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...
bead-lifecycle-shell
by fkbertholdCross-activity lifecycle scaffolding for working a beads issue from claim to merged. Owns MemPalace bug-family search, claim, optional worktree, verification, commit, finishing-a-development-branch, preflight + close + push, and decision drawer + KG triples + diary capture. Each activity recipe (bugfix-a-bead, feature-a-bead, refactor-a-bead, research-a-bead, etc.) references the lettered phases below and supplies its own VARIABLE MIDDLE between phase B and phase C. Internal building block — invoked indirectly via an activity recipe, not directly by the user.
upstream-a-bead
by fkbertholdActivity recipe for working an upstream-contribution-shaped beads issue. Owns the upstream-specific variable middle — lock contract + lane → clone upstream into ~/.loom/upstream/ → RED test in the upstream tree → minimal GREEN fix → draft issue + PR with privacy redaction → user review gate → auto-file via gh + spawn watch-bead. Defers to the bead-lifecycle-shell skill for claim/isolate/verify/close/capture. Two lanes: `--issue-only` (codifies the loom-45i triad filing pattern; skips M3-M5) and `--issue+pr` (full clone + RED/GREEN + PR). Triggers on phrases like "let's work on <upstream-work-bead-id>", "file upstream <owner>/<repo>: ...", "drive <bead> upstream", or right after the session-startup or /working-a-bead router picks an `upstream:work`-labeled bead.
audit-project
by fkbertholdAudit the current project's workflow infrastructure (git/branch hygiene, beads init, bd hooks, workflow.json, MemPalace wing, CLAUDE.md, .claude/rules/, .claude/agents/+commands/, bd memories) and — for projects that already have a Diataxis docs substrate — the docs/system/beads/MemPalace alignment of the project's documentation. Drives the project-onboarder subagent, presents the structured checklist to the user, and offers interactive template-based fixes per gap. Manual-only — never auto-suggested by session-startup or any activity recipe; only fires when the user invokes `/audit-project`.
bugfix-a-bead
by fkbertholdActivity recipe for working a bug-shaped beads issue. Owns the bug-specific variable middle — systematic debugging → RED test → minimal GREEN fix → bug-class coverage → enshrined-test sweep. Defers to the bead-lifecycle-shell skill for claim/isolate/verify/close/capture. Triggers on phrases like "let's work on <bug-bead-id>", "fix <bead-id>", or right after the session-startup or /working-a-bead router picks a bug bead.
cleanup-a-bead
by fkbertholdActivity recipe for working a cleanup-shaped beads issue. Owns the cleanup-specific variable middle — identify scope → hunt orphan references → remove → verify nothing broke. Defers to the bead-lifecycle-shell skill for claim/isolate/verify/close/capture. Triggers on phrases like "remove <X>", "delete <Y>", "drop <Z> dep", "rip out <W>", "retire <thing>", or right after the session-startup or /working-a-bead router picks a cleanup bead.
docs-scaffold
by fkbertholdScaffold a Diataxis-shaped MkDocs Material docs/ tree into the current loom-managed project by copying templates/diataxis/ with variable substitution and per-file approval. Refuses against non-loom-managed projects and against projects carrying the docs/.no-diataxis opt-out marker. Manual-only — never auto-suggested by session-startup or any activity recipe; only fires when the user invokes `/docs-scaffold`.
feature-a-bead
by fkbertholdActivity recipe for working a feature-shaped beads issue. Owns the feature-specific variable middle — brainstorm the design → optionally split into a plan + child beads → RED test that pins the desired contract → minimal GREEN implementation → negative-cases + integration coverage. Defers to the bead-lifecycle-shell skill for claim/isolate/verify/close/capture. Triggers on phrases like "let's work on <feature-bead-id>", "build <bead-id>", "implement <bead-id>", or right after the session-startup or /working-a-bead router picks a feature bead.
loom-mine-history
by fkbertholdMine a brownfield repo's git/PR history for decisions stated in-flight but never captured, then file the salient survivors as `provenance:mined` decision drawers in the project's own MemPalace wing. Drives the `scripts/loom-mine-history` wrapper through a locked two-pass cost gate — zero-spend dry-run preview, explicit user go-ahead, then the paid LLM salience pass — and does the MCP filing the bash engine cannot. Invoked by `/loom-mine-history`.
research-a-bead
by fkbertholdActivity recipe for working a research-shaped beads issue. Owns the research-specific variable middle — define the question → search prior art (palace + KG + bd memories + diary) → fetch authoritative external docs → synthesize → file findings as decision drawer + KG triples + optional follow-up beads. Defers to the bead-lifecycle-shell skill for claim/verify/close/capture. No code, no worktree (usually). Triggers on phrases like "research <topic>", "what do we know about <X>", "investigate <Y>", or right after the session-startup or /working-a-bead router picks a research bead.
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.