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...
retry-and-backoff-patterns
by PranavNagrechaImplementing resilient integration retry logic in Salesforce: exponential backoff, jitter, idempotency keys, dead-letter queues, and circuit breaker patterns for Apex callouts. Use when designing callout retry behavior, preventing thundering-herd issues, or handling persistent integration failures. NOT for Apex async patterns without callouts (use apex-queueable-patterns). NOT for callout governor limits (use callout-limits-and-async-patterns).
financial-data-quality
by PranavNagrechaUse when validating FinancialAccount record integrity in Financial Services Cloud, detecting duplicate financial records, or reconciling FSC data against core banking and custodial source systems. Trigger keywords: FinancialAccount validation, FSC duplicate detection, financial record reconciliation, stale household KPIs, FinancialHolding data quality, FSC data integrity. NOT for generic Salesforce data quality, Duplicate Rules setup on standard objects, or bulk data migration execution.
custom-iterators-and-iterables
by PranavNagrechaUse this skill when implementing the Iterable<T> or Iterator<T> interfaces in Apex to create custom traversal logic, build lazy-evaluation data sources for Batch Apex, or stream large result sets without materializing an entire List. Trigger keywords: custom iterator, Iterable interface, Iterator interface, batch start iterable, lazy evaluation apex, streaming apex query, paginated batch. NOT for standard list iteration (use for-each on List directly), NOT for Batch Apex fundamentals (use batch-apex-patterns), NOT for Apex triggers or synchronous bulk patterns.
lwc-reactive-state-patterns
by PranavNagrechaHow LWC reactivity actually works after Spring '20 (API v48+) — every class field is reactive on reassignment, but @track is still required for in-place mutation of plain object/array contents, and Date / Set / Map mutations are NEVER observed. Covers the renderedCallback infinite-loop trap, reactive-getter caching rules, and when @track is genuinely needed today. NOT for @wire reactive parameters (see lwc/wire-adapters), NOT for Lightning Data Service caching (see lwc/ldws-and-uirecordapi), NOT for cross-component reactive state (see lwc/message-channel-patterns and lwc/state-management-with-modules).
agentforce-production-readiness-checklist
by PranavNagrechaUse when an Agentforce agent is being moved from build/sandbox to live end-user traffic and the team needs a comprehensive readiness gate covering coverage testing, Trust Layer config, guardrails, cost telemetry, observability, rate limits, permissions, rollout strategy, rollback plan, and performance benchmarks. Triggers: 'we want to ship our Agentforce agent next week', 'pre-prod readiness review for our Service Agent', 'what do we need before turning the agent on for real customers', 'agent went live and is hallucinating, what should we have caught', 'cost monitoring for our internal sales agent', 'rollout strategy from internal pilot to GA'. NOT a substitute for the lighter sign-off ritual in agent-deployment-checklist (use this skill instead when the team needs technical depth on what to actually verify, not just sign-off rows). NOT for Trust Layer feature configuration in isolation (use einstein-trust-layer). NOT for designing the guardrails themselves (use agentforce-guardrails) or the test harness (us
agent-script-dsl
by PranavNagrechaAuthoring and managing Agentforce agent definitions using the declarative Agent Script DSL (.agent files) and associated metadata types. Use when creating agents in source control, debugging agent metadata, or understanding the metadata lifecycle of GenAiPlugin/GenAiPlanner/BotVersion types. Triggers: 'how do I deploy an Agentforce agent using source control', 'what metadata types make up an Agentforce agent', 'agent test run command failing in CI pipeline', 'GenAiPlugin vs GenAiPlanner metadata relationship'. NOT for Apex-based agent actions (use custom-agent-actions-apex). NOT for UI-based agent creation (use agentforce-agent-creation).
agentforce-agent-handoff-patterns
by PranavNagrechaUse when designing how an Agentforce agent transfers the conversation to a human agent (Omni-Channel), to another bot/agent, or to an alternate workflow — including context package, deflection, escalation triggers, and user messaging. Triggers: 'agent to human handoff', 'agentforce escalate to omni channel', 'agent to agent handoff', 'transfer conversation with context', 'agent deflection fallback'. NOT for topic selector design (see agent-topic-design).
mulesoft-salesforce-connector
by PranavNagrechaDesigning and configuring MuleSoft Anypoint Salesforce Connector flows: API selection (SOAP/REST/Bulk/Streaming), OAuth 2.0 JWT Bearer auth, watermark-based incremental sync with Object Store, batch processing with record-level error isolation, and replay topic subscriptions. Use when building Mule 4 flows that read from or write to Salesforce, migrating from Mule 3 watermark to Mule 4 Object Store, or troubleshooting connector authentication and API limits. NOT for native Salesforce-to-Salesforce integration without MuleSoft (use platform-events-integration or change-data-capture-integration). NOT for generic REST callout patterns from Apex (use rest-api-patterns).
mulesoft-anypoint-architecture
by PranavNagrechaUse when designing or evaluating MuleSoft Anypoint Platform deployment topology, runtime model selection, API governance with API Manager, or Anypoint Exchange strategy. Trigger keywords: CloudHub, Runtime Fabric, Anypoint Platform, API Manager, Anypoint Exchange, MuleSoft runtime model, private space, Anypoint Security. NOT for Salesforce-native integration patterns (use integration/api-led-connectivity), NOT for Salesforce Connector configuration in MuleSoft (use integration/mulesoft-salesforce-connector), NOT for MuleSoft flow implementation or DataWeave scripting.
crm-analytics-vs-tableau-decision
by PranavNagrechaUse when deciding between CRM Analytics (formerly Einstein Analytics / Tableau CRM) and Tableau Desktop, Tableau Server, or Tableau Cloud for a Salesforce-centric analytics requirement. Triggers: 'CRM Analytics vs Tableau', 'which BI tool for Salesforce', 'Tableau for Salesforce data', 'Einstein Analytics vs Tableau', 'analytics platform decision', 'licensing comparison CRM Analytics Tableau', 'Tableau Next', 'Tableau+ for Salesforce'. NOT for implementation guidance on configuring CRM Analytics datasets, recipes, or Tableau workbooks — use admin/einstein-analytics-basics for that.
tableau-embedding-in-lightning
by PranavNagrechaEmbedding Tableau dashboards (and Tableau Pulse insights) inside Lightning App / Record / Home pages — Tableau Embedding API v3 in an LWC, the connected-app + JWT trust pattern for SSO from Salesforce to Tableau, row-level security so a Salesforce user only sees their data in Tableau, CSP / Trusted Sites configuration for the Tableau host, and the Tableau Viz Lightning Web Component (drag-and-drop alternative to a custom LWC). NOT for building Tableau dashboards / data sources (that's Tableau-side work), NOT for CRM Analytics (Tableau is the separate product; see data/crm-analytics-patterns).
tableau-salesforce-connector
by PranavNagrechaTableau ↔ Salesforce integration patterns: Tableau Salesforce connector, Tableau for Salesforce, CRM Analytics alternative, Data Cloud + Tableau, embedded Tableau dashboards. Choose between connector modes (live, extract, direct-to-Data-Cloud). NOT for CRM Analytics Studio (use crm-analytics-foundation). NOT for generic Tableau Server setup.
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.