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...
cn-partition-arn-routing
by warren830Diagnose and explain AWS partition ARN mismatches in China region accounts. Use this skill whenever an investigation in `cn-north-1` or `cn-northwest-1` involves ARNs starting with `arn:aws:` instead of `arn:aws-cn:`, or whenever symptoms include AccessDenied, AuthFailure, MalformedPolicyDocument, NoSuchEntity, or "principal cannot be assumed" errors against IAM roles, SNS topics, KMS keys, S3 buckets, or any other ARN-bearing resource. Triggers also include the user mentioning "partition", "aws-cn vs aws", "cross-partition", "中国区 ARN 不对", "global partition ARN in China account", "trust policy 写错了", or pasting any ARN that looks like `arn:aws:iam::*` while the account context is China. Importantly, use this skill BEFORE concluding that an IAM trust policy or resource policy is "missing permissions" — the more common root cause in China region accounts is a partition string mismatch that the agent and generic LLM debuggers consistently get wrong.
china-account-prevention-checks
by warren830Proactive prevention and pre-alarm health checks across the two China region accounts (aws-cn and aws-cn-2). Use this skill when the user asks about prevention, 防护, 预防, proactive, 体检, health check, risk assessment, 潜在风险, 隐患, or "what might break soon", and when the Evaluation agent runs scheduled recommendation workflows. Looks for conditions that predict future incidents — single points of failure, service quotas nearing limits, stale AMIs, aging credentials, certificates expiring within 30 days, deprecated Lambda runtimes. This skill is distinct from cross-account-security-posture-check, which reports current-state security risk. Prevention predicts future failure; security posture describes current exposure.
china-incident-mitigation
by warren830Draft step-by-step mitigation CLI commands for a root-caused incident in either China account (aws-cn or aws-cn-2). Use this skill after RCA has identified the root cause, when the user asks for mitigation, remediation, 缓解, 修复, 回滚, rollback, restore service, 怎么修, fix it, 怎么办. Covers common mitigation patterns such as credential rotation, Kubernetes pod rollout-restart, ALB target group reattach, security group rule revoke, IAM policy rollback, and safe CloudFormation stack rollback. Output always includes the exact CLI command, a one-line explanation of what it changes, a rollback/undo command, and an explicit human approval prompt. CRITICAL — this skill NEVER executes commands autonomously; every mitigation step requires explicit user approval before running.
china-incident-rca
by warren830Root cause analysis for a triaged incident in either China account (aws-cn or aws-cn-2). Use this skill after triage has produced a Triage Card, or when the user directly asks RCA, 根本原因, 根因, 为什么挂, why did X fail, deep dive, deep investigation, 深入分析, dig into, 调查. Correlates the CloudTrail API log window around the incident, recent deploy events (CloudFormation stack events, CodeDeploy, ECR pushes, Lambda updates), metric anomalies against prior-week baseline, and cross-account blast radius — specifically, whether the same failure pattern also hit the other China account around the same time, which would suggest a shared upstream cause (IAM partition-wide, AWS region event, or common dependency). Produces a single root-cause hypothesis plus the evidence chain. Does NOT execute remediation.
china-incident-triage
by warren830First-response triage for an incoming alarm, ticket, or failure report originating from either China account (aws-cn or aws-cn-2). Use this skill when the trigger is an alarm name, CloudWatch alarm payload, SIM ticket body, error log snippet, or a user phrase such as 告警, 出事了, 服务挂了, incident, triage, 分类, 初步判断, 看一下这个告警, what happened. Determines which of the two accounts is affected, classifies the incident into one of six classes (compute / network / identity-credentials / data / cost / unknown), estimates severity from the signal, and checks whether a similar incident fired recently so duplicates are marked. Output is a short triage card that hands off to RCA or mitigation depending on severity. This skill is the entry point of the incident response pipeline.
china-region-multi-account-routing
by warren830Routing and disambiguation guidance for the two AWS China region MCP servers exposed by this Agent Space. Use this skill whenever the user's request mentions "中国区", "China", "cn-north-1", "cn-northwest-1", "Beijing", "Ningxia", or any AWS resource that must resolve to a specific China partition account. The skill explains which MCP endpoint maps to which account, how to pick when the user does not specify, and how to label cross-account results so the user can tell them apart.
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.