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...
sf-customer-success
by sfdc-brendanCustomer Success Manager / Technical Account Manager that owns the post-sale relationship — adoption, health scores, expansion, and renewal. Shifts the conversation from "why buy Salesforce" to "how to get more value from what you already own." Creates success plans, adoption scorecards, health check reports, expansion opportunity maps, QBR decks, risk mitigation plans, and feature adoption playbooks. TRIGGER when: success planning, adoption tracking, health scores, customer health checks, expansion opportunity mapping, QBR preparation, renewal strategy, risk mitigation, feature adoption analysis, customer feedback synthesis, onboarding-to-value planning, license utilization reviews, or executive business reviews. DO NOT TRIGGER when: pre-sale strategy (use sf-dse), deal-level selling or demo prep (use sf-se), requirements for new projects (use sf-ba), writing Apex code (use sf-apex), building LWC (use sf-lwc), or configuring metadata (use sf-metadata).
sf-release-manager
by sfdc-brendanSalesforce Release Manager that owns the delivery pipeline — CI/CD, environment strategy, release cadence, and change management. Bridges "it works in dev" to "it's live in production." Creates release plans, environment strategies, CI/CD pipeline designs, deployment checklists, rollback procedures, change management plans, and release notes. TRIGGER when: user plans releases, designs environment strategy, builds CI/CD pipelines, creates deployment checklists, writes rollback procedures, manages change management, handles sandbox management, compares orgs, sets release cadence, designs hotfix processes, or asks for release-management-level review of deployment plans. DO NOT TRIGGER when: writing Apex code (use sf-apex), building LWC (use sf-lwc), making architecture decisions (use sf-sa), gathering requirements (use sf-ba), executing individual deploys (use sf-deploy).
sf-lwc-page-composition
by sfdc-brendanApp Builder-aware component design for Lightning Web Components. Covers Lightning page column layouts, component configuration via meta.xml targets, consistent card height/alignment, cross-component communication contracts (LMS, events, URL params), and design-time preview patterns. Use when building components for record pages, app pages, home pages, or when the user mentions App Builder, page layout, record page, component placement, or configurable components.
sf-lwc-review
by sfdc-brendanDesign quality audit and review for Lightning Web Components. Scores existing LWC code against SLDS 2 compliance, UX patterns, accessibility, styling quality, and visual hierarchy using a combined 300-point rubric across all design skills. Generates actionable fix lists and before/after improvement plans. Use when reviewing LWC code, auditing design quality, checking accessibility, or when the user mentions review, audit, score, lint, design debt, or quality check.
sf-lwc-styling
by sfdc-brendanUtility-first CSS patterns for Lightning Web Components inspired by Tailwind CSS and Shadcn component design, mapped entirely to SLDS 2 global styling hooks with zero external dependencies. Provides reusable CSS class systems, component recipes (cards, badges, tables, forms, modals), and spacing/sizing scale references. Use when styling LWC, creating custom CSS classes, building UI components, or when the user mentions Tailwind, utility classes, Shadcn, CSS patterns, or component recipes.
sf-lwc-theming
by sfdc-brendanCustom theme creation and brand token systems for Lightning Web Components. Covers SLDS 2 theme extension, brand color palettes, multi-brand support, component-level theme overrides, and Experience Cloud theme tokens. Light mode is the default; dark mode is available as an opt-in enhancement. Use when creating custom themes, building brand systems, customizing SLDS, or when the user mentions theming, branding, custom colors, brand tokens, or white-labeling.
sf-lwc-ux
by sfdc-brendanUX patterns, interaction design, and accessibility for Lightning Web Components. Applies Shadcn-inspired component composition, modern interaction patterns (loading states, skeleton screens, empty states, error boundaries), WCAG 2.1 AA accessibility, and responsive layout design within LWC platform constraints. Use when building LWC user interfaces, improving UX quality, adding accessibility, creating layouts, or when the user mentions UX, accessibility, a11y, responsive, loading states, or user experience.
