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...
fwd-issue-create
by baswennekerInteractief een GitHub issue opstellen volgens een vast 5-secties template (probleem, voorbeelden, bevindingen, potentiële oplossing, tests). Skill leest input uit een argument óf de huidige conversatie-context, detecteert bestaande repo-labels, vraagt om een assignee, en laat de gebruiker de complete draft per sectie reviewen voordat `gh issue create` wordt aangeroepen. Use when user wants to create a GitHub issue from a problem they are describing, runs `/fwd:issue-create`, says "maak een issue", or "create issue from context".
fwd-issue-fix
by baswennekerPrivately work through your assigned GitHub issues overnight — pick the oldest open issue, fix it in an isolated worktree, run tests, commit (no push). Driven by /loop. Strictly read-only on GitHub (no labels, no comments, no PRs) so collaborators can't tell the work was automated; all state local in `.claude/issue-loop/state.json`. Use when user says "work through my GitHub issues overnight", runs `/loop /fwd:issue-fix`, or invokes `/fwd:issue-fix` to fix one issue.
fwd-mission-plan
by baswennekerPlan a multi-agent "mission" — scope a software goal through conversation, write a PRD plus a validation contract (what "done" means, before any code), decompose into features and milestones, then create the mission branch and commit the plan. The interactive half of the fwd:mission-* orchestration layer (modelled on Factory.ai Missions); execution is handled afterwards by /fwd:mission-run. Use when the user wants to plan a larger feature as an orchestrated mission, says "plan a mission", "start a mission", "scope this as a mission", or invokes /fwd:mission-plan.
fwd-mission-run
by baswennekerExecute a planned mission — the resident orchestrator of the fwd:mission-* layer (a Claude Code take on Factory.ai Missions). Reads the mission's state.json, drives features one at a time by spawning a fresh coder subagent each, runs adversarial validators (Scrutiny + User-Testing) at milestone boundaries, and commits a checkpoint after every unit so the mission resumes from any worktree or clone. Runs autonomously — never prompts. Use when the user runs /fwd:mission-run <slug>, says "run/execute/resume mission <slug>", or wraps it in /loop for a long multi-day run. Pass `status` as a second argument for a read-only progress report.
fwd-plan
by baswennekerPlan een implementatie — verzamel codebase-context, presenteer eerst een DoD-voorstel met numbered bullets (akkoord of corrigeer in plain text, géén AskUserQuestion), stel daarna 0-3 verdiepende keuzes via AskUserQuestion, en presenteer 1 of 3 plannen in visueel distincte boxen met spec-strip + TL;DR + Wijzigingen-tabel. Sluit altijd af met (Recommended)-tag op het beste plan en een verdict-block met onderbouwing. Use when user wants to plan a feature, refactor, or change met meerdere opties op tafel, of invokes /fwd:plan.
fwd-setup
by baswennekerSetup wizard for HeadingFWD's optional Claude Code conventions. Asks the user in a single multiselect dialog which features to install (currently smartlint Stop-hook, a lessons memory file, gitignore entries for fwd runtime artefacts, Claude Code's clear-context prompt on plan accept, and disabling Claude Code's default commit/PR attribution), then runs the matching installers in batch — copying bundled payload files into .claude/hooks/ or .claude/lessons/, merging JSON snippets into ~/.claude/settings.json or .claude/settings.local.json, injecting an instructions section into CLAUDE.md (lessons), or appending a marker-bracketed block to .gitignore. Idempotent and modular — each feature lives in scripts/<feature>/. Use only when the user invokes /fwd:setup explicitly.
fwd-skill-eval
by baswennekerBlack-box self-evaluation for any Claude Code skill. Reads the target SKILL.md, extracts its surface (triggers, CLI flags, input/output formats, documented exit codes, examples), generates ~10 experiments covering happy paths, flag interactions, error paths, and domain invariants, runs each in an isolated workdir under tmp/eval/, and reports pass/fail in a single markdown table. Refuses to run on a dirty working tree. Ends the report with an undo prompt — reply with `x` or `undo` to remove tmp/eval/. Use when the user says "self-evaluate skill X", "shake down skill X", "test skill X end-to-end", "regression-check skill X after my refactor", "does this skill still behave the way SKILL.md claims", or invokes /fwd:skill-eval.
fwd-caveman
by baswennekerUltra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /fwd:caveman.
fwd-explain
by baswennekerBreak down anything heavy — a plan, code file, diff, doc, stack trace, PR, URL, or concept — into a layered walkthrough. Builds a mental model first (problem framed + best-fit form: diagram, analogy, before/after, or causal narrative — plus structure map), then one chunk at a time on demand. Use when the input is too long to skim, when you've come back to something and lost the thread, or when ramping up on unfamiliar material.
fwd-grill-me
by baswennekerInterview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
fwd-handoff
by baswennekerCompact the current conversation into a handoff document for another agent to pick up.
fwd-premortem
by baswennekerStress-test a plan by imagining it has already failed, then list concrete failure modes, grade each on Likelihood × Impact, and ICE-rank candidate mitigations for the meaningful ones. Use when user wants to pre-mortem a plan, asks "what could go wrong", wants to harden a design before commitment, or invokes /fwd:premortem.
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.