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...
lidr-user-stories
by LIDR-IT🤖 AUTOMATED User Story generation with intelligent RF slicing using 8 proven slicing patterns and INVEST validation. Domain-agnostic — works for any software system, platform, or project methodology. Use for transforming RFs into sprint-ready backlog with capacity management and dependency detection. Essential after Gate 2: converts validated requirements into implementable user stories for Sprint Planning. Always use when RFs are approved and Sprint Planning begins, always use when transforming requirements into actionable development tasks. Do NOT use for requirements generation (use lidr-requirements per-rf mode), for epic decomposition (use bmad-create-epics-and-stories), or for test case creation (use create-test-cases). Triggers on "automated user stories", "RF slicing", "sprint backlog generation", "INVEST validation", "story capacity planning", "requirements to stories". Content authored in English; artifact language follows the client `language` setting (see `_shared/lidr/integrations/`). BDD scenari
lidr-validate-requirements
by LIDR-IT"🤖 AUTOMATED cross-validation of functional (RFs) and non-functional (NFRs) requirements against PRDs using Python automation scripts. Executes 5-pass validation in <5 minutes vs 6+ hours manual. Auto-generates RTM, gap reports with owner assignment, and implementation clusters. Automation-first with manual fallback. Triggers on "validate requirements", "requirements automation", "RTM generation", "5-pass validation", "Gate 2 readiness", "requirements traceability". Essential for Gate 2 evaluation. Use after generate-rf AND generate-nfr. ROI: 150+ hours/year saved. ALWAYS use before Sprint Planning to ensure requirements are complete and testable."
lidr-postmortem
by LIDR-ITStructure a blameless incident postmortem using Five Whys root cause analysis, detailed timeline, and systemic corrective actions. Domain-agnostic - works for any system or service type. Mandatory for S1/S2 production incidents; recommended for S3 with customer impact, near-misses, and executed rollbacks. Deadline: draft in 24h, review in 48h, publish in 72h. Triggers on create postmortem, incident analysis, what happened in production, root cause analysis, five whys, incident report. Culture: blameless — analyze SYSTEMS, don't blame PEOPLE. Output: English by default; artifact language follows the client `language` setting (see `_shared/lidr/integrations/`). ALWAYS use after production incidents to identify root causes and prevent recurrence.
lidr-agents-architecture
by LIDR-ITThis skill should be used when the user wants to author any piece of the .agents/ ecosystem — "create a skill", "create a subagent", "add a command to .agents/", "create a slash command", "create a hook", "PreToolUse"/"PostToolUse"/"SessionStart" automation, "add an MCP server", "integrate MCP", "create a behavioral rule", "generate rule" — or needs guidance on the .agents/ source-of-truth system, choosing the right component type, or how creation propagates with automatic synchronization across all platforms (Cursor, Claude Code, Gemini CLI, Antigravity, GitHub Copilot/VSCode). Umbrella meta-skill folding command, hook, MCP, and rule authoring (see references/).
lidr-audit-standards
by LIDR-ITECOSYSTEM-SCOPE WRAPPER complementing `bmad-review-adversarial-general` (which reviews content quality). This audits the `.agents/` ecosystem STRUCTURE itself: frontmatter consistency, domain-agnostic content, methodology uniformity, staleness detection, path correctness, drift between sources of truth. Use for periodic ecosystem health checks, not content reviews. Triggers on 'audit skills', 'audit ecosystem', 'audit rules', 'audit docs', 'validate standards', 'compliance check', 'frontmatter audit', 'staleness check'.
lidr-automated-handoffs
by LIDR-ITAutomatically generate phase transition handoffs (Dev→QA, QA→Security, Security→DevOps). ALWAYS use when advancing gates to ensure zero information loss between phases.
