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...
avoid-vibe-slop
by e6quProject-local checklist that loads before any non-trivial code change in blerp. Refuses fake/fallback/anemic patterns, fake tests, fake implementations, dead-attempt code paths. Use proactively whenever about to write or modify TypeScript/TSX, modify an API controller, add a test, stage a fix, or touch the dashboard. Pairs with hidden-rot-audit, frontend-slop-check, clerk-monite-fidelity.
clerk-monite-fidelity
by e6quVerify a blerp change against its real reference SDK — Clerk (auth/users/orgs/sessions/JWT) or Monite (entities/payables/receivables). Use whenever editing API controllers under apps/api/src/v1/, routes, SDK packages under packages/{backend,nextjs,shared,api}, or dashboard components that imitate Clerk/Monite UI. Catches drift between what we ship and what the real SDKs do.
context-recovery
by e6quRebuild project state after context compaction, fresh session, or model handoff. Use immediately when the conversation has just compacted, when you're picking up an in-flight task without recent history, or when the user says "continue" / "resume" / "what were we doing." Fights the amnesia that silently rewrites prior decisions. Pairs with avoid-vibe-slop and hidden-rot-audit.
design-system-check
by e6quEnforce blerp dashboard design tokens, color/contrast/typography/spacing/radius/elevation rules, and WCAG AA accessibility for every UI change. Use whenever editing Tailwind classes, defining a new visual variant, picking a color, choosing a font size or weight, adding spacing, or designing focus states. Pairs with frontend-slop-check and ui-verification.
frontend-slop-check
by e6quKill generic AI-aesthetic UI before it lands. Use before/after writing or modifying any React component in apps/dashboard/src — pages, modals, forms, dashboards, tables, empty states, error states. Detects the centered-hero / purple-gradient / 3-column / 4-card / "linear-gradient-from-purple-to-blue" cliché, emoji-as-icon habit, generic placeholder copy, and the "comprehensive but functionally empty" component. Pairs with design-system-check, ui-verification.
hidden-rot-audit
by e6quProactive audit for dead code, fake tests, fake implementations, broken/unreachable UI, abandoned past attempts, and silent failures in blerp. Use before starting work in a directory you don't actively own, after context compaction, when a feature "should work but doesn't", before any milestone close-out, and as a periodic sweep. This repo has had minimal hands-on testing — rot accumulates faster than CI catches.
ui-verification
by e6quVerify the dashboard UI in a real browser with real data before claiming a feature works. Use after writing/modifying any React component, route, modal, form, or page. Combines Playwright (apps/dashboard/tests/), Storybook smoke (port 6006), Vitest browser-mode Storybook tests, and manual screenshot-grade verification. Pairs with frontend-slop-check and design-system-check.
adaptor-fidelity-check
by e6quVerify a sockerless component change against its real reference adaptor (docker CLI / aws CLI / gcloud / az / Terraform / gh CLI / Docker SDK). Use whenever editing files under backends/, simulators/, bleephub/, or anything that other tools speak to over the wire. Catches drift between what we implement and what real adaptors send.
avoid-vibe-slop
by e6quProject-local checklist that loads before any non-trivial code change in sockerless. Anchored in docs/VIBE_CODING.md; refuses fake/fallback/anemic patterns. Use proactively whenever about to write Go or TypeScript code, modify a handler, add a test, or stage a fix.
backpedal-pattern-audit
by e6quMeta-skill that surfaces patterns from BUGS.md "Resolved history" where the same shape was filed and fixed N times across M phases. Each repeat group is a candidate for a new specialist skill or a class-of-bug rule. Run periodically (every ~10 PRs or before starting a major phase) or when the user asks "what blind spots do we have." Distilled from the observation that BUGS 1016/1017/1018/1019/1025/1033 (silent-error swallow) and BUGS 1020/1021/1022/1024/1034 (dead-code silencer) recurred so often they justified dedicated `silent-error-swallow-scan` and `dead-code-silencer-scan` skills.
cross-resource-stack-test
by e6quCodify the production-shape end-to-end test pattern from Phase 159's TestStackProductionShape. Use when adding cross-resource sim features (e.g., new resource A references resource B's ARN/domain/ID) or when authoring a new sim's apply_test.go from scratch. Asserts what references RESOLVE TO, not just that apply doesn't crash.
dead-code-silencer-scan
by e6quSpecialist scan for the dead-code-silencer pattern — `var _ = pkg.Fn` import silencers, `//nolint:unused` directives without consumer references, and `_ = someVar` "keep for later" pins. Distilled from BUGS 1020 / 1021 / 1022 / 1024 / 1034 — five bug IDs across the same shape, where code was held for hypothetical future use and the silencer became the load-bearing artifact. Use before merging any Go change and periodically across the codebase.
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.