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...
logseq-templates
by jluo41Create and use LogSeq templates with dynamic variables for reusable block structures. Use when the user wants to create templates, use dynamic date or time variables, or set up recurring journal structures in LogSeq.
logseq-cc-records
by jluo41Log the current Claude Code conversation to today's LogSeq journal with a time-stamped summary. Use when the user wants to record, log, or save the current session to LogSeq, or when they say /logseq-cc-records.
logseq-markdown
by jluo41Create and edit LogSeq block-based markdown with properties, wikilinks, block references, embeds, tasks, and namespaces. Use when working with .md files in a LogSeq graph, or when the user mentions LogSeq blocks, properties, namespaces, or journal pages.
logseq-queries
by jluo41Write LogSeq simple queries and advanced Datalog queries to filter, search, and aggregate blocks and pages. Use when the user wants to query their LogSeq graph, create dynamic views, filter tasks, or build advanced database queries with Datalog.
logseq-whiteboards
by jluo41Create and edit LogSeq Whiteboard files (.edn) with shapes, connectors, portals, and embeds on an infinite canvas. Use when working with whiteboard .edn files in a LogSeq graph, creating visual diagrams, mind maps, or spatial canvases, or when the user mentions LogSeq whiteboards.
haipipe-probe
by jluo41"Research probe pipeline — drives how tasks/runs in a project roll out. Each probe is a claim-directed research thread with a 5-stage lifecycle (Design → Materialize → Harvest → Judge → Insight) and loop-back from Judge → Explore → Design. Design has two modes: interactive (human) or auto (creator-reviewer agents). Insight stage files full DIKW cascade (D → I → K → W). Contains no code — pure steering layer on top of C_task execution. Feeds E_insight and F_paper. Trigger: probe, claim, hypothesis, drive probe, plan next runs, aggregate runs, statistical test, paired-t, coverage, propose next probe, review-loop, iterate until claim holds, implement the plan, deploy probes, /haipipe-probe."
haipipe-narrative
by jluo41Story layer (N_narrative) — the ARGUE layer in the DO/CLAIM/ARGUE pyramid. 6-stage lifecycle: Idea → Discovery → [Probes&Tasks → Insights → Fill → Ignite]* → Handoff. Owns ALL E_insight filing (sole writer). Reads tasks + probes, curates what becomes permanent knowledge, judges when the story is ready. Handoff → F_paper + G_application. Trigger: narrative, story, angle, ignite, what story, sell this, which claims, gap, /haipipe-narrative.
deepxiv
by jluo41Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.
haipipe-discover
by jluo41Router for Stage A (discover) literature/idea discovery. Dispatches to 1 of 4 buckets: search (arxiv/semantic-scholar/exa-search), read (alphaxiv/deepxiv/paper-analyzer), review (research-lit/comm-lit-review/academic-researcher), idea (idea-creator/novelty-check). Pipelines escalate to /idea-discovery. Patent work lives in D_patent/. Trigger: discover, find paper, lit review, 找idea, 查新, /haipipe-discover.
haipipe-paper-structure-architecture
by jluo41Generate a versioned architecture + section minimap for an academic paper as ONE markdown file (vNN-architecture-minimap.md): config table, key numbers, 5-act arc, paragraph-level section minimap with A/B options, appendix plan, language guide, page budget. Trigger: paper architecture, architecture overview, strategic blueprint, section minimap, /haipipe-paper-structure-architecture.
sl-status
by jluo41Show current state of a subjective-label project: iteration count, gallery size, panel-internal κ, public-dataset κ trajectory, disagreement category breakdown, suggested next step. Read-only. Use when the researcher says /sl-status or wants to check progress.
haipipe-end-develop-databricks
by jluo41Databricks develop specialist for haipipe-end. STATUS: DEFERRED — no platform-databrick-training repo backs this yet; SKILL.md kept as a placeholder for parity with -develop-sagemaker. Would run Stage 5 training as a Databricks Job (notebook or wheel task) with model logged to Unity Catalog and exported as an Endpoint_Set under 6-EndpointStore/. The umbrella's no-args dashboard skips this skill while deferred.
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.