lidr-business-case
by LIDR-ITGenerate a Business Case document from a business problem or initiative request. Use for any budget justification, project approval, or ROI analysis needs. Essential when requesting resources, teams, or timeline extensions. Trigger for strategic initiatives, cost-benefit analysis, or investment decisions. Use when receiving a new project request from Business, CTO, or R&D; when justifying budget, team, or timeline to a sponsor; when Gate 0 (Intake) requires a BC before proceeding. Triggers on phrases like "create business case", "justify this project", "new initiative", "we need approval for", "Gate 0 preparation", "budget request", "resource allocation", "investment proposal". Output: English by default; artifact language follows the client `language` setting (see `_shared/lidr/integrations/`). Audience: executive (Sponsor, CTO, PME). ALWAYS use at project initiation to justify investment and secure stakeholder approval.
lidr-change-request
by LIDR-ITGenerate a Change Request for production deployment following ITIL Change Management (Standard/Normal/Emergency). Domain-agnostic - works for any application type and infrastructure. Essential for any production deployment - no exceptions. Always use before going live, regardless of change size. Required for all releases, infrastructure changes, and configuration updates. Requires QA Sign-off (Gate 5), Security Sign-off (Gate 6), and Rollback Plan as prerequisites. Triggers on "create change request", "prepare deployment", "request production deploy", "CAB approval", "change management". Output: English by default; artifact language follows the client `language` setting (see `_shared/lidr/integrations/`).
lidr-commit-management
by LIDR-ITThis skill should be used when the user asks about "commit best practices", "fix commit", "amend commit", "commit message guidelines", "conventional commits", "rewrite commits", "commit history", or needs help managing git commits following project standards.
lidr-create-test-cases
by LIDR-ITGenerate executable BDD test cases with concrete data from tickets in "Ready for QA". Domain-agnostic — works for any software system, platform, or application type. Use for QA preparation, test coverage analysis, and BDD scenario expansion into detailed test cases. Essential for test execution planning when transitioning tickets to QA. Always use before test execution, always use when tickets move to "Ready for QA" status. Do NOT use for requirements generation (use lidr-requirements per-rf mode), for test planning strategy (use bmad-testarch-test-design), or for bug reporting (use lidr-bug-report). Triggers on "create test cases", "generate TCs", "write test cases", "BDD test cases", "prepare test execution", "Ready for QA test cases". Content authored in English (Gherkin); artifact language follows the client `language` setting (see `_shared/lidr/integrations/`). CSV-ready for the bound {{TEST_MGMT_TOOL}} import. Audience: QA (executes tests), Dev (understands test scope), QA Lead (validates coverage).
lidr-dast-interpretation
by LIDR-ITInterpret DAST (Dynamic Application Security Testing) scan reports from OWASP ZAP, Burp Suite, or Nuclei against running applications. Unlike SAST, DAST tests the app at runtime (black-box) finding configuration issues, missing headers, CORS problems, and runtime vulnerabilities. Use for any dynamic security testing or runtime vulnerability assessment. Essential for production security validation and compliance reporting. Always use before releases and after infrastructure changes. Use pre-release before Gate 6 against staging, post-deployment for production smoke, after infrastructure changes, or when new public endpoints are added. Triggers on 'interpret DAST results', 'ZAP scan report', 'Burp scan', 'security headers check', 'DAST findings', 'runtime security scan'.
lidr-gate-evaluation
by LIDR-ITGenerate standardized gate evaluation reports for SDLC phase transitions. Tool-agnostic - works across all project tracking systems and methodologies. Use for formal gate assessments, handoff package generation, compliance scoring. Essential for maintaining SDLC governance and ensuring phase-gate quality standards. Always use when transitioning between SDLC phases, always use for gate pass/fail decisions. Do NOT use for individual task evaluation or informal progress checks. Triggers on "gate evaluation", "phase transition", "gate assessment", "handoff package". Output: English by default; artifact language follows the client `language` setting (see `_shared/lidr/integrations/`). Audience: PME (conducts evaluations), PO/TL (receives results), QA/Security (provides sign-offs).
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.