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...
business-panel
by trentjhnEvaluate a strategy, product, GTM, pricing, or business decision through a panel of named expert thinkers — each bound to a specific framework — run discuss → debate → Socratic → synthesize. Use when a decision benefits from competing mental models rather than a single critic. TRIGGERS: "business panel", "run a panel on this", "what would [Porter/Christensen/Taleb] say", "stress test this strategy", "multiple expert takes on", "/business-panel". Distinct from red-team (adversarial research on one thesis), premortem (one plan's 6-month failure modes), pitch-stress-test (argument structure of finished materials), compliance-stress-test (regulatory landscape). Adapted from SuperClaude's MODE_Business_Panel.
gsap
by trentjhnThis skill should be used when the user needs to implement web animations using the GSAP (GreenSock Animation Platform) JavaScript library. This includes creating tweens and timelines, scroll-based animations with ScrollTrigger, SVG drawing effects, morphing shapes, physics-based motion, text animations with SplitText, draggable interactions, and other interactive motion design. Use when working with GSAP-specific APIs, debugging GSAP animations, or when keywords like GSAP, ScrollTrigger, ScrollSmoother, SplitText, MorphSVG, Flip, or GreenSock appear.
architecture-viz
by trentjhnGenerate an interactive, navigable system-architecture diagram from a build idea or design.md, so you can SEE the architecture (not just read prose decisions) and click any component to its constraint-matrix + ADR. Use for pre-/cook brainstorming, /cook Phase 1.5–2 design review, or visualizing an existing build. Triggers: "visualize the architecture", "diagram this system", "/architecture-viz", "show me the architecture", "draw the system", "architecture diagram". Builds on LikeC4 (free, local, git-tracked, no Docker). Distinct from the Architecture Soundness Gate (text-only decision gate in system-design-fundamentals.md) — this is its VISUAL companion. Distinct from improve-codebase-architecture (refactors existing code) and dogfood (drives a running app).
improve-codebase-architecture
by trentjhnClean up and improve an existing codebase — first prune the dead matter (unused exports/files/deps, duplication) mechanically, then hunt for deepening opportunities that turn shallow modules into deep ones. Use when the user wants to make a codebase cleaner, more production-grade, more maintainable, remove dead/unused code, improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, reduce the bouncing-between-files tax, or make code more testable. Distinct from the design-time Architecture Soundness Gate (system-design-fundamentals.md — runs BEFORE code exists), deslop (cleans slop in the current branch DIFF, not the whole repo), and post-task-review's taste pass (reviews a single diff). This one walks code that already exists: clears what shouldn't be there, then deepens what survives.
premortem
by trentjhnRun a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed, routed to spec changes / CLAUDE.md constraints / waivers. MANDATORY TRIGGERS: 'premortem this', 'premortem my', 'run a premortem', 'what could kill this', 'future-proof this', 'stress test this plan', 'what am i missing here', 'find the blind spots'. STRONG TRIGGERS: 'what could go wrong', 'am i missing anything', 'poke holes in this', 'where will this break', 'devil's advocate this'. Do NOT trigger on simple feedback requests or factual questions. DO trigger when someone has a plan or commitment where the cost of being wrong is high. MANDATORY for SignalWorks engagements at Phase 1.6 (after spec confirmation, before harness design).
layers-interaction-flow
by trentjhnMaps interaction structure and flow — produces breadboard notation with edge cases, failure paths, and open decisions
blindspots
by trentjhnUse when discussing or shaping a BUILD IDEA — before it's specced or scaffolded — to surface the domain + systems-architecture gaps you can't see because they're outside your expertise. MANDATORY TRIGGERS: 'what am I missing', 'find the blind spots', 'blindspots', 'spot the gaps', 'make this build more complete', 'what am I not seeing'. STRONG TRIGGERS: 'thinking of making', 'I want to build', 'idea for a tool/app', 'help me think through this build', 'thoughts on this build'. Run it on a raw or half-formed build idea — the earlier the better. Distinct from premortem (a committed plan's 6-month failure modes — downstream), red-team (is the market thesis good), idea-validate (should it exist at all), business-panel (strategy frameworks), and the /cook Architecture Soundness Gate (structural gate at scaffold time — blindspots feeds it). This is the EARLIEST lens in the chain. Breaks the agreeable-assistant ceiling via fresh-context expert subagents, not inline persona role-play.
cinema-worldbuilder-pro-2-0
by trentjhnUniversal cinema worldbuilding director for Seedance video prompts with locked compositional rigor. Reads uploaded reference images for wardrobe, hair, makeup, identity, and environment, then composes production-ready Seedance prompts using a five-mode cinematography grammar (M1 Narrative, M2 Studio, M3 Action, M4 Performance, M5 Atmospheric) plus explicit Frame Map, Subject Lock, Movement, and Last Frame controls. Anchors subjects to screen positions, depth layers, contact points, and gaze so characters never drift, swap, or destabilize. Diegetic audio only — never music or lyrics. Use whenever the user wants a Seedance video prompt, mentions Seedance, asks for a cinematic scene breakdown, uploads references for a scene, describes a shot for video generation, or asks for music videos, action sequences, performance scenes, narrative shorts, fashion films, or atmospheric environment plates — even without saying 'cinematic' or naming a mode.
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.