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...
add-new-entry
by kimtthWorkflow and tools for adding new entries from temp.md to the section files. Includes legend format, section reference, code tools, and common pitfalls. USE FOR: Adding new resources to the knowledge base. DO NOT USE FOR: Editing existing entries or restructuring sections.
update-app-count
by kimtthWorkflow for updating the popular LLM applications pool (section/x_llm_apps.md) using get_app_list_by_github_star.py. Covers full refresh, alternate exports, topic tuning, and common pitfalls. USE FOR: Refreshing the ranked GitHub applications list linked from applications.md. DO NOT USE FOR: Hand-curating application entries inside applications.md or adding GitHub star badges to the generated file.
update-llm-pool
by kimtthWorkflow for updating the LLM landscape paper pool (section/x_llm_papers.md) using fetch_llm_papers.py. Covers full re-fetch, resume from checkpoint, and adding new topics. USE FOR: Refreshing citation counts, expanding topic coverage. DO NOT USE FOR: Adding hand-curated entries to section files (use add-new-entry), updating RAG/Agent citation sections in best_practices.md (use update-cite-count).
activator-authoring-cli
by kimtthCreate alerts, notifications, and automated actions on Fabric data and events via Fabric REST API and `az rest` CLI. Use when the user wants to: (1) create, update, or delete an alert or notification flow, (2) send a Teams message, send an email, or run a Fabric item when something happens, (3) connect alert logic to Eventhouse, Eventstream, Real-time Hub, or Digital Twin Builder / Ontology data, (4) adjust thresholds, filters, event triggers, or actions, (5) troubleshoot or change an existing Activator/Reflex definition. Triggers: "create an alert", "notify me when", "let me know when", "take action when", "send me an email when", "send a teams message when", "run a pipeline when", "update an alert", "delete an alert", "activator rule"
activator-consumption-cli
by kimtthInspect existing alerts, notifications, and automated actions in Fabric via read-only REST API calls using `az rest` CLI. Use when the user wants to: (1) list existing alerts in a workspace, (2) inspect how an alert or notification is configured, (3) read and decode an Activator/Reflex definition (ReflexEntities.json), (4) list rules, sources, and actions behind an alert, (5) understand why an alert fires or what action it takes. Triggers: "show my alerts", "what alerts do I have", "inspect this alert", "show me the rule", "show me the action", "show me the source", "get reflex definition", "list activators", "activator details"
databricks-migration
by kimtthPort Databricks notebooks and jobs to Microsoft Fabric. Provides an exhaustive dbutils to notebookutils substitution table: fs operations (mount removal via OneLake Shortcuts), secret scope to Key Vault URL conversion, notebook run and exit, widget replacement with parameter-tagged cells, and library install replacement with Fabric Environments. Covers Unity Catalog three-level namespace reduction to Lakehouse two-level schemas, DBFS path conversion to OneLake, Databricks Jobs to Spark Job Definitions, MLflow tracking URI removal, and Photon to Native Execution Engine substitution. Use when the user wants to: (1) replace dbutils with notebookutils, (2) collapse Unity Catalog namespaces to Lakehouse schemas, (3) convert Databricks Jobs or Delta Live Tables. Triggers: "migrate from databricks", "databricks to fabric", "dbutils to notebookutils", "dbutils fabric", "unity catalog migration", "dbfs to onelake", "databricks notebook migration", "delta live tables fabric", "photon native execution".
dataflows-authoring-cli
by kimtthCreate, update, delete, and manage Fabric Dataflows Gen2 artifacts with Power Query M mashup definitions via CLI (az rest / curl). Uses az rest and curl against the Fabric REST API to author definitions containing base64-encoded mashup.pq, queryMetadata.json, and .platform parts. Supports creating dataflows with inline definitions, modifying mashup queries, binding connections, triggering Execute refresh jobs with typed parameter overrides, and exporting definitions for CI/CD. Use when the user wants to: (1) create a new Dataflow Gen2 with Power Query M queries, (2) update a dataflow mashup definition, (3) trigger a dataflow refresh job, (4) bind or manage dataflow connections, (5) set up CI/CD via definition export and import, (6) delete a dataflow, (7) configure staging destinations. Triggers: "create dataflow", "author dataflow", "Power Query M", "mashup document", "update dataflow definition", "refresh dataflow", "dataflow connection", "ETL dataflow", "dataflow CI/CD".
dataflows-consumption-cli
by kimtthMonitor, inspect, and discover Fabric Dataflows Gen2 via read-only CLI operations (az rest / curl). List dataflows across workspaces, decode base64 definitions to inspect Power Query M queries and queryMetadata.json, discover typed parameters with defaults, poll refresh operations for status, retrieve job history with timing and error details, and classify queries by staging settings. Use when the user wants to: (1) list dataflows, (2) inspect a dataflow definition and decode its mashup, (3) discover parameters, (4) check refresh status, (5) retrieve job history, (6) analyze staging settings, (7) examine connections and data source bindings. Triggers: "dataflow status", "refresh history", "dataflow monitor", "list dataflows", "dataflow parameters", "explore dataflow", "inspect dataflow", "dataflow run status".
dataflows-save-as-authoring-cli
by kimtthAssess, plan, and execute dataflow Gen1 → Gen2.1 CI/CD save-as operations via CLI (az rest / curl) against both Power BI REST and Fabric REST APIs. Scan workspaces or entire tenants for Gen1 dataflows, evaluate save-as readiness with seven risk signals (incremental refresh, BYOSA storage, Power Automate triggers, pipeline dependencies, linked entities, DirectQuery, caller-not-owner), produce a Save-As Readiness Snapshot (markdown + JSON), and invoke the SaveAsNativeArtifact API to create upgraded Gen2.1 copies of Gen1 dataflows. Use when the user wants to: (1) discover Gen1 dataflows in a workspace or tenant, (2) assess save-as readiness and risk signals, (3) upgrade or migrate Gen1 into a Gen2.1 copy, (4) validate post-save-as data integrity, (5) detect residual Gen1 references. Triggers: "save Gen1 dataflow", "convert dataflow Gen1", "upgrade dataflow", "migrate dataflow", "dataflow readiness", "Gen1 to Gen2", "dataflow save-as assessment", "saveAsNativeArtifact", "dataflow save-as scan".
fabric-alm-cicd
by kimtthPlan, implement, review, and troubleshoot Microsoft Fabric ALM and CI/CD workflows using Git integration, deployment pipelines, Variable Libraries, Fabric REST APIs, fabric-cicd, GitHub Actions, or Azure DevOps. Use when the user asks about source control, deploy, promote, release, dev/test/prod, environment variables, deployment pipeline automation, Git sync, fabric-cicd, or Fabric item definition validation.
fabric-api-discovery
by kimtthDiscover Fabric APIs, OpenAPI specs, item schemas, and best practices using the Fabric MCP Server. Use when exploring available Fabric workloads, looking up API specifications, finding item definition formats, or managing OneLake files programmatically. All MCP tools run locally for reference.
fabric-core
by kimtthCore Microsoft Fabric platform reference: topology, authentication, token scopes, REST API base URL, pagination, long-running operations, throttling, workspace and item resolution, OneLake access, and common gotchas. Use this skill whenever working with Fabric REST APIs, managing workspaces/items, or troubleshooting auth errors.
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.