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...
xb-hague-child-abduction-1980-intake
by dislovelhlBuilds a supervised, trauma-informed Hague Convention on the Civil Aspects of International Child Abduction (25 October 1980, HCCH Conv. 28) intake packet, organizing habitual-residence facts, wrongful-removal-or-retention timeline, Article 12 one-year window analysis, Article 13(b) grave-risk and child-objects exception facts, Central Authority routing questions, and family-lawyer review items. Use only for supervised cross-border intake assembly with live HCCH status verification, mandatory trauma-informed escalation, and lawyer-review routing; never to file a return petition, contact Central Authorities, advise on custody, or decide return.
xb-eu-us-ediscovery-blocking-statute-screen
by dislovelhlBuilds a supervised EU-US e-discovery conflict-of-authorities issue map covering Article 48 of Regulation (EU) 2016/679 (GDPR), French Loi nº 80-538 (the French blocking statute), the Hague Evidence Convention of 18 March 1970, 28 U.S.C. §§ 1782 and 1783, and Federal Rules of Civil Procedure 26-37, organizing custodian and data-subject inputs, requesting-court facts, EU controller / processor posture, blocking-statute exposure, Hague Evidence channel candidacy, and EU-and-US litigation-counsel review items. Use only for supervised conflict-of-authorities issue spotting and counsel handoff, not autonomous preclusion, enforceability, or production decisions. Highest UPL surface in Wave-3.
xb-us-eu-data-transfer-assessment
by dislovelhlBuilds a US-EU data transfer assessment packet, organizing transfer facts, exporter/importer roles, mechanism candidates, SCC and DPF evidence, supplementary measures, vendor questions, and privacy-counsel review flags. Use only for supervised EU Wave-1 legal-agent workflows, not for autonomous legal advice, final filing, certification, negotiation, or regulator-facing action.
ca-multilingual-translation
by dislovelhlTranslates client documents and communications between English, French, Spanish, Chinese, and other supported languages for non-evidentiary use, preserving legal meaning where feasible and expressly not replacing certified translation. Use whenever a non-English/French document is uploaded for review or client communication requires translation.
uk-pre-action-protocol-civil-claim-intake
by dislovelhlBuilds a supervised England & Wales pre-action protocol civil claim intake organizer under the Civil Procedure Rules 1998, the CPR Practice Direction on Pre-Action Conduct and Protocols, the relevant subject-matter pre-action protocols, and the Limitation Act 1980, organizing claimant and defendant facts, claim type and protocol selection, factual chronology, documents to disclose pre-action, alternative dispute resolution and Part 36 considerations, costs-and-conduct exposure, and a Limitation Act 1980 currency flag. Use only for supervised pre-action intake and solicitor handoff, not autonomous letter-of-claim drafting, final limitation computation, claim issuance, or settlement-strategy decisions.
uk-data-transfer-post-brexit-tra-packet
by dislovelhlBuilds a supervised UK post-Brexit international data transfer risk assessment (TRA) packet under the UK GDPR and Data Protection Act 2018, organizing controller/processor and importer facts, transfer purpose, lawful-basis and Article 6 / Article 9 special-category facts, transfer mechanism (UK adequacy regulations including the UK-US Data Bridge, UK International Data Transfer Agreement (IDTA), UK Addendum to the EU SCCs, BCRs, Article 49 derogations), importer-jurisdiction surveillance-law facts, additional or supplementary safeguards, ICO TRA Tool steps, and privacy-counsel review items. Use only for supervised UK TRA intake and counsel handoff, not autonomous transfer approval, EU GDPR Chapter V conclusions, surveillance-law opinions, or final adequacy or supplementary-measures determinations.
xb-hague-service-1965-packet
by dislovelhlBuilds a supervised Hague Service Convention 1965 civil-service packet, organizing forum, destination state, document, translation, Central Authority, Article 10, status-table, and lawyer-review questions. Use only for cross-border procedural packet assembly with live HCCH status verification, not autonomous service or legal advice.
xb-ny-convention-arbitral-award-enforce
by dislovelhlBuilds a supervised New York Convention arbitral-award recognition and enforcement screening packet, organizing award facts, arbitration agreement evidence, seat and enforcement-state facts, Article V refusal-ground issue flags, live contracting-state and reservation checks, source verification, and lawyer-review items. Use only for cross-border enforcement issue spotting and attorney handoff, not autonomous legal advice, final enforceability conclusions, filings, or asset-enforcement action.
xb-fcpa-ukba-anti-bribery-screen
by dislovelhlBuilds a supervised US Foreign Corrupt Practices Act (FCPA) and UK Bribery Act 2010 (UKBA) anti-bribery screening packet, organizing transaction-counterparty facts, foreign-public-official screening, intermediary and third-party risk, books-and-records inputs, UKBA s. 7 failure-to-prevent adequate-procedures inputs, and anti-corruption-counsel review items. Use only for supervised compliance screening intake and counsel handoff, not autonomous transaction approval, sanctions or export-control screening, or final criminal-exposure determinations.
xb-ca-us-tax-treaty-issue-spot
by dislovelhlBuilds a supervised Canada-US tax treaty issue-spotting packet anchored on the Canada-US Tax Convention 1980 as amended through the Fifth Protocol 2007, organizing residence, permanent establishment, withholding, business profits, and limitation-on-benefits (LOB) facts, mapping I.R.C. § 894 (treaty-based return positions) and I.R.C. § 6114 / Treas. Reg. § 301.6114-1 (treaty-based return-position disclosure on Form 8833) inputs, and routing Article XXIX-A LOB, Canadian residence, and treaty-position-statement decisions to cross-border tax counsel. Use only for supervised issue-spotting and counsel handoff, not autonomous treaty-position conclusions, LOB eligibility determinations, Form 8833 filings, or final cross-border tax advice.
xb-export-control-ofac-eu-sanctions-screen
by dislovelhlBuilds a supervised cross-border OFAC, EU, and UK sanctions-screening flag map under 31 C.F.R. Ch. V (OFAC), the International Emergency Economic Powers Act (IEEPA) at 50 U.S.C. § 1701 et seq., EU restrictive-measures regulations including Council Regulation (EU) 2580/2001 and Council Regulation (EU) 833/2014, and the UK Sanctions and Anti-Money Laundering Act 2018 (SAMLA) c. 13. Organizes counterparty-identity facts, beneficial-ownership and 50%-rule facts, list-hit candidates across the OFAC Specially Designated Nationals (SDN) and Consolidated Sanctions lists, the EU consolidated financial-sanctions list, and the UK consolidated sanctions list, sectoral and dual-use considerations, EU Reg 833/2014 sectoral measures, UK post-2020 SAMLA-regime measures, live-list fetch pointers, and sanctions-counsel review items. Use only for supervised cross-border sanctions-screening intake and counsel handoff, not autonomous transaction approval, sanctions-clearance conclusions, export-control licensing determinations, O
arckit-mod-secure
by dislovelhlGenerate a MOD Secure by Design assessment for UK Ministry of Defence projects using CAAT and continuous assurance
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.