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...
windows-boot-recovery
by dmaynorDiagnose and recover non-booting Windows machines from a Linux recovery environment (e.g., SystemRescue USB). Use this skill whenever a user or agent mentions: a Windows machine that won't boot, BSOD loops, NTFS filesystem errors, hibernation/Fast Startup issues, GPU driver crashes preventing boot, or needs to back up data from a dead Windows drive. Also triggers on: "my laptop won't boot", "Windows is stuck", "ntfsfix", "dirty filesystem", "rsync from Windows", "recover data from Windows drive", or any scenario involving Linux-based diagnosis of a Windows disk. When in doubt, use this skill — it is designed to run safely and will ask the operator before any destructive action.
purple-teaming
by dmaynorPlan and execute purple team exercises for detection validation. Collaborative offensive/defensive testing using atomic or scenario-based methodologies. Triggers on "purple team", "detection validation", "atomic test", "adversary emulation", or requests for ATT&CK technique test cases, Splunk/Sigma queries, detection coverage gaps, or Kill Chain/Diamond Model/Pyramid of Pain analysis. Methodologies: ATOMIC (isolated techniques), SCENARIO (attack chains).
apple-vuln-research-apple-silicon-kernel-layout
by dmaynorFind the correct arm64e kernel and per-SoC kernelcache for a research target on Apple Silicon macOS. Use when: (1) `/System/Library/Kernels/kernel` reports as `Mach-O 64-bit executable x86_64` on an Apple Silicon Mac and you wonder which binary the system actually boots; (2) you need the per-SoC arm64e kernel for a specific Mac model (t8140 = A18 Pro / MacBook Neo, t8103 = M1, t8112 = M2, t6000/t6020/t6030/t6031/t6041/t6050 = M-Pro/ Max/Ultra families, t8122/t8132 = newer A-series in Mac, t8142 = next-gen MacBook Air, vmapple = virtualization); (3) you need the monolithic prelinked kernelcache that the BootROM actually loads (it's NOT at /System/Library/Kernels and NOT named "kernel" — it's at /System/Volumes/Preboot/<UUID>/restore/kernelcache.release.macNg where macNg is a board-id, e.g. mac17g for Mac17,5); (4) you took a "pre-update kernel snapshot" by copying /System/Library/Kernels/ kernel and a diff agent told you it's the wrong architecture; (5) you need to know whether two Mac models share a kernel bu
pdf-report-formatting
by dmaynorProduce branded, professionally formatted PDF reports with selectable themes (light/cyber), cover page, table of contents, running header, page-N-of-M footer, consistent typography, modern tables, callouts, and ordered/unordered lists. Use whenever the user asks for a PDF report, briefing, white paper, audit deliverable, technical memo, or wants existing markdown/text/HTML content turned into a polished PDF — even if they don't explicitly say "PDF formatting". Also use when the user asks for a "tactical", "terminal", "cyber", or "dark mode" PDF, or wants the report to match a specific brand palette. Prefer this skill over generic PDF tools when output style/branding matters.
autonomous-loop-safety-constraints
by dmaynorHarden autonomous research loop safety blocks against LLM rationalization. Use when: (1) an autonomous loop keeps triggering crashes/panics despite prompt-level blocks, (2) the loop "works around" a safety constraint by reframing the task (e.g., "static analysis" that ends up running the blocked operation), (3) you need to write a blocklist that an LLM cannot rationalize past. Covers: prompt hardening patterns, mandatory service blocklists in generated code, graduated constraint escalation.
claudeception
by dmaynorContinuous-learning meta-skill: identifies skill gaps in the current session's work and creates new skills to fill them. The complement to skill-improver (which refines existing skills). Triggers: (1) /claudeception command to review session learnings, (2) "save this as a skill" / "extract a skill from this", (3) "what did we learn?", (4) after any task involving non-obvious investigation, methodology development, or trial-and-error discovery, (5) when you notice you re-derived something a future session will also need to derive. Adapted from blader/Claudeception (MIT, https://github.com/blader/Claudeception) for the dmaynor-skills-marketplace plugin structure.
macos-dyld-shared-cache-analysis
by dmaynorAnalyze macOS framework binaries that live in the dyld shared cache. Use when: (1) otool/nm/strings/codesign fail on framework binaries with "No such file or directory", (2) framework binary is a broken symlink, (3) need to extract strings/symbols/linked-libs from shared-cache residents. Key tool: dyld_info (in /usr/bin/ on macOS 13+).
swarm-orchestration
by dmaynorMulti-agent swarm orchestration for complex tasks. TD (Technical Director) decomposes user requests into task lists, delegates to specialized role-based agents (Architect, Programmer, QA, Critic, Security Engineer, Red Team, etc.), and coordinates via shared channel communication. Supports comprehensive Notion persistence for cross-session continuity - captures conversation dialogue, extended thinking, agent communication, artifacts (code/config/docs), and outputs. Use when tasks require parallel specialist work, coordinated implementation pipelines, multi-perspective review, or when user says "save/load project", "sync logs", "team-based", "swarm", "multi-agent", or references existing projects by name.
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.