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...
audit-reproducibility
by ericluo04Cross-check every numeric claim in a manuscript against the actual R / Python outputs that produced it, and report PASS / FAIL per claim against numeric tolerances. Use when the user says "audit reproducibility", "check my numbers", "verify the tables match the code", "reproducibility audit", "do the paper numbers match", or before submitting / resubmitting a paper or releasing a replication package. Designed for quant-marketing manuscripts (Marketing Science, JMR, JCR, Management Science) and economics-style projects in R or Python.
create-lecture
by ericluo04Scaffold a new Beamer lecture or research-talk `.tex` from source papers, notes, or a prior deck — with notation consistency against the project preamble and the user's bold-math conventions wired in. Use when user says "create a lecture on X", "new lecture from these papers", "scaffold a Beamer deck", "build me a research talk on Y", "start a seminar deck", "MBA lecture on Z". Supports two modes: research-talk (MKSCI / JMR / JCR / MS seminars) and pedagogical-lecture (MBA Quant Marketing / Marketing Analytics).
review-paper-light
by ericluo04Run a fast 2-agent pre-submission check for an empirical paper — focuses on contribution, identification, and causal overclaiming. Designed for marketing (MKSCI, JMR, JCR, MS) and economics/finance papers. Completes in ~1 minute.
review-paper
by ericluo04Run a 6-agent pre-submission referee report for an academic paper targeting a specified journal. Covers spelling/style, internal consistency, unsupported claims, math/notation, tables/figures, and an adversarial top-journal referee evaluation. Supports marketing (MKSCI, JMR, JCR, MS) and economics/finance journals.
review-grant
by ericluo04Run a 6-agent pre-submission panel review for a grant proposal targeting a specified funder or program (NSF, NIH, ERC, HorizonEurope, foundation, etc.). Covers clarity/compliance, internal consistency/deliverables, significance/innovation, research design/feasibility, budget/timeline/team, and an adversarial panel review with funding recommendation.
academic-slides
by ericluo04Create Beamer-inspired academic HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build slides for a conference talk, lecture, seminar, or thesis defense. Supports theorem environments, KaTeX equations, algorithm pseudocode, and citations. Helps academics discover their preferred visual theme through Beamer-style previews rather than abstract choices.
academic-pptx
by ericluo04Use this skill whenever the user wants to create or improve a presentation for an academic context — conference papers, seminar talks, thesis defenses, grant briefings, lab meetings, invited lectures, or any presentation where the audience will evaluate reasoning and evidence. Triggers include: 'conference talk', 'seminar slides', 'thesis defense', 'research presentation', 'academic deck', 'academic presentation'. Also triggers when the user asks to 'make slides' in combination with academic content (e.g., 'make slides for my paper on X', 'create a presentation for my dissertation defense', 'build a deck for my grant proposal'). This skill governs CONTENT and STRUCTURE decisions. For the technical work of creating or editing the .pptx file itself, also read the pptx SKILL.md.
cite
by ericluo04Resolve a paper (DOI, arXiv ID, title, or URL) to a Zotero entry, append its BibTeX to the active project's .bib file, and return the citation key ready for \citep{}. Use this whenever the user asks to add a citation, "cite this paper", or pastes a paper identifier.
tikz-iterate
by ericluo04Iteratively refine a TikZ diagram by compiling it, rendering to PNG, asking the tikz-reviewer sub-agent to evaluate, and applying fixes until APPROVED (or 5 iterations elapse). Designed for Beamer / standalone TikZ snippets in academic papers and lecture decks. Use when the user says "/tikz-iterate", "polish this tikz", "iterate on this diagram until it looks right", "make this figure not look terrible", "compile and review this tikz", or pastes a TikZ block with "fix it visually". Distinct from /slide-excellence (which reviews a whole deck) and the standalone tikz-reviewer agent (which reviews once); /tikz-iterate is the orchestration loop that drives multiple compile/render/refine rounds. Cross-platform — uses latexmk + pdftoppm from MiKTeX (Windows), MacTeX (macOS), or TeX Live (Linux).
draft
by ericluo04Drafts paper sections (Intro, Lit Review, Method, Empirical Setting, Empirics, Discussion, Limitations, or arbitrary paragraphs) in the user's voice — hedged, modest, natbib-apa citations, \Cref cross-references, \emph over \textit, figure/table notes minipages, three-stream lit-review structure. Use this skill whenever the user asks to "draft", "write", "rewrite in my voice", "give me a paragraph on", or "draft a section" for any of their papers. Also triggers on phrases like "write the limitations", "draft an intro for X", "write up the empirical setting", "rewrite this in my voice". Output always goes to a dated draft file under `<project>/drafts/` — never directly into the main `.tex`.
referee-response
by ericluo04Drafts an R&R response letter in the user's R2R style — sectioned by role (Senior Editor / Associate Editor / Reviewer 1 / Reviewer 2), reviewer quotes in `\textit{...}`, location-pinned changes ("see Section 3", "Footnote 7", "Table 4"), "Done." for trivial fixes, polite pushback with cited authority, abandoned drafts kept in `\begin{comment}` blocks. Reads existing `R2R_*.tex` files in the project for tone match and grounds every location pin against the actual `main*.tex`. Use whenever the user asks to "respond to referees", "draft an R&R response", "write the R2R", "address reviewer comments", "respond to the AE", or pastes reviewer comments from an Outlook export / decision letter. Also triggers on "continue the R2R" (extend a partial draft). Output goes to `<project>/R2R_R<n>.tex`.
bibcheck
by ericluo04Audit an existing .bib file entry-by-entry against ground truth (DOI, Semantic Scholar, OpenAlex, arXiv) to catch the silent citation errors that pass spell-check but kill peer review — wrong year, mis-cited authors, wrong journal/volume, swapped title-author pairs, fabricated DOIs, and outright hallucinated entries (a real concern with LLM-assisted drafting). Spawns one narrow-focus subagent per entry so each citation gets full attention rather than the gradient-decay that single-pass audits suffer at scale. Use whenever the user says "/bibcheck", "audit my .bib", "verify references", "check my bibliography for errors", "any fake citations", "pre-submission bib audit", "did Claude hallucinate any of these", or before shipping a manuscript / R&R to Marketing Science, JMR, JCR, Management Science. Read-only and audit-only — never adds, edits, or removes entries; produces a PASS/WARN/FAIL report and a `corrected.bib` the user can diff and move into place themselves. Strictly distinct from `/cite` (which ADDS on
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.