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...
design-update
by 95-agConservative, minimal-diff editing tool for already-compliant DESIGN.md files. Use this skill when the user wants to make a targeted edit to a design doc — adding or removing a token, updating a section, propagating a terminology change, fixing a cross-reference, or adding a new component section. Trigger on phrases like "add a section for X to DESIGN.md", "update the radius token", "rename a surface token", "fix the cross-reference to Foundations → Colors", "propagate the new term", "tighten this section", "add this token to the design doc", or any single-section or single-token edit. Do NOT use when the request touches more than two top-level sections, requires relocating content across sections, or implies a full structural overhaul — use design-rewrite for those.
design-rewrite
by 95-agHeavyweight structural transformation tool for DESIGN.md files. Use this skill when the user wants to rewrite, restructure, align, or normalize a design doc — including large-scale migrations, full compliance passes, hierarchy reorganizations, terminology unification, or section consolidations. Trigger on phrases like "rewrite DESIGN.md", "restructure DESIGN.md", "align DESIGN.md to the contract", "make DESIGN.md compliant", "normalize DESIGN.md structure", "full pass on DESIGN.md", "bring the design doc into compliance", "reorganize the hierarchy", "consolidate duplication", "migrate sections", or any request that touches more than two top-level sections or implies moving/renaming canonical sections. Do NOT use for targeted single-section edits, token additions, or cross-reference fixes — use design-update for those.
project-assets-generation
by 95-agFrom an approved portfolio MDX, derives the required asset list from content analysis (not from MDX slots), presents it for user approval, then generates each asset from a tracked source file using shared tooling, frames and crops per the framing and crop normalization principles, and places optimized exports in /public/projects/<slug>/ with editable sources retained in assets-source/. Always generates from source — never hand-edits production files directly. Use this skill after MDX is approved and the user says things like "generate the assets for <slug>", "make the diagrams for <slug>", "build the figures", "create the pipeline diagram", "generate the charts". Fire on any figure/diagram/chart request tied to a portfolio page even without the word "asset". Do NOT fire for hero cover generation (separate skill) or MDX content edits (separate skill).
project-content-extraction
by 95-agConverts a research project (PDF report + repo + user context) into a fresh, schema-aligned portfolio MDX page at content/projects/<slug>.mdx. Always rebuilds body content from scratch — never transforms a prior draft. Produces complete frontmatter + H2-spine body, density-reduced and ready for human approval before asset generation begins. Use this skill whenever the user starts a new portfolio project page, says things like "extract <project> into MDX", "build the case study for <slug>", "write up the <project>", "turn this paper/repo into a portfolio page", or supplies a PDF + repo + slug in any combination — even if they don't say "MDX" or "portfolio". Fire on any request that initiates the content phase of a project. Do NOT fire for asset generation (diagrams, charts), cover/hero work, or reviewing an existing page — those are separate sibling skills.
project-cover-generation
by 95-agBuilds the hero cover for a portfolio project page — a technically grounded SVG composition that encodes the project's core concept, approved in three sequential gates: direction proposals → base composition → optional annotations. Always produces a live React SVG component when theme-adaptive colors or handwritten annotations are needed; falls back to a static WebP/PNG only when no theme adaptation is required. Use this skill after project assets are approved and the user says things like "build the hero cover for <slug>", "make the cover", "design the hero", "generate the cover direction", "what should the cover look like", or "it needs a hero image". Fire on any cover or hero request tied to a project page even without the word "cover" — phrases like "make it look good on the card" or "give it a hero" imply this skill. Do NOT fire for content extraction (separate skill), asset generation (separate skill), or UI/page review (playwright-cli).
project-review
by 95-agRuns the two-pass content review on a completed portfolio MDX page — a cold technical-recruiter pass and a cold technical-hiring-manager pass, run as separate subagents with no shared context, followed by conflict surfacing and a prioritized fix list. Use this skill when the user says things like "review the content", "run the reviewers", "QA the page", "final review", "check the MDX", "does this read well", "is the content ready", or "review model-extraction-attacks". Fire whenever a portfolio project page is being evaluated for quality, credibility, or readiness — even if the user just says "look this over" while a project MDX is in scope. Do NOT fire for asset generation, cover generation, or page layout issues.
spec-write
by 95-agAuthors and maintains a project's non-design specification docs — the product doc (PRODUCT.md / PROJECT.md), the implementation-plan doc (IMPLEMENTATION-PLAN.md / build-flow / phases), the content/schema doc (CONTENT-SCHEMA.md), and similar prose docs. Use this skill whenever you are writing one of these docs from scratch OR editing, aligning, restyling, or restructuring an existing one — e.g. "write the PRODUCT doc", "add a section to PRODUCT.md", "align CONTENT-SCHEMA to the actual schema", "reword the implementation plan", "strip the section numbering from these docs", "split this wall of prose into bullets", "fix the cross-references between PRODUCT and CONTENT-SCHEMA", "make these docs machine-readable". Reach for it even when the user doesn't name the skill — any time the deliverable is the writing, format, or structure of a spec doc, this is the tool. Do NOT use it for DESIGN.md (use design-update / design-rewrite) or to brainstorm, invent requirements, or make product/design decisions — it shapes alre
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.