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...
project-inventory
by nasrulhazimDiscovers and inventories all Claude Code and AI-integrated projects across specified directories. Scans for CLAUDE.md files, .claude/ directories, AI SDK imports, and MCP configurations, then generates structured reports in Markdown, JSON, and a self-contained HTML portfolio dashboard with AI collaboration metrics. Use this skill whenever the user asks to list all their Claude Code projects, discover AI-powered repos, audit which projects use Claude, generate a project inventory, build an AI portfolio dashboard, or export project data — including: "list semua project Claude Code", "scan for AI projects", "inventory my repos", "which projects use Claude", "export project list", "cari semua project yang guna AI", "senarai project Claude", "audit Claude Code usage", "buat dashboard AI", "generate AI portfolio", "show my AI stats".
livewire-flux
by nasrulhazimLivewire 4 + Flux UI component scaffolder and pattern guide for Laravel projects. Generates Livewire components using Flux UI primitives — forms, data tables, modals, notifications, file uploads with Spatie Media Library, and role-gated UI with Spatie Permission. Supports both full-class and Volt single-file components. Use this skill whenever the user asks to create a Livewire component, build a form, scaffold a data table, add a modal, wire up file uploads, or integrate Spatie packages with Livewire — including: "buat Livewire form untuk user", "create a data table component", "scaffold CRUD with Livewire", "tambah modal delete confirmation", "buat file upload guna Media Library", "wire up role-based UI", "tolong buat component pakai Flux", "generate Volt component", or "I need a Livewire page with filters and sorting". Also triggers when the user mentions Flux UI components, Livewire patterns, or asks about best practices for reactive Laravel UIs. Assumes Livewire 4 and Flux are already installed with dark
project-docs
by nasrulhazimFull SDLC documentation toolchain for software projects — pre-development through post-release. Scaffolds numbered folder structures, generates Product Specs via interview, creates versioned roadmaps (Markdown table + Mermaid Gantt + GitHub Milestones + phase-based), builds support clusters (FAQ, triage workflow, SLA, post-mortem, deprecation), validates documentation, generates health reports with SDLC coverage scoring, and creates release notes from git logs. Use this skill whenever the user asks to create, scaffold, validate, or health-check project documentation — including: "set up docs for my Laravel package", "write a product spec", "generate a roadmap", "create an FAQ", "write a post-mortem", "generate a release note", "check my docs health", "add badges", "scaffold a support runbook", or "deprecate my package". Compatible with the nasrulhazim/claude-docs Claude Code slash command.
project-roadmap
by nasrulhazimGenerates project roadmaps in Nasrul's exact style — always produces BOTH a ROADMAP.md (phase-based markdown with checkboxes, exit criteria, dependency map, and quick reference) AND a beautiful custom-styled HTML visual roadmap. Use this skill whenever the user asks for a roadmap, project plan, implementation plan, development phases, or says "buat roadmap", "plan for this project", "phase out the implementation", "apa first step", or "how should I build this". Also triggers when a CLAUDE.md exists and the user wants a matching roadmap, or when an existing roadmap needs updating based on new decisions. Always generates both files together — never just one. The HTML roadmap is styled uniquely per project type (not a generic template). Compatible with the nasrulhazim/claude-docs project structure.
sales-planner
by nasrulhazimProduct pricing, sales, quotation, marketing copy, and financial planning assistant for developers and solo founders. Use this skill whenever the user wants to figure out how to price their product or service, generate a quotation, calculate partner/reseller margins, plan revenue targets, write marketing copy or elevator pitches, or build a product pricing config. Triggers for requests like "how much should I charge", "help me price my SaaS", "generate a quotation for a government project", "what should my reseller margin be", "write a tagline for my product", "how many sales do I need to hit RM X", "build a pricing framework for my product", or "help me with my sales strategy". Works with or without an existing product-config.md — if none exists, interviews the user first to build one. Compatible with the nasrulhazim/claude-sales Claude Code slash command file structure.
ci-cd-pipeline
by nasrulhazimCI/CD pipeline builder for Laravel projects — extends Kickoff's existing GitHub Actions CI with continuous deployment pipelines (staging/production), Docker containerisation, secret management, and failure notifications. Generates Dockerfiles, docker-compose.yml, deployment configs for VPS via SSH, container registry push workflows, and leverages Kickoff's /bin scripts (deploy.sh, backup.sh, setup.sh) in automated workflows. Use this skill whenever the user asks to set up deployment pipelines, containerise a Laravel app, configure CD for staging or production, push Docker images to a registry, manage deployment secrets, add failure notifications to CI, or integrate /bin scripts with GitHub Actions. Triggers for requests like "set up CD pipeline", "deploy to staging automatically", "dockerise my Laravel app", "add Docker to my project", "push image to registry", "manage secrets in CI", "notify on failure", "extend CI with deployment", "setup deploy pipeline", "nak deploy guna GitHub Actions", "tambah Docker da
code-quality
by nasrulhazimPHP and Laravel code quality toolchain — static analysis with Larastan/PHPStan, code style enforcement with Pint, automated refactoring with Rector, baseline management for legacy codebases, and CI pipeline integration via GitHub Actions. Use this skill whenever the user asks to check code quality, fix linting errors, run static analysis, modernise PHP code, set up CI quality gates, manage PHPStan baselines, configure Pint presets, or apply Rector rules. Triggers for requests like "run quality check", "fix my code style", "analyse with larastan", "update phpstan baseline", "modernise my PHP code", "set up CI for quality", "check code quality", "pint tak jalan", "nak fix phpstan error", "setup rector", "betulkan code style", "tambah quality gate dalam CI", or "baseline phpstan untuk legacy code". Assumes Laravel Kickoff as the baseline — PHPStan, Pint, Rector, and GitHub Actions CI are already configured. This skill extends and customises that baseline.
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.