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...
ui-design
by abbayeINTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes after editing *.xaml under WpfHexEditor.App/, Editors/, Controls/, Plugins/, Core/ to enforce the design-system: no hardcoded colors (use {DynamicResource Dock* / HexEditor_* / Panel_*}), no unknown tokens, canonical spacing scale, canonical FontSize ladder, glyph-only interactive elements need ToolTip, no template reinvention. Skip on: Themes/*.xaml (themes ARE the palette), ColorPicker (legitimate color literals), generated *.g.cs.
leak-guard
by abbayeINTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes after editing C# files that touch IDisposable, events, FileStream, Process, Timer, or files under Services/, *Manager.cs, *Service.cs, *Watcher*, *Adapter.cs. Detects: event handlers added without unsubscribe, IDisposable without Dispose, missing GC.SuppressFinalize, FileStream without using, Timer not stopped, Process not disposed, static event collections, weak-event candidates, hardcoded secrets. Skip on: Tests/, Samples/, *.Designer.cs, *.g.cs, generated code.
loc-guard
by abbayeINTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes on two scopes: (1) PARITY — after editing any *.resx (base or satellite), verifies the 28-language satellite parity (missing/orphan keys, placeholder drift, untranslated). (2) SOURCE — after editing *.xaml or *.cs under App/, Editors/, Plugins/, Core/, Controls/, advisory checks for: DynamicResource on loc keys (must be StaticResource), hardcoded user-visible string literals, IdeMessageBox.Show literals, legacy MessageBox.Show usage (ADR-009), and missing LocalizedResourceDictionary wiring (ADR-005). All SOURCE findings are warn-only. Distinct from xaml-guard (which only checks Designer.cs parity for the base resx). Skip on: Themes/, ColorPicker, Designer.cs/g.cs, Tests/, Samples/, pure structural XAML edits.
xaml-guard
by abbayeINTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes after editing any *.xaml, *.resx, or *Resources.Designer.cs file to detect regressions in the high-incident XAML/resx/loc domain (hardcoded user-strings, XAML patcher corruption, resx malformed, key drift, HexEditor Resources alias, MessageBox in code-behind, ContextMenu transparency, DockPanel-row alignment). Skip on: pure structural attribute edits (Grid.Row, Margin, Width).
nuget-guard
by abbayeINTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes after editing any *.cs or *.csproj that belongs to one of the 13 packages published on nuget.org by abbaye (WpfHexEditor.Core.ByteProvider, .BinaryAnalysis, WPFHexaEditor, WpfCodeEditor, WpfDocking, WpfColorPicker, WpfTerminal, whfmt.Analysis/.Backfill/.CodeGen/.Fuzz/.Validate/.FileFormatCatalog). Protects the standalone-mode contract when IDE features are added: detects IDE-only references leaking into a NuGet package, TFM drift, UseWPF leak on core-xplat packages, WPF/WinForms usings in core-xplat, and public-API regressions vs git HEAD (api-removed, api-renamed). Extending the API is always allowed; removing/renaming is not. Skip on files outside protected packages, Tests/, Samples/, *.Designer.cs, *.g.cs.
code-analysis
by abbayeINTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes this skill BEFORE any non-trivial edit AND AFTER multi-file changes, to enforce CLAUDE.md rules (functions <=25 lines, classes <=300, 1-file-1-responsibility, module boundaries, forbidden patterns). Auto-trigger on: edits >50 lines, new files, refactors, module-crossing changes, plugin/SDK touches, performance-sensitive paths (HexEditor buffer, CodeEditor render, viewport, drag/scroll), Roslyn diagnostics work. Skip on: doc-only, resx-only, comment fixes, single-line bug fixes, single-file <20-line edits.
memory-recall
by abbayeINTERNAL DEV WORKFLOW for WpfHexEditor — at the start of a new task turn, Claude self-invokes to surface relevant memory entries based on keywords in the user prompt (WebView2, dock, tab, XAML patcher, loc, resx, viewport, drag/scroll, etc.). Prevents re-discovering documented bugs and re-making the mistakes captured in feedback_* memories. Skip on: continuation of an in-progress task in the same turn, purely social messages, single-line follow-ups.
perf-hotpath-guard
by abbayeINTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes after editing C# in render/layout/scroll hot paths (HexEditor/, CodeEditor/Rendering*, *Viewport*, *GlyphRun*, *Renderer*, *ScrollHandler*, OnRender, MeasureOverride, ArrangeOverride) to detect allocations and patterns that cause jank or GC pressure. Skip on: tests, mocks, designer files, non-render code in non-hot directories.
solid-guard
by abbayeINTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes after creating new C# files OR adding >50 lines to existing classes (especially under Services/, Managers/, *Manager.cs, *Service.cs). Heuristics that CORRELATE with SOLID violations: SRP (mixed UI+IO concerns, classes >300 lines + >15 public methods), OCP (massive switch statements >10 cases), DIP (newing services instead of injecting, static singleton mutation), ISP (fat interfaces, NotImplementedException stubs). LSP is out of scope (impossible to detect mechanically). All findings are ADVISORY (warn-only). Skip on: Tests/, Samples/, *.Designer.cs, *.g.cs.
theme-parity
by abbayeINTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes after editing Themes/<Theme>/Colors.xaml or *Theme.xaml to verify the 18 themes share the same key surface. Detects: theme-key-missing (key in Dark but not in the edited theme), theme-key-orphan (key only in this theme), theme-color-no-brush (Color without paired SolidColorBrush), theme-merge-order (wrapper merges Colors.xaml after Menu.xaml/TabControl.xaml). Skip on: edits outside the Themes/ tree.
whfmt-guard
by abbayeINTERNAL DEV WORKFLOW for WpfHexEditor — Claude self-invokes after editing any *.whfmt under Core/WpfHexEditor.Core.Definitions/FormatDefinitions/ or the whfmt.schema.json. Domain checks NOT covered by build gate EmbeddedWhfmt_Tests (parse-only) or nuget-guard (public API): JSONC parse with /* */ header tolerated (per feedback_whfmt_guard), version monotone vs git HEAD (per feedback_whfmt_version), required schema fields (formatName, formatId, extensions, category, description), formatId uniqueness across catalog, magic-signature collisions, detection.strength enum (catches typos before SignatureStrength converter crash — bug_signaturestrength_converter), and placeholder/variables drift. Skip on: files outside FormatDefinitions/, Tests/, Samples/, doc-only or comment-only edits.
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.