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...
onyx
by PetrCalaOnyx state management patterns — useOnyx hook, action files, optimistic updates, collections, and offline-first architecture. Use when working with Onyx connections, writing action files, debugging state, or implementing API calls with optimistic data.
regenerate-app-icons
by PetrCalaRegenerate every Kiroku app icon, boot splash, notification icon, in-app SVG, and web favicon from the master SVG using the single-source generation script. Use this skill whenever the user wants to update the app logo, replace the master art, change the badge colors or labels on variant icons (DEV / STG / ADHOC), add a new build variant's icon set, tweak which sizes get generated, or otherwise refresh the visual brand on iOS / Android / web. Trigger even when the user phrases it indirectly — e.g. "update the icon", "swap the logo", "change the staging badge", "make the dev icon orange", "I need new app store assets", "rerun the icon thing". This is the project's only sanctioned way to touch icon assets; do not hand-edit `*.appiconset/`, `mipmap-*/`, or `drawable-*/` files.
coding-standards
by PetrCalaProvides coding standards for React Native — performance patterns, consistency rules, and clean React architecture. Use when writing, modifying, or reviewing code.
frame-app-store-screenshots
by PetrCalaTurn raw Kiroku app captures into App Store-ready marketing screenshots — real screenshot composited onto a branded gradient background with a caption, rendered at the exact pixel sizes App Store Connect requires (6.9" 1320×2868, 6.7" 1290×2796), per locale. Use whenever the user wants App Store screenshots, store images, marketing screenshots, "the images users see on the App Store", framed/captioned screenshots, to re-generate or restyle store screenshots, change a caption, add a locale, or change the screenshot background/theme. Trigger on indirect phrasing too — "make the store screenshots", "frame my screenshots", "App Store images", "screenshot captions", "regenerate the store shots". This is the sanctioned, deterministic way to produce store screenshots without the full fastlane snapshot pipeline; do not hand-edit the framed PNGs.
translate
by PetrCalaTranslate Kiroku UI strings into supported non-English locales using each language's curated glossary/style guide. Use whenever translation files (src/languages/*.ts) need new keys filled in, missing translations backfilled, or an existing language re-harmonized for consistency. Trigger on phrasing like "translate the new strings", "add Czech translations", "fill missing translations", "fix translation inconsistencies", or "audit the cs_cz file".
asc
by PetrCalaInspect App Store Connect state, lint the iOS store listing, and submit an app version for review for Kiroku via the zero-dependency scripts/asc.mjs CLI (App Store Connect API). Use whenever the user wants to check App Store / ASC status (version, build, subscription states, review submissions), submit or resubmit the iOS build for review, verify the store listing before submitting, confirm subscriptions are parked, or work through an App Store rejection. Trigger on phrasing like "submit the build", "what's my App Store status", "is the build ready to submit", "check ASC", "resubmit to App Review", "scrub the store listing", "did the subscriptions get attached", "why was the app rejected". Encodes the gotchas of Apple's review-submission model.
release-notes
by PetrCalaGenerate store-facing "What's New" release notes for Kiroku by comparing the last publicly shipped version on each store (App Store / Google Play) against current master. Use whenever the user wants release notes, what's-new text, a store changelog, copy for promoting a build to public release, or a user-facing summary of what changed since some version, for either or both platforms. Trigger even on loose phrasing like "we're pushing to the Play Store, write the notes" or "what's new since 0.3.13?". Not for the automated CI TestFlight changelog (scripts/generateReleaseNotes.sh owns that).
ios-signing
by PetrCalaDiagnose and fix expired iOS code-signing assets for Kiroku via the zero-dependency scripts/ios-signing.mjs CLI (App Store Connect API). Use whenever the staging/production or test-build deploy fails on the iOS "Run Fastlane" step with signing errors ("No certificate for team ... matching 'Apple Distribution'", "Provisioning profile 'Kiroku' expired", "Code Signing Error"), or whenever the user wants to renew/regenerate the iOS distribution certificate or the Kiroku / Kiroku_AdHoc provisioning profiles, check how soon they expire, or re-encrypt the committed ios/*.gpg signing assets. Trigger on phrasing like "the iOS deploy is failing on signing", "the provisioning profile expired", "renew the certificates", "regenerate the signing assets", "are the iOS certs about to expire".
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.