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...
game-audio
by harshavardhanbailur-kisshtComprehensive web game audio implementation covering Phaser 3 built-in audio, Howler.js, Tone.js, and Web Audio API. Use when building audio systems for web games, implementing sound effects, background music, audio sprites, spatial audio, or integrating audio libraries into Phaser/TypeScript/JavaScript games. Covers browser compatibility, mobile/iOS considerations, audio formats, performance optimization, and free sound resources. Achieves AAA-quality immersive experiences like Naruto Storm, Genshin Impact, Dragon Ball FighterZ.
game-audio
by harshavardhanbailur-kisshtComprehensive web game audio implementation covering Phaser 3 built-in audio, Howler.js, Tone.js, and Web Audio API. Use when building audio systems for web games, implementing sound effects, background music, audio sprites, spatial audio, or integrating audio libraries into Phaser/TypeScript/JavaScript games. Covers browser compatibility, mobile/iOS considerations, audio formats, performance optimization, and free sound resources. Achieves AAA-quality immersive experiences like Naruto Storm, Genshin Impact, Dragon Ball FighterZ.
ui-ux-mastery
by harshavardhanbailur-kisshtComprehensive UI/UX design system applying research-backed principles from Nielsen Norman Group, Baymard Institute, WCAG 2.2, cognitive psychology, and major design systems (Material Design 3, Apple HIG, Carbon, Atlassian, Fluent). Automatically triggers for: website design, landing pages, dashboards, forms, checkout flows, navigation, buttons, modals, cards, tables, mobile apps, accessibility, components, UI patterns, user interfaces, web applications, SaaS products, e-commerce, healthcare apps, enterprise software. Includes domain-specific prioritization matrices, conflict resolution frameworks, and evidence-based implementation patterns.
ui-ux-mastery-modular
by harshavardhanbailur-kisshtComprehensive UI/UX design system applying research-backed principles from Nielsen Norman Group, Baymard Institute, WCAG 2.2, cognitive psychology, and major design systems (Material Design 3, Apple HIG, Carbon, Atlassian, Fluent). Automatically triggers for: website design, landing pages, dashboards, forms, checkout flows, navigation, buttons, modals, cards, tables, mobile apps, accessibility, components, UI patterns, user interfaces, web applications, SaaS products, e-commerce, healthcare apps, enterprise software. Includes domain-specific prioritization matrices, conflict resolution frameworks, and evidence-based implementation patterns. Modular structure with deep-dive reference files for each domain.
deep-thinker
by harshavardhanbailur-kisshtPure thinking mode for Claude. ONLY THINKS - no execution. Maximum cognitive depth. Creates persistent knowledge base in .deep-think/ that survives context compaction. Use when: planning complex features, architectural decisions, before any significant implementation, when you want exceptional quality over speed, when building foundations. Triggers: "think deeply", "ultrathink", "architect this", "deep dive", "explore all scenarios", "plan thoroughly", "/think", "before we code", "analyze completely", "think through", "comprehensive analysis"
deep-thinker-v4
by harshavardhanbailur-kisshtDeep Thinker v4 — pure thinking mode. ONLY THINKS, no execution. Maximum cognitive depth. Creates persistent knowledge base in .deep-think/ that survives context compaction. Targets 6 specific failure modes: satisficing, memory loss, single-path exploration, confirmation bias, missed complexity, and executor-unfriendly output. Use when planning complex features, architectural decisions, before any significant implementation, when building foundations, or when explicitly asked to "think deeply", "ultrathink", "architect this", "deep dive", "plan thoroughly", "/think", "before we code", "analyze completely", "think through", or "comprehensive analysis". Sibling of the v1 deep-thinker skill — invoke this slug explicitly to test v4 behavior side-by-side.
