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...
model-development-workflow
by informatics-isi-eduUse when STANDING UP a new ML pipeline or onboarding to one for the first time — the cycle-zero work that has to happen before any hypothesis-driven experiment can start. Covers the end-to-end bootstrap: schema design → create small representative dataset → validate features → dry run → small-data run → first full-scale production run. Teaches the three-tier pattern (dry_run → small dataset → full dataset) that catches config and pipeline bugs before they cost full-scale compute. The skill's job ends when the pipeline produces real results; from there, hypothesis-driven iteration belongs in `/deriva-ml:experiment-lifecycle`. Triggers on: 'new ML project', 'set up a new pipeline', 'first model', 'onboard to existing project', 'standing up training', 'how should I get started', 'start small', 'representative dataset', 'development subset', 'what order should I do things', 'best practices for training', 'debug my training' (when the pipeline itself is new/unproven).
configure-experiment
by informatics-isi-eduALWAYS use this skill when setting up a DerivaML experiment project, adding config groups, or understanding how experiments compose. Triggers on: 'set up experiment', 'config groups', 'project structure', 'hydra defaults', 'DerivaModelConfig', 'experiment preset', 'new project from template'.
write-hydra-config
by informatics-isi-eduWrite, bootstrap, and validate hydra-zen config files for DerivaML — DatasetSpecConfig, asset_store, builds(), experiment_config, multirun_config, with_description. Use when adding/editing/updating any config in configs/, when bootstrapping a fresh project's configs from an existing catalog (per-config-group recipes + a worked end-to-end example), or when validating that config RIDs and versions match the catalog (singular validators per group, whole-tree composition, or the single-call deriva_ml_validate_config_file tool). Triggers on: 'write hydra config', 'edit datasets.py', 'edit assets.py', 'bootstrap configs', 'populate configs from catalog', 'validate config', 'validate datasets.py', 'check config matches catalog'.
compare-model-runs
by informatics-isi-eduUse when comparing metrics across multiple ML training executions in DerivaML — ranking model runs by accuracy/F1/loss, finding the best of N recent runs, identifying performance regressions, or aggregating results across a sweep. Covers three metric-storage patterns: features-as-scalars (`deriva_ml_list_feature_values(execution_rids=...)` for one-round-trip catalog query), metrics-as-JSONL-asset files (`Metrics_File` asset, download + parse locally), and prediction-CSV-as-`Execution_Asset` (per-execution tabular CSV plus optional per-analysis summary CSV — the deriva-ml-model-template's default pattern). ALSO use for **artifact provenance tracing** — when the question is 'where did this prediction come from', 'what code produced this asset', 'what dataset version trained this model', or 'why is this metric different from the last run' — `deriva_ml_get_lineage` walks the full data-flow chain in one call; the worked example shows the two-step pattern (lineage walk → workflow resource fetch) that yields the wor
help
by informatics-isi-eduUse when the user asks general questions about DerivaML, Deriva, deriva-mcp, or what they can do with these tools — including 'what is DerivaML', 'how do I use Deriva', 'what can you help me with', 'how does this work', or 'where do I start'. Also use for broad orientation questions about catalogs, datasets, experiments, hydra-zen configuration, ML workflows, or the MCP server when the user is asking 'how do I approach this' rather than requesting a specific action.
download-bag
by informatics-isi-eduALWAYS use this skill when getting data OUT of a Deriva catalog as a BDBag — exporting a slice of rows + their FK-reachable relations + the bulk objects they reference into a portable, self-describing, checksummed archive. Covers what a BDBag is, the two export paths (server-side export service via `deriva-export` / `DerivaExport`, or client-side orchestration via `deriva-download-cli` / `DerivaDownload`), authoring the export spec (the JSON config that defines what to include), the `bdbag` CLI for validating and materializing bags, asset materialization and caching strategy. Standalone — works on any Deriva catalog. Triggers on: 'download a bag', 'export a bag', 'BDBag', 'export catalog data', 'pull data out', 'download dataset' (when the user means the bag-export mechanism, not the DerivaML Dataset entity), 'deriva-download-cli', 'deriva-export', 'export spec', 'snapshot the catalog', 'bag manifest', 'materialize assets', 'self-describing archive', 'portable export', 'reproducible data drop', 'data package'
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.