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...
implement
by hugorodgerbrownTake a scoped Linear ticket from Ready-for-dev through to an open PR in one flow: create the branch, plan, wait for plan approval, implement + review, push, and open the PR. Use when the user says "implement SNOW-NN", "implement this", "go on SNOW-NN", or just "implement" / "go" / "continue" when a feature branch is already checked out. Do NOT use for: scoping a ticket (`scope` skill), ad-hoc edits unrelated to a ticket, or any message without either a SNOW-NN reference or an existing SNOW-NN branch checked out.
linear-ticket-author
by hugorodgerbrownUse when creating a new Linear ticket, updating an existing ticket's description, or posting a scoping comment on a ticket. Covers the scoping comment contract, ticket decomposition rules (one ticket per independently-shippable unit), MCP parameter gotchas (priority/estimate enums, state name matching, `blocks` relationship quirk), and the rule that only a clean scoping comment promotes a ticket to `Ready for dev`. Do NOT use when implementing a ticket that's already scoped — use linear-ticket-implementer for that.
linear-ticket-implementer
by hugorodgerbrownUse when picking up a scoped Linear ticket to implement it — i.e. the user says "implement SNOW-xxx" or equivalent. Covers the pickup sequence (fetch issue + comments, verify scoping comment exists, stop if missing), branch naming, the MCP move to In Progress (no push yet), PR title/body format including the `Closes SNOW-xxx` magic string, and when to stop and ask rather than push through. Do NOT use when creating or scoping a ticket — use linear-ticket-author for that.
project-update
by hugorodgerbrownDraft and post a Linear project status update. Use when the user asks for a daily, weekly, or on-demand project update — e.g. "post a daily update for <project>", "project update for Snowdesk", "status update on <project>". Gathers everything shipped since the last update, groups it by theme, lists newly-logged tickets, surfaces what's still open for the next milestone, and posts via the Linear MCP `save_status_update` tool. Also used by an autonomous Routine for daily updates — when invoked with `routine` (or `daily` / `--no-approval`) in the args, runs end-to-end without an approval gate.
scope
by hugorodgerbrownScope a Linear ticket: read the description, explore the codebase, produce a written scope, post it as a Linear comment, and transition the ticket from Todo to Ready for dev. Use when the user asks to "scope SNOW-NN", "let's scope SNOW-NN", "work out SNOW-NN", "spec SNOW-NN", or any phrasing where they want a Linear ticket turned from a sentence into a proper scope. Do NOT use for: starting work on an already-scoped ticket, asking questions about a ticket without producing a scope, or any message that doesn't explicitly reference a SNOW-NN identifier.
audit
by hugorodgerbrownRun a security audit scoped to Snowdesk by invoking the security-auditor agent with the project's specific threat surface pre-loaded (SLF CAAML ingest, Resend email, subscription tokens, HTMX partials, Django settings) — no need to describe the stack each time. Use whenever the user asks for a security audit, vulnerability scan, CVE or dependency check, secrets scan, pentest, or pre-deploy security review of this project — "/audit", "audit the project", "check for vulnerabilities", "run a security scan". Accepts a scope argument: "deps" for a dependency CVE scan only, or a path to limit the audit to one module. Do NOT use for reviewing the pending changes on a single branch or diff — that is the `security-review` skill.
ticket-authoring-guide
by hugorodgerbrownUse when creating a new Linear ticket, updating an existing ticket's description, or posting a scoping comment on a ticket. Covers the scoping comment contract, ticket decomposition rules (one ticket per independently-shippable unit), MCP parameter gotchas (priority/estimate enums, state name matching, `blocks` relationship quirk), and the rule that only a clean scoping comment promotes a ticket to `Ready for dev`. Do NOT use when implementing a ticket that's already scoped — use ticket-implementation-guide for that.
work-on
by hugorodgerbrownWork a Linear ticket end-to-end in a single session: scope it (if it still needs scoping) and then immediately implement it through to an open PR — Todo → Ready for dev → In Progress → In Review, with both approval gates intact. The ticket may be referenced as a bare number — every ticket in this project is SNOW-prefixed, so "work on 295" means SNOW-295. Use when the user says "work on SNOW-NN", "work on NN", "take NN through to review", "scope and implement NN", "do SNOW-NN end to end", or any phrasing that asks for both scoping and implementation of one ticket in one go. Do NOT use for: scoping only (`scope` skill), implementing an already-scoped ticket when the user only asks to implement (`implement` skill), resuming work on an existing branch, or any message without a ticket reference.
ticket-implementation-guide
by hugorodgerbrownUse when picking up a scoped Linear ticket to implement it — i.e. the user says "implement SNOW-xxx" or equivalent. Covers the pickup sequence (fetch issue + comments, verify scoping comment exists, stop if missing), branch naming, the MCP move to In Progress (no push yet), PR title/body format including the `Closes SNOW-xxx` magic string, and when to stop and ask rather than push through. Do NOT use when creating or scoping a ticket — use ticket-authoring-guide for that.
post-project-update
by hugorodgerbrownDraft and post a Linear project status update. Use when the user asks for a daily, weekly, or on-demand project update — e.g. "post a daily update for <project>", "project update for Snowdesk", "status update on <project>". Gathers everything shipped since the last update, groups it by theme, lists newly-logged tickets, surfaces what's still open for the next milestone, and posts via the Linear MCP `save_status_update` tool. Also used by an autonomous Routine for daily updates — when invoked with `routine` (or `daily` / `--no-approval`) in the args, runs end-to-end without an approval gate.
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.