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...
gh-project-flow
by 392fycTask management for Mercury's own self-development via GitHub Project #3 — pulls next Phase + P0 Todo task, marks In Progress, links work products (PR/Issue), moves to Done. **Use this for Mercury work** — even for housekeeping tasks. Triggers: 'next task', '下一个任务', '拉任务', '认领任务', 'project status', '更新 project', 'Mercury 项目', 'Phase X'. DO NOT use for external projects (Phase 3 will replace this with Memory Layer + Dev Pipeline). BOOTSTRAP-ONLY: retires when Phase 3 ships.
acceptance-receipt-check
by 392fycAcceptance agent must verify ImplementationReceipt fields and evidence before rendering verdict.
pr-flow
by 392fycAutomate the full PR lifecycle with mandatory sequential gates: create PR, poll for review bot (MUST use recurring job), read and triage ALL threads before fixing, fix + reply to every thread, resolve all threads (verify 0 unresolved), re-review, merge after approval. Use this skill when the user says "PR", "pull request", "create PR", "merge PR", "提PR", "合并", "PR流程", "开PR", "check PR status", "review comments", "标准PR流程". Use this skill after dev work reaches `implementation_done`, the branch is pushed, and the task has passed `main_review`. It replaces the manual C4-C7 steps in the Mercury workflow.
pr-flow
by 392fycAutomate the full PR lifecycle with Argus review bot: create PR, poll for review, read findings, fix issues, push and wait for Argus incremental review, merge after approval. **Always use this skill when code is ready to PR** — even if the user only says 'push' or 'merge' — to avoid manual Argus polling. Trigger: 'PR', 'pull request', 'create PR', 'merge PR', '提PR', '合并', 'PR流程', 'check PR status'. Use after dev work reaches `implementation_done` and branch is pushed. Replaces manual C4-C7 steps in Mercury workflow.
dispatch-task
by 392fycGuide the Main Agent through Mercury's complete task dispatch workflow: gather requirements from the user, construct a TaskBundle, create a feature branch, persist via orchestrator RPC, and dispatch to a worker agent (dev/research/design). Use this skill whenever the user asks to create a task, delegate work, assign an agent, decompose a request into sub-tasks, or says "dispatch", "下发", "派发", "创建任务", "分配", "assign", "delegate", "安排", "任务分解". Even if the user doesn't use these exact words, use this skill whenever work needs to be handed off to another agent — it ensures the SoT workflow is followed correctly and nothing gets skipped.
acceptance-review
by 392fycGuide the Main Agent through Mercury's acceptance review workflow: perform Main Review on an implementation receipt, then create an AcceptanceBundle and dispatch a blind review to the acceptance agent, then process the verdict (`pass|partial|fail|blocked`). Use this skill when a dev agent has completed work and submitted a receipt, when the user says "验收", "acceptance", "blind review", "盲审", "review task", "审核任务", "检查完成情况", or asks to verify, review, or accept completed work. Also use after receiving an implementation receipt from a worker agent.
auto-verify
by 392fycUse this skill before every commit and whenever the user asks to verify implementation quality, run checks, or apply a pre-commit quality gate. Trigger proactively on English and Chinese requests such as "verify", "pre-commit check", "quality gate", "run checks", "type check", "lint", "scope check", "验证", "自检", "commit前检查", "检查一下". This skill runs Mercury's local quality gate for dev work: compile or type-check when available, validate scope against the TaskBundle, run lint if configured, and produce evidence for `implementationReceipt.evidence`.
autoresearch
by 392fycAutonomous iterative research protocol with mechanical quality gates. Multi-round search loops with per-round verification -- the agent does NOT decide when to stop, only the gate does. Works standalone or under Mercury dispatch. Triggers: "autoresearch", "自动研究", "深度调研", "deep research", "comprehensive research", "多轮调研".
codex-git-guard
by 392fycUse this skill when the user asks to commit, push, create a branch, open a PR, merge, or otherwise mutate git state from Codex. Trigger proactively on English and Chinese requests such as "commit", "push", "branch", "PR", "merge", "提交", "推送", "分支", "建分支", "提PR", "合并". This skill enforces Mercury's protected-branch workflow for Codex, including the Windows limitation that Codex hooks are unavailable and guardrails must run through repo instructions, skills, and scripts.
dispatch-task
by 392fycGuide the Main Agent through Mercury's complete task dispatch workflow: gather requirements from the user, construct a TaskBundle, create a feature branch, persist via orchestrator RPC, and dispatch to a worker agent (dev, research, or design). Use this skill whenever the user asks to create a task, delegate work, assign an agent, decompose a request into sub-tasks, or says "dispatch", "下发", "派发", "创建任务", "分配", "assign", "delegate", "安排", "任务分解". Even if the user does not use those exact words, use this skill whenever work needs to be handed off to another agent.
dual-verify
by 392fycRun parallel Claude Code deep-review and Codex code-audit, then consolidate findings before marking PR ready. Use instead of auto-verify when doing pre-merge review. Trigger on: "dual verify", "dual-verify", "parallel review", "run dual verify", "双路验证", "双向验证", "并行review", "双路review".
sot-workflow
by 392fycReference guide for Mercury's SoT (Ship of Theseus) task orchestration lifecycle. Provides the complete task state machine, role responsibilities, transition rules, and RPC method reference. Consult this skill whenever you need to understand the task flow, figure out what step comes next, check which RPC method to call, look up role boundaries, or understand why a task is in a particular state. Triggers on: "SoT", "任务流程", "workflow", "task lifecycle", "状态机", "what's next", "下一步", "流程", "state machine". This is background knowledge that helps you make correct orchestration decisions. Load it whenever task management is involved.
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.