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...
fieldwork-methods
by MattArtzAnthroUse this skill whenever a user needs help designing fieldwork data collection instruments or protocols for qualitative or anthropological research. Triggers include: "interview guide," "interview protocol," "focus group guide," "observation protocol," "field notes," "field note template," "fieldwork protocol," "data collection instruments," "sampling strategy," "purposive sampling," "snowball sampling," "data management plan," "DMP," "transcription protocol," "researcher training," "pilot testing," "semi-structured interview," "life history interview," "key informant interview," or "participant observation protocol." Covers interview guides, focus group guides, observation protocols, field note systems, sampling and recruitment, training, pilot testing, and data management. Do NOT use for IRB protocol narratives (use irb-protocol skill), consent documents (use informed-consent skill), or methodology selection (use methodology-selection skill).
informed-consent
by MattArtzAnthroUse this skill whenever a user needs help designing informed consent processes or documents for qualitative or anthropological research. Triggers include: any mention of "informed consent," "consent form," "consent process," "information sheet," "study information sheet," "participant consent," "verbal consent," "oral consent," "community consent," "consent for recording," "consent for photos," "consent for video," "media consent," "ongoing consent," "process consent," "iterative consent," "re-consent," "consent waiver," "waiver of documentation," "consent template," "consent language," "consent for minors," "assent form," "guardian consent," "culturally appropriate consent," "consent in low-literacy settings," "consent for longitudinal research," "consent for multi-site research," or "consent checklist." Covers designing consent processes (written, verbal, community-based, tiered), writing consent forms and information sheets, cultural adaptation, media and recording consent, and consent for special populati
irb-protocol
by MattArtzAnthroUse this skill whenever a user needs help writing, revising, or evaluating an IRB or ethics protocol for qualitative or anthropological research. Triggers include: any mention of "IRB," "ethics protocol," "IRB application," "ethics review," "human subjects," "Common Rule," "informed consent form," "consent process," "how to write an IRB protocol," "ethics board," "IRB submission," "protocol narrative," "exempt vs expedited vs full board," "consent waiver," "verbal consent," "data security plan," "confidentiality," "de-identification," "deductive disclosure," "vulnerable populations," "fieldwork ethics," or "recruitment script." Also trigger when users ask about writing consent forms, recruitment materials, data management plans for IRB, risk assessment for qualitative research, digital ethnography ethics, or oral history IRB issues. Covers all qualitative and ethnographic methods. Do NOT use for upstream method selection (use methodology-selection skill), full research plan writing (use research-plan skill),
methodology-selection
by MattArtzAnthroUse this skill whenever a user needs help selecting, justifying, or evaluating research methods for anthropological or qualitative research. Triggers include: any mention of "methods," "methodology," "method selection," "which methods should I use," "how to choose methods," "how do I justify my methods," "method-stance alignment," "my reviewer says my methods don't match my theory," "multi-method design," "mixed methods in anthropology," or "what methods fit an interpretivist / critical / STS / feminist / phenomenological / applied / cognitive / linguistic / computational project." Also trigger when users ask about epistemic coherence between theory and methods, evidence types needed for a research question, how to compose a multi-method system, how to write a methods justification narrative, or how to handle data governance as a design decision. Covers all anthropological subfields and qualitative social science approaches. Do NOT use for writing a full research plan (use research-plan skill), grant proposal
research-plan
by MattArtzAnthroUse this skill whenever a user needs help writing, drafting, revising, or structuring a standalone research plan for anthropological or qualitative research. Triggers include: any mention of "research plan," "research design," "study design," "fieldwork plan," "methods plan," or "how to structure my research" when not tied to a specific funder or committee milestone; requests to draft or revise sections of a research plan (problem statement, research questions, methods, analysis plan, ethics, feasibility, timeline); questions like "what should my research plan include," "how do I plan my fieldwork," "help me think through my methods," or "I need to write up my research design." Also trigger when a user has a project idea and needs to develop it into a structured, evaluable plan. Covers all anthropological subfields and qualitative social science approaches. Do NOT use for grant proposals targeting a specific funder (use grant-proposal skill), dissertation prospectuses for a committee defense (use dissertation
research-question
by MattArtzAnthroDevelop, refine, and stress-test anthropological research questions. Use this skill whenever a user mentions research questions, RQs, dissertation questions, proposal questions, or asks for help formulating what they want to study. Also trigger when users say things like "I want to study X," "how do I narrow my topic," "is this question too broad," "help me write my research question," "I'm writing a proposal and need questions," or "what should I be asking." Covers sociocultural, linguistic, archaeological, biological, medical, applied, and design anthropology as well as cognate qualitative social sciences. Works across genres: journal articles, dissertation proposals, grant applications (NSF, Wenner-Gren, Fulbright), and applied/consulting projects. If someone is working on any pre-fieldwork intellectual framing task, this skill applies.
