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...
horizon
by estevanhernandez-stack-edThis skill should be used when the user says `/vibe-iterate:horizon` and wants to think long-range — what bets to make now to be ahead in months and years, not days and weeks. Ingests four forward signals (stack/platform roadmaps, ecosystem/model curves, competitor trajectory, own-product trajectory), scores bets via :forecast, places them on a Three-Horizon map (H1 ~3-6mo, H2 ~1-2yr, H3 ~3-5yr), and seeds H1 bets into the Atlas for feature-add to pick up. Never ships a PR — matured bets graduate to feature-add.
generate
by estevanhernandez-stack-edThis skill should be used when the user says `/vibe-test:generate`. Generates tests for the gaps the most recent audit identified. Confidence-tiered routing — high-confidence tests auto-write, medium-confidence stage in `.vibe-test/pending/` for batch review, low-confidence show inline in chat for per-test accept/reject. Honors scoped audits, env-var detection, detected framework idioms, and prior team decisions. Playwright E2E generation defers to the `playwright` plugin via Pattern #13.
coverage
by estevanhernandez-stack-edThis skill should be used when the user says `/vibe-test:coverage`. Standalone honest-denominator coverage measurement with builder-facing adaptation-prompt UX. Detects the test framework, proposes the diff to add `--coverage.all` (vitest) or `--collectCoverageFrom` glob (jest); only applies on builder opt-in. Falls back to `c8 --all` when adaptation is refused. Defers raw coverage parsing to `tessl:analyzing-test-coverage` when present. Emits a CI-friendly JSON sidecar at `.vibe-test/state/coverage.json` for machine consumers; exits 0 regardless of threshold (gate decides pass/fail).
walk
by estevanhernandez-stack-edPhase 1.5 interview gates + Phase 2 tour generator for vibe-walk. Reads .vibe-walk/discovery.json, resolves the tour substrate via the decision tree (substrate_tree.py), runs five interview gates, writes .vibe-walk/build-plan.json, then orchestrates four Phase 2 steps: anchor injection (M4), tour module emission (M3), analytics wiring (M5), and trigger wiring (M7).
vibe-walk-guide
by estevanhernandez-stack-edShared reference detail for vibe-walk — the D1–D6 output conventions (the data-tour anchor contract, Driver.js default, the 5-step cap, the 6-event analytics schema, the REVIEW_NEEDED halt) and the friction-trigger map. Load this when a vibe-walk workflow is about to build a tour or log friction. The always-on Sherpa persona, posture, and hard rules live in AGENTS.md, not here.
626labs-design
by estevanhernandez-stack-edUse this skill to generate well-branded interfaces and assets for 626Labs, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
guide
by estevanhernandez-stack-edInternal SKILL — not a slash command. Shared behavior for vibe-wrap commands — voice rules (sentence-case headings, em-dashes, no emoji, no corporate speak), bumper-lanes invariant (default no-action at every gate, every gate has a skip path), persona adaptation (reads `shared.preferences.persona` from the unified builder profile and adapts wrap voice to professor / cohort / superdev / architect / coach), friction-trigger contract linking each command to its `friction-logger.log()` invocations. Referenced by every other vibe-wrap SKILL. See `references/voice.md`, `references/persona-adaptation.md`, `references/friction-triggers.md`.
wrap
by estevanhernandez-stack-edThis skill should be used when the user says `/vibe-wrap` (or `/vibe-wrap:wrap`) and wants a session-end handoff doc that reads the breadcrumb trail sibling vibe plugins already left, surfaces what shipped + what's uncommitted + what's unpushed, and gates commit + push interactively. Multi-repo aware (read wide, mutate narrow): "What shipped" + "Still unpushed" span every sibling repo that had commits in the session window, while the commit/push gates stay scoped to the current repo. Reads breadcrumbs, sibling session-logs / friction / wins, git state across repos, and the active decision-log backend. Writes a markdown wrap doc to `docs/session-wraps/<ts>.md` (fallback `.vibe-wrap/wraps/<ts>.md`) and prints inline. Bumper-lanes invariant — every gate defaults to no-action and has a clear skip path. Flags: `--inline-only`, `--bridge`, `--session-window <hours>`, `--repos <p1,p2,...>`, `--repo-roots <dir>`, `--no-multi-repo`.
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.