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...
el-auditor
by geocarp24Always-on weekly compliance sub-agent for the R9 plantel. Audits the stack against WI wholesaler law, TCPA (SMS), CAN-SPAM (email), Fair Housing Act, GDPR, and ADA web accessibility. Flags lawsuit-exposure before they become lawsuits.
el-analista
by geocarp24Always-on weekly executive dashboard sub-agent for the R9 plantel. Unifies outputs from Mercader + Posicionador + Escriba + Remitente + Cazador + Clasificador + Espía + Auditor plus CRM pipeline and revenue into a 3-paragraph executive brief Jorge reads Monday 7am CT.
remitente
by geocarp24El Remitente — email marketing sub-agent del plantel R9. 100% Airtable-native + Hostinger SMTP (pinnacle_mail.php endpoint) — CERO dependencia de servicios externos (Mailchimp/Beehiiv/ConvertKit). Modos: draft_campaign (redacta campaña desde Content_Queue/topic), schedule_send (scheduler de campañas + sequences), process_welcome (trigger on_subscribe del popup), process_drip (daily tick de secuencias activas), weekly_report (open/click/unsub stats a Telegram). Usa tablas Email_Subscribers + Email_Campaigns + Email_Templates + Email_Events. Envío real via PHP mail() desde deals@pinnaclegroupwi.com con SPF/DKIM/List-Unsubscribe. Tracking pixel + click redirect en el mismo endpoint. 1-click unsubscribe HMAC-signed compliant Gmail/Yahoo 2024+. Use when: 'send email campaign', 'draft newsletter', 'run El Remitente', 'email report', o cron triggers. Wraps: copywriting, content-humanizer, email-sequence, email-template-builder.
el-supervisor
by geocarp24Always-on meta-agent watchdog for the entire R9 plantel. Monitors every agent, cron, pipeline, API, and data flow. Detects drift, failures, and stuck pipelines. Auto-repairs what it safely can (ghost lead reset, endpoint re-trigger, rate limit backoff). Escalates to Telegram only when human judgment is needed. In evolve mode, observes 7d patterns and proposes concrete code/flow improvements. Objective: Jorge no tiene que estar detrás de nada — el sistema se autogobierna.
el-espia
by geocarp24Always-on daily competitor watchdog sub-agent for the R9 plantel. Scrapes competitor sites (homepage + pricing + landing pages), detects diffs vs prior scan (pricing changes, new offers, new CTAs, new pages), scores severity 0-10, and alerts Jorge when a competitor moves in a way worth reacting to.
el-clasificador
by geocarp24Always-on lead scoring sub-agent for the R9 plantel. Scores every inbound lead 0–100 (urgency + distress + property + timeline + motivation), classifies heat (Hot/Warm/Cold/Disqualify), proposes owner + action, and writes to Airtable Lead_Scores. Feeds Fer prioritization so hot leads get called first.
cazador
by geocarp24El Cazador — paid advertising audit + spend tracking sub-agent del plantel R9. Corre cada 3 días (ads_health) + semanal lunes (ads_deep). Wraps claude-ads skill suite (ads-audit, ads-google, ads-meta, ads-tiktok, ads-budget, ads-creative, ads-competitor, ads-landing, ads-math, ads-test). Tenant-aware: usa industry template real-estate para benchmarks. Lee data provista (exports, screenshots, pasted metrics) — NO scrapea cuentas (diseño anti-ban del ecosistema claude-ads). Output a Airtable Ad_Performance table. Alerts Telegram en budget waste o CPL drift. Use when user asks for 'ads audit', 'run El Cazador', 'paid ads review', 'spend check', 'campaign optimization', or cron triggers. Tenant zero = Pinnacle real-estate WI.
posicionador
by geocarp24El Posicionador — always-on SEO monitoring sub-agent for the SaaS multi-tenant real-estate stack. Runs SEO health check every 3 days + weekly deep SEO audit per tenant. Reads tenant config from agents/tenants/<slug>.json, invokes /seo audit + /seo local + /seo maps + /seo technical, writes structured results to Airtable SEO_Audits, alerts Telegram on regressions or issues below thresholds. Mobile-first priority (R7) — Core Web Vitals on mobile weighted heavy. Local SEO priority for Pinnacle WI market (R8 tenant-aware). Use when user asks for 'SEO audit', 'run El Posicionador', 'SEO health check', 'local rank check', or when cron triggers it. Wraps: seo, seo-audit, seo-local, seo-maps, seo-technical, seo-content, seo-schema, seo-drift, seo-google.
escriba
by geocarp24El Escriba — sub-sub-agente de El Posicionador. Especialista en copywriting SEO-driven para content marketing: blogs, news articles, Q&A pages, pillar pages. Objetivo: crear contenido que llene los SEO gaps detectados por El Posicionador, responda preguntas reales (ATP / People Also Ask), atraiga backlinks locales, y convierta el sitio del tenant en autoridad estatal. Modos: plan_week (content calendar), draft_article (produce blog/news/Q&A draft + metadata + schema), atp_mine (minar preguntas reales de la audiencia). Escribe drafts a Airtable Content_Queue; opcionalmente publica a WordPress en status=draft para revisión humana. Wraps: copywriting, content-humanizer, content-strategy, content-production, seo-content, seo-cluster, schema-markup, marketing-psychology.
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.