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...
sales-roleplay
by arkangelaiSimulate a prospect persona (skeptical CFO, busy CMO, paranoid CISO, hostile committee) so a rep can practice the next meeting without burning the real prospect. Coaches against the Arkangel sales submarine — UFC, qualify, pain funnel, quantification, next-step — and scores Sandler + MEDDIC adherence at the end.
clinical-report-writer
by arkangelaiDrafts Colombian clinical reports — epicrisis, evolución diaria, nota operatoria, resumen de egreso, historia clínica de ingreso, interconsulta — following MinSalud Resolución 1995/1999 (historia clínica), Resolución 1552/2013 (RIPS), and the format expected by EPS auditors. Use it when the user pastes raw clinical data (notas del médico, paraclínicos, signos vitales, evolución) and asks to produce a formal clinical document, or when an IPS needs to standardize the format of an outgoing record before it goes to the EPS.
medical-invoice-medical-audit
by arkangelaiRuns the clinical-pertinence audit of a Colombian medical invoice (valid CIE-10 diagnosis, adherence to MinSalud Guías de Práctica Clínica, signed medical order with RETHUS-registered professional, procedures with indication and operative note, medications with correct dose/duration, justified diagnostic aids, inpatient stay with admission criteria and daily progress, and epicrisis with discharge plan). Generates medical_checklist_output.json with findings cited to the clinical history. Use it when the user asks to audit the clinical side of a case, review procedure pertinence, or run the medical sub-agent of the pipeline.
medical-invoice-financial-audit
by arkangelaiRuns the financial and anti-fraud audit of a Colombian medical invoice (active IPS contract with modality, affiliate plan and applicable tariff sheet, SOAT/ISS/proprietary manual with correct UVB/UVR, CUPS/CUM/INVIMA homologation, liquidation with surcharges and surgical access rules, packages vs. events, coverage limits and grace periods, copays, and 14 anti-fraud rules covering DIAN consecutive numbering, double-billing SOAT+EPS+ARL, overlapping stays, post-mortem services, upcoding, and unbundling). Generates financial_checklist_output.json. Use it when the user asks to audit tariffs/contracts/fraud or run the financial sub-agent of the pipeline.
medical-invoice-admin-audit
by arkangelaiRuns the administrative audit of a filed Colombian medical invoice (patient identity, IPS contract, RIPS structure, DIAN invoice, prior authorization, signed clinical history, cross-document consistency, and filing timeliness). Emits findings with traceable evidence and generates admin_checklist_output.json. Use it when the user asks to audit the administrative side of a case, resume a failed audit, or run the admin sub-agent of the pipeline.
hospital-devolucion-response-sender
by arkangelaiSends the IPS's finished glosa responses back to an EPS via Gmail using `gogcli`, as a single consolidated Excel attachment with one row per glosa showing both the EPS objection and the IPS response side by side. Recipient resolved from the sender task context, formal Spanish body referencing the Res. 3047/2008 / Res. 416/2009 response window, delivery recorded on the sender task and on each glosa task. Use it once a human auditor triggers "Enviar" on a group of finished glosa responses for one pagador.
hospital-devolucion-gmail-intake
by arkangelaiWatches a Gmail inbox with `gogcli` for EPS→IPS glosa notifications, classifies emails as glosa batches, downloads Excel/CSV attachments, and creates a `hospital_devolucion_batch` task in Salmona with the file attached. Use it when the hospital wants to automatically process incoming glosas sent by an EPS via email, configure the devolucion watcher, or reprocess a glosa email that was missed.
hospital-devolucion-audit
by arkangelaiAnaliza UNA glosa recibida de una EPS (un ítem objetado sobre una factura) y produce la respuesta argumental — disputar o aceptar, con valor a defender y a aceptar, y la justificación clínica/administrativa/financiera. Aplica DAMA-UK, PERT-CLIN o FIN-CTR según el prefijo del código causal. Emite glosa-response.json. Usar cuando la IPS recibe una glosa y necesita construir su respuesta dentro del plazo de 15 días hábiles (Res. 2284/2023).
hospital-devolucion-batch-parse
by arkangelaiLee el Excel/CSV de glosas que la EPS envió a la IPS y crea una task hija por cada fila — una task = una glosa = un ítem objetado. Cada hija arranca el skill hospital-devolucion-audit. Sin agregaciones, sin agrupación por num_documento. La task envelope transita a archived al terminar.
prior-authorization-review
by arkangelaiReview pre-autorización (prior authorization) requests for Colombian EPS — assesses medical necessity, validates the requested service against the Plan de Beneficios en Salud (PBS, ex-POS), checks contract coverage between EPS and IPS, and emits an approval/denial/conditional decision with the specific causal and references. Use it when the user pastes a pre-autorización solicitud (medication, procedure, ayuda diagnóstica, hospitalización), asks "¿se debe autorizar X?", or needs to draft the formal response to an IPS requesting authorization.
scout-grants
by arkangelaiFind grant opportunities, evaluate eligibility and fit, and create a clean opportunity brief. Use when starting from zero, triaging new calls, or deciding whether an opportunity is worth drafting.
medical-invoice-claim-denial-generator
by arkangelaiProduces the formal PDF of a Colombian medical invoice glosa (claim denial) from the consolidated audit output, with institutional header, executive summary, per-causal (Anexo 6, Res. 3047) findings table, legal and clinical justification, evidence cited by file and page, and a legal footer with the 15 business-day response deadline. Supports incremental versions (v1, v2, ...) when fix-review requests changes. Use it when the case is consolidated (label `auto-denial` or post human-review) and needs the formal document that will be sent to the IPS.
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.