deep-thinker
by harshavardhanbailur-kisshtPure thinking mode for Claude. ONLY THINKS - no execution. Maximum cognitive depth. Creates persistent knowledge base in .deep-think/ that survives context compaction. Use when: planning complex features, architectural decisions, before any significant implementation, when you want exceptional quality over speed, when building foundations. Triggers: "think deeply", "ultrathink", "architect this", "deep dive", "explore all scenarios", "plan thoroughly", "/think", "before we code", "analyze completely", "think through", "comprehensive analysis"
workflow-guardian
by harshavardhanbailur-kisshtPrevents Claude from breaking existing applications when adding features or modifying workflows. This skill enforces a mandatory 4-phase workflow: RECONNAISSANCE (System Map generation with optional sub-agents), IMPACT ANALYSIS (duplication and boundary detection), IMPLEMENTATION (with defensive guardrails), and VERIFICATION (touch-point validation). It is NOT a code quality tool — it exists to preserve working functionality when extending existing systems. USE THIS SKILL WHENEVER: - Adding features to an existing, working application (web apps, dashboards, internal tools) - Modifying workflows in running systems (React, Vue, Angular, Next.js, Svelte, etc.) - The user says "add X to my app" or "build Y on top of this codebase" - Touching more than 2 existing files in a production application - The codebase already has functioning routes, forms, dashboards, or data flows - Building on top of existing issue trackers, CRMs, dashboards, or authenticated systems - The user has reported "Claude broke my app" before
workflow-guardian
by harshavardhanbailur-kisshtPrevents Claude from breaking existing applications when adding features or modifying workflows. This skill enforces a mandatory 4-phase workflow: RECONNAISSANCE (System Map generation with optional sub-agents), IMPACT ANALYSIS (duplication and boundary detection), IMPLEMENTATION (with defensive guardrails), and VERIFICATION (touch-point validation). It is NOT a code quality tool — it exists to preserve working functionality when extending existing systems. USE THIS SKILL WHENEVER: - Adding features to an existing, working application (web apps, dashboards, internal tools) - Modifying workflows in running systems (React, Vue, Angular, Next.js, Svelte, etc.) - The user says "add X to my app" or "build Y on top of this codebase" - Touching more than 2 existing files in a production application - The codebase already has functioning routes, forms, dashboards, or data flows - Building on top of existing issue trackers, CRMs, dashboards, or authenticated systems - The user has reported "Claude broke my app" before
claude-code-best-practices
by harshavardhanbailur-kisshtComprehensive Claude Code best practices covering architecture patterns, CLAUDE.md configuration, context window management, sub-agent orchestration, skills design, hooks system, MCP servers, permissions, cost optimization, and anti-patterns. Use this skill PROACTIVELY whenever setting up a Claude Code project, creating CLAUDE.md files, designing skills or agents, configuring hooks or MCP servers, optimizing context window usage, debugging Claude Code behavior, or reviewing Claude Code configuration. Also trigger when users mention Claude Code architecture, agent teams, worktrees, permissions, sandbox, progressive disclosure, or development workflows like RPI or plan-then-execute.
kissht-release-notes-mastery
by harshavardhanbailur-kisshtComprehensive release notes generation, stakeholder-specific user guide creation, and Jira automation system for Kissht/Ring fintech products (LAP LOS, UP/Ring, Saral LSQ). Transforms raw Jira ticket data into tailored, AI-generated documentation for Product Managers, QA Engineers, Developers, Training Teams, Business Analysts, Operations, and Leadership. USE THIS SKILL WHEN the user mentions: release notes, release documentation, stakeholder guides, user guides from Jira, Kissht releases, LAP release notes, Ring release notes, ticket summaries, sprint documentation, changelog generation, release communication, training materials from releases, QA test impact notes, developer changelog, BA impact analysis, operations runbook from releases, Jira-to-documentation pipeline, automated release notes, release announcements, or when they want to generate any form of documentation from completed Jira tickets for different team roles. Also trigger when: building release note web apps, automating Jira webhook-to-docs
flutter-master
by harshavardhanbailur-kisshtThe definitive Flutter mobile app development skill for building production-grade, high-performance Flutter applications. USE THIS SKILL whenever the user mentions Flutter, Dart mobile development, cross-platform mobile apps, or any of these specific topics: Flutter animations (implicit, explicit, physics-based, Rive, Lottie, Hero transitions, CustomPainter, staggered), Flutter performance optimization (widget rebuilds, Impeller, frame budget, jank, isolates, memory leaks, app size), Flutter state management (Riverpod 3.0 (stable), BLoC 9.0+, Provider, Signals, Clean Architecture), Flutter debugging (DevTools, performance profiling, memory leaks, shader warmup), Flutter architecture (Clean Architecture, repository pattern, dependency injection, folder structure), Flutter testing (unit, widget, integration, golden tests, mocking, TDD), Flutter CI/CD (Fastlane, Codemagic, GitHub Actions, flavors, store deployment), Flutter UI (Material Design 3, Cupertino, responsive design, accessibility, i18n, dynamic theming
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.