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...
kongcode-backup-native
by 42UActivate when the user asks to back up the kongcode database, export the graph, snapshot SurrealDB, or save a copy for restore into another SurrealDB instance. Triggers on "back up kongcode", "export the database", "snapshot memory", "dump kongcode to disk". Use this skill for the **lossless** path when the target is also SurrealDB.
kongbrain
by 42UActivate when user mentions "search memory", "recall", "remember", "core memory", "introspect", "memory status", "what did we do", "past sessions", "identity", "soul", or when you need to store/retrieve persistent knowledge across sessions.
kongcode-backup-jsonl
by 42UActivate when the user wants to export kongcode for import into a non-SurrealDB system — Postgres + pgvector, Neo4j, OpenSearch, a custom store, or any system that ingests JSON. Triggers on "export kongcode to JSON", "dump kongcode for ingestion", "migrate kongcode off SurrealDB". Use this skill when the destination is not SurrealDB; for SurrealDB-to-SurrealDB use `kongcode-backup-native`.
kongcode-web-ui
by 42UOpen the kongcode read-only web UI to explore the memory graph (dashboard, memory/concept browsers, graph explorer) in a browser. Use when the user asks to see/visualize/inspect what kongcode has stored.
kongcode-restore-jsonl
by 42UActivate when the user wants to restore/import a kongcode JSON-Lines backup (produced by scripts/backup-jsonl.mjs) back into a SurrealDB kongcode graph, or merge one machine's kongcode export into another. Triggers on "restore kongcode from JSON", "import the jsonl backup", "merge kongcode graphs", "load my kongcode dump". Counterpart to kongcode-backup-jsonl.
kongcode-release
by 42UEnd-to-end procedural skill for shipping a new kongcode version. Bumps all 6 version surfaces atomically, commits, tags, pushes, and verifies CI green with the correct exit-code pattern. Use BEFORE running `git push` on a release commit, not after.
kongcode-health
by 42UActivate when the user asks about kongcode status, health, whether memory is working, before extracting knowledge from a new source, or when recall/write operations appear to be failing. Also activate for phrases like "is kongcode working", "check memory", "pipeline health", "anything broken".
kongcode-forget
by 42USelectively and REVERSIBLY forget stored memories/concepts (privacy / declutter) — soft-deactivate content matching a query or date so it stops surfacing in retrieval. Use when the user wants sensitive or unwanted data out of their kongcode graph.
kongcode-backup-semantic
by 42UActivate when the user wants to send the kongcode knowledge core (concepts, memories, skills, reflections, artifacts, soul) to another agent or system WITHOUT the transcript volume (turns, retrieval_outcomes, metrics). Triggers on "transfer knowledge to ikong", "share kongcode brain", "extract just the concepts", "give my graph to another agent". For full snapshot use `kongcode-backup-native`; for non-SurrealDB targets use `kongcode-backup-jsonl`.
synthesize-sources
by 42UActivate when the user wants a comparison, contrast, or synthesis across 2+ sources already in the graph. Produces meta-concepts that link back to the original source gems, earning the graph compound value from the cross-source edges.
knowledge-gap-scan
by 42UActivate when the user wants to know what they DO and DON'T know about a topic, before starting research or a project. Turns the graph from a reference library into an active planning tool by reporting coverage and explicit gaps.
supersede-stale
by 42UActivate when a recalled or injected concept is contradicted by current code, a newer source, or a user correction. Use this to demote stale knowledge in realtime rather than letting the batch daemon eventually catch it — stale concepts compete with fresh ones in recall and poison grounding.
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.