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...
ny-landlord-tenant
by codearrangerSubject-matter bundle for New York landlord-tenant defense and prosecution — particularly residential summary proceedings under RPAPL Article 7. Triggers include 'eviction defense New York', 'NYC Housing Court', 'RPAPL 711 holdover', 'RPAPL 731 nonpayment', 'HSTPA 2019', 'Housing Stability and Tenant Protection Act', 'Good Cause Eviction Law 2024', 'rent stabilization', 'RPL 235-b warranty of habitability', 'Real Property Law 226-c', '14-day demand letter', '30-day notice to vacate'. Covers **RPAPL Article 7** summary proceedings (holdover + nonpayment); **2019 HSTPA** reforms (rent increases, security deposits, attorney's-fee shifting); **2024 Good Cause Eviction Law** (RPL Article 6-A); **RPL 235-b** warranty of habitability; **ERAP** automatic stay; and **NYC Housing Court** practice including right-to-counsel under NYC Admin Code § 26-1301.
in-hearings
by codearrangerThis skill should be used when the user asks to "prepare for an Indiana hearing", "oral argument Indiana", "Indiana courtroom etiquette", "Marion zoom hearing", "Indiana virtual hearing", "WebEx Indiana court", "hearing day checklist Indiana", "Indiana evidentiary hearing", "Indiana CCS conference", "Indiana telephonic hearing", "Indiana bench trial", or any related hearing-preparation question. Covers oral argument in motion practice, evidentiary hearings, the statewide Webex remote-hearing protocol under Indiana Administrative Rule 14, courtroom etiquette, hearing-day logistics, exhibit handling, the role of the court reporter, and pro se conduct expectations. Trigger phrases: "Indiana hearing prep", "Marion oral argument", "Lake bench trial", "Webex Indiana", "Admin Rule 14", "Indiana courtroom protocol", "evidentiary hearing Indiana".
ny-city-courts
by codearrangerUse when drafting or filing in an upstate City Court — the limited-jurisdiction civil layer outside New York City under the **Uniform City Court Act (UCCA)** with procedural rules at **22 NYCRR Part 210**. Triggers include 'Buffalo City Court', 'Rochester City Court', 'Syracuse City Court', 'Albany City Court', 'Yonkers City Court', 'White Plains City Court', 'Schenectady City Court', 'Utica City Court', 'Troy City Court', 'UCCA', 'Uniform City Court Act', '22 NYCRR Part 210', 'upstate City Court'. Covers the ~60 City Courts' civil and small-claims jurisdiction, Housing Parts where they exist, and the variable NYSCEF e-filing rollout. NOT for NYC Civil Court (see `ny-nyc-civil-court`); not for Town & Village Justice Courts (UJCA — see `ny-justice-courts`); not for Long Island District Courts (UDCA — see `ny-nassau-dc` and `ny-suffolk-dc`).
or-statewide-format
by codearrangerThis skill should be used when the user asks to "draft a pleading", "format an Oregon court document", "apply UTCR 2.010", "UTCR formatting", "build a caption", "create a declaration", "format a motion", "notice of hearing", or "proposed order" for any Oregon circuit court. Covers Uniform Trial Court Rules (UTCR) 2.010 page formatting, UTCR 2.100 caption requirements, UTCR 2.110 document titles, UTCR 2.120 confidential information / SSN redaction, numbered paragraphs, line-numbered pleading paper, signature blocks, exhibit lists and cover pages, and citation format per the Oregon Appellate Courts Style Manual.
az-statewide-format
by codearrangerUse when the user asks to "format an Arizona pleading", "draft an Arizona court document", "apply Ariz. R. Civ. P. 10", "build an Arizona caption", "format an Arizona complaint", or "format an Arizona motion" for any Arizona state court — Superior Court, Justice Court, or family-law proceeding. Triggers: "Arizona caption", "Ariz. R. Civ. P. 10", "form of pleadings Arizona", "Rule 7.1 motion", "AZTurboCourt", "Arizona e-filing", "certificate of service Arizona", "line numbering", "Arizona motion format", "how do I format an Arizona complaint". Covers the Ariz. R. Civ. P. 10 caption form, numbered paragraphs, Rule 11 signature block with State Bar bar number, Rule 5 electronic filing via AZTurboCourt, certificate of service, line-numbered pleading paper, footer conventions, and Arizona citation format.
ca-statewide-format
by codearrangerUse when drafting or formatting California court documents. Triggers include "draft a pleading", "format a California court document", "CRC 2.100", "build a caption", "create a declaration", "format a motion", "notice of motion", "two-hole punch California", "California caption format", "declaration for California court", "line numbers on pleading paper", "California Style Manual citation". Covers California Rules of Court (CRC) 2.100–2.119 page-format requirements (paper, margins, font, line spacing, line numbers, footers, two-hole punch), CRC 2.111 caption, CRC 2.112 document titles, numbered lines, declaration verification under Code Civ. Proc., § 2015.5, exhibit attachment, and California Style Manual (6th edition) citation format. Also covers e-filing basics via Odyssey eFileCA.
