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...
copy-macro
by ZenUmlE2E test for Confluence's "Make a copy" page action against pages that contain ZenUML macros (sequence, graph/DrawIO, OpenAPI). Verifies that after copy-then-edit, the macro on the new page correctly references a custom content owned by the new page — not the source page's customContent. Drives the test via Playwright MCP and the Confluence REST v2 API. Non-destructive: never purges custom content, only inspects state. Use when the user says "copy macro test", "test page copy", "verify cross-page-copy fix", "run the copy e2e", or whenever they want to validate the cross-page macro writeback behavior (PR #124 / ZEN-1170) on any Forge site.
diagramly-admin
by ZenUmlNavigate to the Diagramly admin panel on a Confluence site and interact with admin features (enroll space for demo page, etc.). Triggers on "diagramly admin", "enroll space", "create demo page admin".
download-attachment
by ZenUmlDownload a Confluence page attachment to local disk. First explains the 5 ways an attachment can be downloaded (so the developer learns the trade-offs), then automates the easiest one. Use when investigating customer issues that require the original PNG/PDF/file backed up against a customContent, recovering source from PNG iTXt embedded metadata, or any time a Confluence attachment needs to land on disk. Triggers on "download the attachment", "get the PNG", "save attachment to disk", "extract iTXt", "pull attachment", or any follow-up step after `find-macros-on-page` reveals a backup attachment.
graph-macro
by ZenUmlDrive the ZenUML Graph (DrawIO) macro through any entry point — slash-menu insert, in-editor Edit, copy-then-edit fallback, or view-mode Edit — and into the inner DrawIO editor to append a timestamp shape and Publish. Classifies the save outcome as success or did-not-persist, and records whether the paywall was observed. Use whenever you need to verify a Graph macro insert / edit / save end-to-end via Playwright MCP without re-deriving the Forge → DrawIO iframe chain. Triggers on "insert graph macro", "edit graph macro", "publish graph", "spot check drawio publish", "test graph save", "verify graph publish on lite", or any ad-hoc Graph-macro MCP spot check on lite-stg / full-stg / dia-stg / zenuml-stg / prod.
pvt-drawio
by ZenUmlFocused production validation for the Graph (DrawIO) macro: nested Forge + DrawIO iframes, title field, at least one shape on the canvas (required — avoids false PASS on empty diagrams), Publish from inner editor, and verified rendered geometry on the Confluence page. Invoked by release-app Step 5.5 when graph/drawio-related commits are detected. Triggers on "pvt-drawio", "test drawio", "validate graph macro".
pvt-edit
by ZenUmlFocused production validation for the macro edit path (Forge custom UI modal, editor mount, Publish). Confirms opening Edit from the viewer loads the editor iframe and can publish or cancel without blank states. Invoked by release-app Step 5.5 when editor-related commits are detected. Triggers on "pvt-edit", "test macro edit", "validate editor", "pvt-editor".
pvt-fullscreen
by ZenUmlFocused production validation for macro fullscreen / expanded viewer (Forge fullscreen modal bridge). Opens fullscreen from the viewer toolbar, verifies the diagram remains usable, then exits cleanly. Invoked by release-app Step 5.5 when fullscreen-related commits are detected. Triggers on "pvt-fullscreen", "test fullscreen", "validate fullscreen viewer".
pvt-paywall-banner
by ZenUmlFocused production validation for the paywall WARNING page-banner (Lite, 85–99 macro band) on the single `zenuml-page-banner` Forge pageBanner host. Covers render + count, both CTAs (Copy admin message, Request extension), dismiss/7-day snooze, the critical-band (100+) no-banner boundary, the below-band (<85) no-banner case, and single-host priority (paywall outranks CSAT). Checks Mixpanel events (paywall_banner_shown, paywall_banner_dismissed, advocacy_message_copied, extension_request_clicked — all surface=page_banner). This is the full granular matrix; CI keeps only a slim 3-test subset in tests/e2e-tests/tests/insert/paywall-page-banner.spec.ts. For the paywall MODAL (100+ hard gate) use pvt-paywall instead. Triggers on "pvt-paywall-banner", "test paywall banner", "validate warning banner".
pvt
by ZenUmlProduction Validation Testing (PVT) — quick sanity check immediately after a release. Runs Mermaid only on production to confirm the app is live and the new version is rendering. Not a full smoke test — CI already handles that. Use after /release-app completes. Triggers on "pvt", "production validation", "validate release", "validate production".
rendering-perf
by ZenUmlRendering performance analysis for ZenUML macros. Queries Mixpanel macro_viewed duration_ms percentiles by macro type, compares against baseline, and guides investigation of regressions or improvements. Usage: /rendering-perf Triggers on "rendering performance", "how fast do macros render", "p50 p90 p99", "duration_ms baseline", "render time regression".
repro
by ZenUmlReproduce a bug in the conf-app. Extract the bug from the current conversation or user prompt, then try to reproduce it in the simplest available environment. Use when the user says "repro", "reproduce", "can you repro this", "reproduce the bug", "verify this bug", or describes a bug they want confirmed. Try environments in strict order: local dev server first, then conf-stg-lite.zenuml.com, then conf-lite.zenuml.com, then real Confluence as last resort.
smoke-test
by ZenUml[on <site>] [lite|full|diagramly] [macros...] Sites: zenuml-stg (default), zenuml, lite-stg, full-stg, dia-stg, diagramly. Smoke test ZenUML Confluence Cloud macros (ZenUML, PlantUML, Mermaid, Graph/DrawIO, OpenAPI). Uses the Playwright MCP to create a test page, insert macros, publish, and verify rendering. Triggers on "smoke test confluence", "test macros on staging", "verify ZenUML on confluence", "run smoke test on zenuml-stg", "test lite macros", or any macro validation request.
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.