sf-ba
by sfdc-brendanSalesforce Business Analyst that owns the requirements lifecycle, process analysis, user stories, UAT planning, and training materials. Sits at the intersection of business process and platform capability. Translates between stakeholders and technical teams. Creates requirements docs, process maps, acceptance criteria, UAT scripts, backlog items, and adoption materials. TRIGGER when: user gathers or documents requirements, writes user stories, maps business processes, plans UAT, creates training materials, triages backlog requests, defines acceptance criteria, conducts stakeholder analysis, or asks for BA-level review of requirements or process flows. DO NOT TRIGGER when: writing Apex code (use sf-apex), building LWC (use sf-lwc), making architecture decisions (use sf-dse), configuring org metadata directly (use sf-metadata), or deploying (use sf-deploy).
sf-demo-engineer
by sfdc-brendanSalesforce Demo Engineer responsible for demo environment setup, sample data generation, demo reset procedures, environment runbooks, and demo reliability. Owns the technical infrastructure that makes demos repeatable and believable. TRIGGER when: user sets up demo orgs, generates sample/persona data, creates demo reset procedures, builds demo data plans, maintains demo environments, maps environment dependencies, curates persona-based test data, or asks for demo reliability review. DO NOT TRIGGER when: demo narrative or strategic framing (use sf-dse), deal strategy or account planning (use sf-se), requirements gathering or user stories (use sf-ba), production deployments (use sf-deploy).
sf-dse
by sfdc-brendanDistinguished Solutions Engineer strategic advisor with executive-level Salesforce platform expertise. Operates at high altitude across deals, accounts, and business units. Creates reusable strategic assets (POVs, executive briefings, architecture narratives, demo scripts, GTM plays). Provides technical consultancy on must-win deals and complex architectures. Coaches SE teams on executive engagement and demo excellence. TRIGGER when: user needs strategic Salesforce guidance across multiple clouds/products, creates executive-facing deliverables, designs cross-cloud architectures, builds reusable demo content, prepares C-suite presentations, develops GTM plays, or asks for DSE-level review of solutions. DO NOT TRIGGER when: single-product implementation (use the matching sf-* skill directly), Apex-only code (use sf-apex), LWC-only work (use sf-lwc), or narrow deploy tasks (use sf-deploy).
sf-industry-advisor
by sfdc-brendanDeep vertical expertise and regulatory context for Salesforce implementations. Enriches every other role with industry-specific knowledge — regulations, terminology, KPIs, buying patterns, and process patterns per vertical. TRIGGER when: industry-specific process mapping, regulatory compliance requirements, vertical terminology translation, industry KPIs/benchmarks, industry data models, industry-specific Salesforce clouds (Health Cloud, Financial Services Cloud, Communications Cloud, Manufacturing Cloud, Consumer Goods Cloud, Public Sector Solutions, Education Cloud, Nonprofit Cloud), cross-industry pattern transfer, or any conversation where vertical context materially changes the recommendation. DO NOT TRIGGER when: generic platform work without industry context (use the matching sf-* skill), Apex code (use sf-apex), solution architecture without vertical nuance (use sf-sa).
sf-sa
by sfdc-brendanSalesforce Solution Architect that owns the technical design layer between strategy and requirements. Translates business requirements into platform blueprints — data model, integration architecture, security model, automation strategy, and environment planning. Creates solution design documents, data model diagrams, integration architectures, technical decision logs, build-vs-buy analyses, and environment strategies. TRIGGER when: user designs solutions, models data, plans integrations, makes technical decisions (declarative vs. custom, build vs. buy), defines environment strategy, evaluates technical feasibility, or asks for SA-level review of a solution design. DO NOT TRIGGER when: executive strategy or GTM plays (use sf-dse), requirements gathering or user stories (use sf-ba), writing Apex code (use sf-apex), building LWC (use sf-lwc), configuring Flows (use sf-flow), or deploying metadata (use sf-deploy).
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.