eoir-immigration-courts
by codearrangerUse this skill to understand the EOIR immigration-court system and filing rules — the structural/formatting anchor for every EOIR filing. Covers the Executive Office for Immigration Review (EOIR): ~70 courts, immigration judges, Board of Immigration Appeals, jurisdiction, venue, change of venue, master-calendar vs. individual-calendar hearings, and the procedural authority (8 CFR Parts 1003/1240/1208 binding regulations + ICPM/BIA Practice Manual guidance). Triggers: "immigration court rules", "ICPM", "how do I file in immigration court", "EOIR filing format", "ECAS", "eFiling", "master calendar hearing", "change of venue", "page limits immigration court", "proof of service EOIR", "cover page", "which immigration court". Produces filing checklists, caption/cover-page/service scaffold, venue worksheets. Composes with eoir-removal-defense, bia-appeals, and immigration-fact-check.
co-statewide-format
by codearrangerUse when drafting Colorado court documents — pleadings, motions, declarations, proposed orders under **C.R.C.P. 10** (form of pleadings) and **Chief Justice Directive 11-01** (statewide filing standards). Covers the **flexible caption** (four-row table: court-type / county / address; parties; attorney/pro se + COURT USE ONLY box; title), numbered paragraphs, signature blocks (with Colorado attorney registration #), exhibits, footer with page count, line numbering, and citation format. Triggers: "draft a Colorado pleading", "C.R.C.P. 10", "CJD 11-01", "flexible caption", "Colorado declaration".
in-statewide-format
by codearrangerUse when drafting Indiana court documents — pleadings, motions, declarations, proposed orders, formatting under **Indiana Trial Rule 5(E)** (paper size, margins, font, line spacing, footer), **T.R. 10** (caption, paragraph numbering), **T.R. 11(A)** (signature block), **Odyssey e-filing conventions**, and citation format per the Indiana Supreme Court Rules on Citation. Triggers: "format an Indiana pleading", "Indiana caption", "T.R. 5(E)", "T.R. 10", "Trial Rule 11 signature", "Indiana declaration", "Odyssey eFile Indiana".
mi-statewide-format
by codearrangerUse when formatting a Michigan pleading or court document. Triggers include "Michigan caption", "MCR 1.109", "MCR 2.113", "MiFILE", "proof of service Michigan", "P-number", "how do I format a Michigan complaint". Covers MCR 1.109 (document format, legibility, paper, caption, the MCR 1.109(E) signature requirement and sanctions, verification), MCR 2.113 (form of pleadings, caption, numbered paragraphs), the Michigan caption structure, the attorney's State Bar "P-number", proof of service under MCR 2.107, line-numbered pleading-paper conventions, the running footer, and Michigan citation format per the Michigan Appellate Opinion Manual. Canonical home for marketplace layout conventions for Michigan filings.
ny-statewide-format
by codearrangerUse when drafting or formatting any document for a New York state court (Supreme Court, County Court, Civil Court of the City of New York, District Court, City Court, or Town/Village Justice Court). Triggers include 'draft a New York pleading', 'format an affidavit', 'apply 22 NYCRR § 202.5', '22 NYCRR 202.5-b NYSCEF format', 'build a New York caption', 'verify NY citation style', 'Tanbook citation', 'CPLR caption', 'verified complaint format', 'affirmation under CPLR 2106'. Covers **22 NYCRR § 202.5** page/font/margin requirements, **22 NYCRR § 202.5-b** NYSCEF electronic-filing, **New York caption** (CPLR 305(a) / CPLR 2101), document-title conventions, **verified vs. unverified pleading** distinction (CPLR 3020–3021), affidavit (CPLR 2309) vs. affirmation (CPLR 2106) signature blocks, and **Tanbook** citation format.
oh-statewide-format
by codearrangerUse when drafting any Ohio court filing — applies Ohio Civ. R. 10 caption + signature requirements, the common local-rule format conventions adopted by most Ohio Common Pleas and Municipal Courts (Letter paper; 1-inch margins with 1.5-inch top on first page for caption; 12-point minimum body font; double-spaced body), the Ohio public- domain citation format `YYYY-Ohio-NNNN` mandatory in appellate cases since 2002, and the affidavit-vs- declaration terminology distinction (Ohio uses "affidavit" under R.C. 2319.04 + Civ. R. 56; "declaration under penalty of perjury" is federal practice). Triggers include "Ohio court filing format", "Ohio Civ. R. 10", "Ohio caption", "Ohio attorney registration number", "Ohio public-domain citation", "Ohio affidavit format", "first page caption Ohio", "Common Pleas local rules format".
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.