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...
deep-research
by Undertone0809Conducts enterprise-grade research with multi-source synthesis, citation tracking, and verification. Produces citation-backed reports through a structured pipeline with source credibility scoring, and grounds abstract findings in concrete examples, cases, counterexamples, or mini-scenarios when helpful. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.
landing-proof-shots-maintainer
by Undertone0809Maintain the Rudder landing-shot workflow. Use when the user wants either polished app screenshots captured for them or a seeded dev/demo organization so they can capture screenshots themselves. Enforces full-page whole-app screenshots instead of browser-window or cropped-partial captures.
release-maintainer
by Undertone0809Maintain and execute Rudder releases across npm, GitHub Releases, and Desktop portable assets. Use this skill whenever the user asks about 发版, release, publishing to npm, canary/stable promotion, GitHub Release assets, Desktop distribution, `npx @rudderhq/cli@latest start`, `npx @rudderhq/cli start`, broken npm `latest` dist-tags, full Desktop install smoke tests, GitHub Release API/rate-limit failures, version bumps, rollback, obsolete canary GitHub Release/tag cleanup after stable promotion, first-time package bootstrap, npm token-based fallback publishing, or release workflow failures. Prefer this skill for both planning and hands-on release operations in the Rudder repository, even when the user only asks "现在要做什么" or "帮我发版".
skill-creator
by Undertone0809Create new skills, improve existing skills, and evaluate whether a skill definition is actually doing useful work.
skill-optimizer
by Undertone0809Improve, debug, benchmark, or refactor an existing Agent Skill from conversation evidence, execution traces, user corrections, eval failures, or target skill files. Use this skill whenever the user asks to optimize, harden, generalize, validate, benchmark, package, or turn observed behavior into durable skill changes. Produces evidence-based diagnosis, reviewable patches, trigger evals, validation cases, and safe next-run behavior; do not use it to perform the target skill's normal task.
software-product-advisor
by Undertone0809Cross-functional advisor for software product work when a feature, workflow, UI, spec, or implementation feels wrong but the user cannot yet express a precise critique. Use this whenever the user says a result feels off, too complex, too noisy, too generic, or not ready for another blind iteration; whenever they want a professional diagnosis before more implementation; or whenever vague discomfort needs to become explicit standards, evaluation criteria, realistic options, and a clear next move. Also use it when a team is stuck deciding whether to patch the current solution, rewrite the spec, revise the architecture, or establish a missing standard first.
build-advisor
by Undertone0809Expert advisor for when a build, UI, workflow, spec, or implementation feels wrong but the user cannot yet express the right product, design, engineering, or evaluation critique. Use before more implementation to turn vague dissatisfaction, weak AI-built results, traces, benchmarks, or eval evidence into a grounded first-principles scenario analysis, explicit criteria, realistic options, corner-case coverage, and a recommended next move.
advisor-review-loop-maintainer
by Undertone0809Run a decision-grade advisor-to-reviewer loop for Rudder development work. Use this skill when the user asks to combine Build Advisor with Agent Work Reviewer Maintainer, wants first-principles scenario and requirement analysis plus an independent reviewer loop or acceptance gate, asks for two reviewer agents, says "迭代两轮", "没有通过 review 返工", "从场景和需求出发", "corner cases", or needs a proposal, skill, workflow, UI, architecture, release review, or agent outcome to survive independent review before final handoff. Prefer plain build-advisor for first-principles advice that does not require reviewer agents, repeated review rounds, or acceptance gating.
agent-work-reviewer-maintainer
by Undertone0809Review Rudder agent work. Use for review/第一性原理/PM review of Codex sessions, PRs, commits, UI, releases, regressions, or agent outcomes. Separates author-claimed proof from reviewer-verified proof. For functional or UI reviews, run the real Rudder scenario with Browser or Computer Use when available instead of accepting from diffs.
codex-session-benchmark-maintainer
by Undertone0809Benchmark and compare local Codex sessions for Rudder development work. Use when the user gives a target Codex session id or clearly asks to compare one session or class of sessions with recent Codex history, recent Rudder runs, or "最近 30/50/100 条". Cover efficiency, follow-up rate, interruption rate, token/cost hints, problem-resolution rate, workflow quality, or whether the target performed better or worse than the surrounding cohort. Produces a proxy-metric report with explicit caveats, failure classes, and next skill/workflow improvements. Prefer this over generic conversation analysis for target-vs-baseline comparison; do not use it alone for cohort-only skill hygiene prompts whose deliverable is "which skill should be optimized".
codex-session-product-reviewer-maintainer
by Undertone0809Review a local Codex session, task, or commit as a professional product manager and first-principles reviewer. Use when the user gives a Codex session id, asks to review another agent's task, says "PM review", "professional product manager", "first principles", "第一性原理", "作为 reviewer", "review 一下 codex session", or wants a judgment on whether an implemented task solved the right product problem. Pull evidence from local Codex logs and repo artifacts before judging.
debug-run-transcript-maintainer
by Undertone0809Debug and analyze Rudder agent run transcripts, run logs, and execution traces. Use this skill whenever the user mentions: - "debug run", "分析 run", "查看 run" - "为什么这个 agent 执行失败", "run 出错了" - "transcript 怎么看", "run 的日志" - a run ID or run ID prefix - "最近 30 个 run", "recent runs", "run 质量", "分析这个 org 最近运行" - agent execution, tool calls, stdout/stderr 调试 Prefer this skill whenever the user wants to understand what happened during one run or a recent batch of runs, even if they only have a partial run ID, org name, agent/runtime, or timeframe. Do not default to raw SQL first; use Rudder's run-intelligence path first, then fall back only if needed.
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.