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...
lazy-batch-retro
by jacobrocks1212Audit and grade a completed /lazy-batch or /lazy-batch-cloud run for skill-compliance. Read-only. Writes per-feature review artifacts under docs/features/<feat>/LAZY_BATCH_REVIEW_<date>.md. After writing, Step 6c runs the shared audit-table-validator component over every artifact, annotating Compliance Matrix / Findings rows with ⚠ NOT-FOUND-IN-SPEC or ⚠ CROSS-FEATURE-DUP markers so the next audit walker spots misattributions and copy-paste errors before walking them as gaps. Triggers on 'audit batch', 'grade batch', 'review batch run', '/lazy-batch-retro'.
retro
by jacobrocks1212Retrospective analysis of completed work — identifies issues, incorrect assumptions, and workflow improvements. After writing the retro plan, dispatches a Sonnet spec-body-fixer (Step 6b.5) to propagate Minor doc-drift divergences (resolved-research checklists, stale counts, deferred-API surface entries, stale Status) into SPEC.md inline and annotates the plan's Minor rows with the fix commit — Significant rows untouched. RETRO_DONE.md (Step 6c) only fires when the Significant table is empty.
strudel-music-composition-and-theory
by jacobrocks1212Provides guidance for applying music theory concepts within the Strudel live coding environment. This skill covers topics such as harmony, melody, rhythm, and non-traditional tuning systems.
strudel-pattern-transformation
by jacobrocks1212Provides guidance for working with pattern transformation in the Strudel live coding environment. This skill covers the rich set of functions for altering, combining, and manipulating patterns in Strudel.
strudel-core-concepts
by jacobrocks1212Provides guidance for working with the core concepts and syntax of the Strudel live coding environment. This skill covers the fundamental building blocks of creating music with Strudel, including patterns, cycles, pitch, and the various notation systems.
strudel-integration-and-visualization
by jacobrocks1212Provides guidance for integrating Strudel with external systems and for using its visual feedback capabilities. This skill covers topics such as MIDI, OSC, Hydra, and the various visualization tools available in Strudel.
strudel-sound-generation-and-audio-effects
by jacobrocks1212Provides guidance for working with sound generation and audio effects in the Strudel live coding environment. This skill covers the use of samples, synthesizers, Csound, and the various audio effects available in Strudel.
nxtest
by jacobrocks1212Run frontend tests with filtered output (PASS/FAIL + errors only). Wraps client-test-filtered.ps1.
lazy-batch-cloud
by jacobrocks1212Cloud-environment variant of /lazy-batch. Loops on lazy-state.py --cloud and spawns Opus subagents per cycle, deferring any step that requires the Tauri desktop or MCP HTTP server. Halts on BLOCKED.md, needs-research (strict halt by default — the first research-pending feature stops the queue; opt into batched research with --allow-research-skip), queue-blocked-on-research (only reachable under --allow-research-skip), cloud-queue-exhausted, or max-cycles cap. NEEDS_INPUT.md (design decisions) does NOT halt: Step 1g calls AskUserQuestion, dispatches a Sonnet apply-resolution subagent to propagate the choice into SPEC/PHASES, and resumes the loop. Research uploaded mid-session via chat triggers in-session resume: /ingest-research is dispatched immediately (writing the tracked RESEARCH.md + RESEARCH_SUMMARY.md — critical because docs/gemini-sprint/results/ is gitignored and bare .txt stages do not survive cloud-container reclaim) and the loop is re-invoked — no manual re-run required.
lazy-batch
by jacobrocks1212Autonomous orchestrator for the AlgoBooth (or any queue.json-driven) feature pipeline. Loops on lazy-state.py, spawns one Opus subagent per cycle, and drives the full tail (/spec → /plan-feature → /execute-plan → /mcp-test → __mark_complete__). A halt for any reason other than max-cycles presents an AskUserQuestion resolution path and resumes — only max-cycles, all-features-complete, environment-exhaustion, and missing-queue remain clean stops. Terminal action is __mark_complete__, gated by the MCP-coverage audit + completion-integrity gate. (The /retro step is unwired — 2026-06.)
lazy-batch-retro
by jacobrocks1212Audit and grade a completed /lazy-batch or /lazy-batch-cloud run for skill-compliance. Read-only. Writes per-feature review artifacts under docs/features/<feat>/LAZY_BATCH_REVIEW_<date>.md. After writing, Step 6c runs the shared audit-table-validator component over every artifact, annotating Compliance Matrix / Findings rows with ⚠ NOT-FOUND-IN-SPEC or ⚠ CROSS-FEATURE-DUP markers so the next audit walker spots misattributions and copy-paste errors before walking them as gaps. Triggers on 'audit batch', 'grade batch', 'review batch run', '/lazy-batch-retro'.
lazy
by jacobrocks1212Stateless dispatcher — infers project state from filesystem via lazy-state.py, invokes exactly ONE sub-skill per invocation to progress the current feature. Distinguishes STUB specs (canonical `> Draft (pre-Gemini)` trailer OR queue.json `"stub": true` → Step 4.5 dispatches interactive /spec to shape the baseline via AskUserQuestion) from STRUCTURED specs awaiting research (no stub markers, missing RESEARCH.md → Step 5 halts on needs-research and waits for the user's Gemini upload — single-turn, no conversation). The `__mark_complete__` special action runs an MCP-coverage audit (Gate 1) before the SPEC flip — uncovered SPEC Locked Decisions route to authoring the missing MCP coverage (or a documented test-exempt note) per the completeness-first standing policy (D7), deferring the flip; the operator is never asked
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.