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...
neuronj-documentation
by LJMedPhysNeuronJ is an ImageJ plugin for semi-GUI-based 2D neurite/neuron tracing and measurement of elongated grayscale structures. Use this skill for launching the NeuronJ tracing GUI, choosing tracing parameters, saving or exporting NeuronJ data files (NDF), and post-processing existing NDF tracings into CSV tables or ImageJ ROI files. For headless neurite/neuron tracing, SWC reconstruction analysis, morphometry, Sholl analysis, or batch automation, use the SNT skill instead.
snt-documentation
by LJMedPhysSNT is Fiji's framework for semi-automated neurite tracing, SWC reconstruction I/O, neuronal morphometry, Sholl analysis, graph theory analysis, brain atlas integration, online database access, and batch reconstruction analysis. Use this skill for manual tracing in the SNT GUI, importing or exporting SWC/TRACES files, scripting morphometry and Sholl analysis, graph-theoretic measurements, compartment-specific analysis, batch analysis of SWC directories, downloading reconstructions from NeuroMorpho.org or MouseLight, and analyzing brain area projections in the Allen CCF.
turboreg-documentation
by LJMedPhysAn ImageJ plugin for Registration from EPFL BIG that automatically aligns a **source** image or stack to a fixed **target** image using intensity-based pyramid optimisation. Achieves sub-pixel accuracy via cubic-spline interpolation. Standard tool for motion correction, channel alignment, and time-lapse stabilisation in Fiji. Read the files listed at the end of this SKILL for verified commands, GUI walkthroughs, scripting examples, and common pitfalls.
featurej-documentation
by LJMedPhysFeatureJ is a Fiji/ImageJ plugin suite for multi-scale differential feature extraction in grayscale images. This skill documents the validated Groovy automation path through the installed ImageScience classes for Derivatives, Edges, Laplacian, Hessian, Structure, and Statistics, plus the verified FeatureJ menu surface and a parameterized workflow script that saves TIFF and CSV outputs.
orientationj-documentation
by LJMedPhysOrientationJ is a Fiji/ImageJ plugin for local orientation and coherency analysis in grayscale images, based on the structure tensor. This skill documents the validated Groovy automation path — macro-recorded `IJ.run(...)` calls for Analysis, Distribution, Vector Field, Corner Harris, and Dominant Direction — plus a runnable export workflow for the image and table outputs those commands produce. Read the files listed at the end of this SKILL for full parameter keys, menu paths, workflow steps, and scope limits.
stackreg-documentation
by LJMedPhysAn ImageJ plugin from EPFL BIG that aligns all slices of a stack by **sequential propagation** — each slice is registered to the previous one, starting from the current anchor slice. Uses TurboReg internally for each pairwise registration. Primary use cases are time-lapse drift correction, serial section alignment, Z-stack stabilisation. Read the files listed at the end of this SKILL for verified commands, GUI walkthroughs, scripting examples, and common pitfalls.
bunwarpj-documentation
by LJMedPhysbUnwarpJ is a Fiji/ImageJ plugin for 2D elastic pairwise image registration with B-spline deformations. It supports bidirectional `Fast` and `Accurate` registration, unidirectional `Mono` registration, optional landmarks and masks, and saving elastic transformation files for reuse. In this repo, the reliable automation path is the direct Groovy API in `bunwarpj.bUnwarpJ_` rather than `IJ.run("bUnwarpJ", ...)` in headless scripts. Read the files listed at the end of this SKILL for validated Groovy workflows, GUI steps, and caveats.
stardists-documentation
by LJMedPhysStarDist is a Fiji/ImageJ plugin for cell and nuclei detection using deep-learning star-convex polygon models. Apply pre-trained or custom models to 2D microscopy images. **2D only** — the Fiji plugin has no 3D stack support. Default models only for NUCLEI in fluorescence or H&E histology images. Custom models must be in CSBDeep `.zip` format and compatible with StarDist 2D. See the full documentation for installation, scripting, parameter tuning, and troubleshooting.Read the files listed at the end of this SKILL for verified commands, GUI walkthroughs, scripting examples, and common pitfalls. RGB only for H&E model.
sholl-analysis-documentation
by LJMedPhysSholl Analysis in this Fiji environment is provided through SNT and supports radial analysis of segmented images, traced morphologies, and pre-sampled Sholl profiles. Use this skill for image-based Sholl profiles from binary 2D or 3D images, tracing-based Sholl measurements from SWC reconstructions, and polynomial fit or decay statistics from CSV profile tables.
bigstitcher-documentation
by LJMedPhysA Fiji plugin for stitching and fusing multi-tile, multi-angle, multi-TB microscopy datasets.Stores all state in an XML project file; uses BigDataViewer for interactive display. Primary use cases are cleared-tissue lightsheet stitching, tiled confocal reconstruction, multi-view lightsheet registration. Read the files listed at the end of this SKILL for verified commands, GUI walkthroughs, scripting examples, and common pitfalls.
supervisor-pipeline-phases
by LJMedPhysDetailed step-by-step instructions for each phase of the ImageJ analysis pipeline. The supervisor MUST read the relevant phase file BEFORE entering that phase. Phase sequence: 1(gather) → 2(plan) → 3(setup) → 4a(io) → 4b(process) → 4c(stats) → 4d(plot) → 5(summarize) → 6(document) → 7(qa).
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.