because troubleshooting has its own discipline: cleanup contract upfront, hypothesis-driven probes, ground-truth verification, narrow interventions, conclude-or-escalate, teardown.
autonomous-worker-loop
by ScreenfieldsPer-task execution prompt for autonomous worker sessions. Fed via adapter_invoke to the runtime. Defines the strict implementation pattern: read issue substrate → implement code + tests → run local validation to green → open PR with Completion Signal → emit <promise>DONE</promise>.
design
by ScreenfieldsGuided design document creation for new services, features, or integrations. Use when the user says "let's build X", "design this", "plan for X", or when you're about to implement something involving multiple components, a new service, or unfamiliar technology. Also trigger when the user asks to scaffold, bootstrap, or create a new project. This skill prevents common failures: missing UI, wrong target environment, missing deployment setup.
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.