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...
shopping-hunter
by jakkajDeep shopping research skill for finding products similar to a reference link or image, benchmarking global pricing, comparing quality/provenance, and creating a reusable buying dossier with links, per-item prices, shipping notes, and value-focused recommendations.
plan-1b-v3-specify-and-clarify
by jakkajCreate a feature spec AND resolve high-impact ambiguities in a single skill. Front-loads questions: asks host-independent questions (Mode/Testing/Mock/Docs) in ONE batched prompt BEFORE writing the spec, generates the sketch with those answers already applied, then asks a conditional second batch only for sketch-dependent gaps (Domain Review, Agent Harness, topic-specific markers). Cap ≤8 total. Uses batched prompting where the host supports it (e.g., Claude Code's AskUserQuestion), falls back to sequential one-at-a-time on hosts that don't. Replaces the old plan-1b → plan-2 two-skill hop.
plan-2b-v2-prep-issue
by jakkajGenerate terse, industry-standard issue text from specs and plans for Azure DevOps, GitHub Issues, or any tracker. Domain-aware v2.
plan-2c-v2-workshop
by jakkajCreate detailed design documents for complex concepts identified in the spec's Workshop Opportunities, or any topic needing deep exploration. Domain-aware v2.
plan-6a-v2-update-progress
by jakkajUpdate plan progress with task status and domain context. V2 standalone rewrite.
plan-6b-worked-example
by jakkajGenerate a runnable worked example that demonstrates a phase's implementation through a clear, narrative, step-by-step script you can run and debug.
plan-1a-v2-explore
by jakkajDeep-dive research into existing codebase functionality. Auto-detects plan context or creates new plan folder. Integrates with FlowSpace MCP when available. Domain-aware v2.
plan-3a-v2-adr
by jakkajGenerate an Architectural Decision Record (ADR) from the feature spec and clarifications; persist to docs/adr and cross-link into the plan. Domain-aware v2.
plan-5b-flightplan
by jakkajGenerate a consumable Flight Plan (.fltplan.md) at phase or plan level. Phase-level is auto-called by plan-5. Plan-level is auto-called by plan-1b/plan-3 for executive overview.
harness-2-backpressure
by jakkajAdvisory deterministic-backpressure coverage survey. Runs AFTER the spec (plan-1b / plan-2c) and BEFORE the architect (plan-3). Inventories the deterministic sensors a repo already has (build / type / test / lint / smoke / boot / architecture checks, CodeQL / Roslyn / dependency-rules / data-scripts), derives the feature's experienced failure modes from the spec's acceptance criteria + target domains + risks, maps each criterion/failure-mode to a sensor (EXISTS / BUILDABLE / ABSENT × computational / inferential / human-judgement), emits a qualitative certainty rating (Strong / Partial / Weak), and — only when material behaviour/architecture gaps exist — recommends a "Phase 0: Establish Backpressure". Writes docs/plans/<ordinal>-<slug>/backpressure-coverage.md, which plan-3-v3-architect consumes. ADVISORY / best-effort only: never blocks, never flips a plan to DRAFT, no numeric thresholds, no persisted index. Honours docs/harness/.disabled.
the-flow
by jakkajThe single front door to the SDD pipeline (docs/plans/): research → spec → workshop → architect → ADR → phase tasks → implement → progress → review → merge. Use when the user wants to plan, research, explore, specify, clarify, workshop, architect, write an ADR, break a phase into tasks, implement or build a phase (optionally with a live review companion), update progress, code-review, or merge a plan — or types /the-flow (or a legacy /plan-N command), or asks to start, resume, or adopt a plan flow. Guided mode (no args) coaches stage-by-stage from durable on-disk state; direct jump runs exactly one stage: /the-flow <id> <verb> [flags] — 1a explore, 1b specify (incl. clarify re-entry), 2c workshop, 3 architect, 3a adr, 5 tasks, 6 implement (--companion for live review), 6a progress, 7 review, 8 merge. Ids and verbs each resolve alone; printed commands always carry both. Sub-skill logic lives in references/stages/*.md, loaded lazily — one module per step.
util-0-v2-handover
by jakkajGenerate a domain-aware handover document for LLM agent continuity. V2 standalone rewrite.
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.