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...
scientific-writing
by yibeichanWrite rigorous scientific manuscripts, research papers, grant proposals, and literature reviews. Use when drafting or revising any part of a scientific document including abstracts, introductions, methods, results, and discussions. Applies IMRAD structure, citation styles (APA/AMA/Vancouver/IEEE), reporting guidelines (CONSORT/STROBE/PRISMA), and publication standards. Triggers on requests to write research papers, journal articles, scientific reports, academic manuscripts, grant applications, or improve scientific prose.
careful
by yibeichanSafety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".
cso
by yibeichanChief Security Officer mode. Performs OWASP Top 10 audit, STRIDE threat modeling, attack surface analysis, auth flow verification, secret detection, dependency CVE scanning, supply chain risk assessment, and data classification review. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review".
freeze
by yibeichanRestrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze", "restrict edits", "only edit this folder", or "lock down edits".
investigate
by yibeichanSystematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively suggest when the user reports errors, unexpected behavior, or is troubleshooting why something stopped working.
plan-eng-review
by yibeichanEng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when the user has a plan or design doc and is about to start coding — to catch architecture issues before implementation.
retro
by yibeichanWeekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint.
review
by yibeichanPre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land code changes.
bids-format
by yibeichanBIDS standard for all data types — MRI, DWI, PET, EEG, MEG, iEEG, fNIRS, behavioral, annotations, motion capture, microscopy, physiology, and multi-modal datasets. Covers BIDS naming conventions (entities, suffixes, extensions), dataset creation, modality-specific conversion tools (heudiconv, dcm2bids, MNE-BIDS, pypet2bids), validation, project directory layout (sourcedata, rawdata, derivatives, code, stimuli, phenotype), derivatives organization, DataLad version control, multi-experiment projects, and sharing on OpenNeuro. Trigger keywords: BIDS dataset, BIDS format, BIDS naming, BIDS entities, BIDS convert, organize project, project structure, rawdata, derivatives, sourcedata, phenotype, participants.tsv, dataset_description.json, multi-modal BIDS, behavioral data BIDS, EEG BIDS, DWI BIDS, PET BIDS, annotation data, research data management, DataLad, OpenNeuro, data sharing.
bidsapp-nidm-standards
by yibeichanStandards and tools for creating, maintaining, and refactoring NIDM-integrated BIDSapps that run through BABS. Use when working with sensein BIDSapp repositories (freesurfer_bidsapp, mriqc-nidm_bidsapp, ants_bidsapp) or creating new BIDSapps. Helps with repository structure consistency, NIDM integration patterns, CLI argument standardization, BIDS-compliant output structures, and BABS configuration.
dicom2fmriprep
by yibeichanGenerate scripts for the full fMRI preprocessing pipeline from raw DICOM files through BIDS conversion (heudiconv) to fMRIPrep, including HPC/SLURM execution via BABS. Use this skill whenever someone needs to preprocess fMRI data, convert DICOMs to BIDS, write heudiconv heuristics, run fMRIPrep on a cluster, set up BABS projects, fix BIDS validation errors, or generate any scripts related to the DICOM-to-fMRIPrep pipeline.
fmri-ssm
by yibeichanState-space models (SSMs) for fMRI analysis: HMM, HMM-MAR, sticky/HDP-HMM, IO-HMM, SLDS, rSLDS, SNLDS. Covers resting-state, task-based (MID, SST, N-back), and naturalistic fMRI (movie, gaming). Python code generation (hmmlearn, ssm, pyhsmm, osl-dynamics, glhmm), HRF-aware modeling, fMRIPrep/XCP-D preprocessing, CIFTI/parcellation/ICA, model selection, and single-subject + group-level inference. Trigger keywords: HMM on brain data, brain state dynamics, dynamic FC, switching dynamics, latent states from BOLD, HRF deconvolution for state models, SLDS/rSLDS on neural timeseries, choosing K for fMRI, state-space + neuroimaging, task paradigms (MID, SST, N-back, movie-watching) with dynamic/latent-state analysis, temporal dynamics beyond standard GLM.
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.