dissertation-prospectus
by MattArtzAnthroUse this skill whenever a user needs help writing, drafting, revising, or structuring a dissertation prospectus, dissertation proposal, qualifying exam proposal, upgrade document, transfer document, or fieldwork clearance proposal for anthropological research. Triggers include: any mention of "prospectus," "dissertation proposal," "qualifying exam," "QE," "upgrade proposal," "transfer of status," "confirmation of status," "fieldwork proposal," or "fieldwork clearance" in the context of anthropology or ethnographic research; requests to structure, draft, or revise any section of a dissertation proposal (problem statement, research questions, theoretical positioning, literature review, methods, ethics, timeline, budget); questions about what a committee expects or how to prepare for a prospectus defense or upgrade viva. Also use when the user says "I need to write my prospectus," "I'm preparing for my qualifying exam," "how do I structure a dissertation proposal," or "what should my prospectus include." Covers
academic-review
by MattArtzAnthroUse this skill whenever a user needs help writing, evaluating, or responding to peer reviews for anthropological research. Triggers include: any mention of "peer review," "review a manuscript," "write a review," "reviewer comments," "respond to reviewers," "rebuttal letter," "revision plan," "manuscript evaluation," "assess this paper," "reviewing for [journal name]," "R&R response," "how to review," "reviewer feedback," "revise and resubmit." Covers writing constructive peer reviews for anthropology journals, evaluating manuscripts from the reviewer's perspective, and responding to reviewer feedback (rebuttal letters, revision plans). Review types: invited review, desk review, blind review, open review. Do NOT use for grant review panels (use grant-proposal skill) or student work feedback (use teaching-materials skill). This skill handles peer review as a professional scholarly practice and revision as a strategic engagement with reviewer critique.
career-statements
by MattArtzAnthroUse this skill whenever a user needs help writing professional philosophy statements for academic career advancement. Triggers include: any mention of "research statement," "teaching statement," "teaching philosophy," "diversity statement," "DEI statement," "tenure narrative," "promotion statement," "research vision," "future research plans," "statement of purpose," "personal statement for academic job," "how to write a research statement," "how to write a teaching statement," or "tenure portfolio." Covers research statements, teaching statements/philosophies, diversity statements, and tenure/promotion narratives for anthropologists at all career stages. Do NOT use for CVs, cover letters, or job talks (use job-materials skill), course syllabi or assignments (use teaching-materials skill), or grant proposals (use grant-proposal skill).
conference-materials
by MattArtzAnthroUse this skill whenever a user needs help preparing materials for an anthropology conference presentation. Triggers include: any mention of "conference abstract," "AAA abstract," "organized session," "roundtable proposal," "poster session," "workshop proposal," "slide deck," "conference presentation," "conference talk," "academic poster," "speaker notes," "20-minute talk," "15-minute talk," "CASCA abstract," "AES presentation," "SfAA abstract," "help with my AAA panel," "poster design," or "oral delivery." Covers abstract writing for individual papers, organized sessions, roundtables, poster sessions, and workshop proposals; slide deck design for 15-20 minute conference talks; academic poster design including content structure and visual hierarchy; and speaker notes with oral delivery preparation. Do NOT use for job talks (use job-materials skill), public talks for non-academic audiences (use public-engagement skill), or full paper writing (use academic-paper skill when available).
grant-proposal
by MattArtzAnthroUse this skill whenever a user needs help writing, drafting, revising, or structuring a grant proposal, funding application, or dissertation prospectus for anthropological research. Triggers include: any mention of NSF, Wenner-Gren, Fulbright, ERC, SSHRC, Wellcome, or other research funders in the context of anthropology or ethnographic research; requests to write a Project Description, research narrative, budget justification, broader impacts statement, or specific aims page; requests to draft or revise a dissertation prospectus or fieldwork grant; questions about how to frame ethnographic methods for a grant committee; requests to translate a research plan into a funder-specific format. Also use when the user mentions "grant writing," "proposal writing," "funding application," or "fellowship application" in the context of anthropology, sociology, STS, or other social science fieldwork research. Do NOT use for general academic writing (use academic-paper skill), research plan writing without a specific funde
job-materials
by MattArtzAnthroUse this skill whenever a user needs help preparing academic job application materials for anthropology positions. Triggers include: any mention of "academic CV," "curriculum vitae," "cover letter," "job application," "job talk," "academic job market," "tenure-track application," "postdoc application," "VAP application," "lecturer position," "how to write a cover letter," "CV formatting," "job talk preparation," "campus visit," "search committee," "application package," "tailoring applications," or "academic hiring." Covers academic CV design and formatting, cover letters tailored by position type, job talk design and delivery, and application strategy. Do NOT use for research/teaching/diversity statements (use career-statements skill), conference presentations (use conference-materials skill), or grant proposals (use grant-proposal skill).
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.