Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
discover-engineering
This skill automatically detects when users are working on engineering tasks and provides access to 14 specific software engineering practice skills. It serves as a gateway to detailed documentation on code review, TDD, DDD, refactoring, and RFC processes through simple file system commands.
vibecoder-guide
Guides non-technical users through development workflows using natural language. Detects project state (no project, planning phase, active tasks) and provides context-specific next-step suggestions in plain Japanese. Helps beginners navigate coding projects without technical jargon.
agile-product-owner
This skill provides automated user story generation with INVEST criteria validation and sprint capacity planning. It helps product owners break down epics into stories with acceptance criteria and point estimates. The tool focuses on backlog management and sprint execution workflows.
karen-repo-reviewer
Provides brutally honest AI-powered code reviews with Karen Scores (0-100) across five dimensions: bullshit factor, functionality, code quality, completion honesty, and practical value. Includes market research, specific file references, and actionable fixes. Available as Claude Skill and GitHub Action.
cc-devflow-orchestrator
This skill acts as a central router for a complex development workflow system. It directs users to specific commands and agents based on their current project phase, preventing duplication of detailed standards. It provides clear state-based routing, troubleshooting guides, and integration with specialized agents for PRD writing, tech design, UI prototyping, and code review.
ultrathink
Deep planning philosophy for craftsman-level architecture. Transforms planning from research-then-design to research-question-simplify-design. Use when --deep flag is set, for epics, complex features (30+ tasks), or when auto_deep_mode preference is enabled. Invokes assumption questioning, codebase soul analysis, and ruthless simplification. (project)
scientific-critical-thinking
A skill for systematically evaluating scientific research quality. It provides structured frameworks for assessing methodology, detecting biases, and applying evidence grading systems like GRADE and Cochrane ROB. Helps identify logical fallacies in scientific arguments.
release-guide-info
Generates internal operations update guides by analyzing git diffs between two references. Supports strict read-only mode and temporary cloning for fresh refs. Includes auto-version detection, multi-language output (English/Portuguese), and enforces comprehensive change documentation rules for ops teams.
ui-ux-designer
Create interface designs, wireframes, and design systems. Masters user research, accessibility standards, and modern design tools. Specializes in design tokens, component libraries, and inclusive design. Use PROACTIVELY for design systems, user flows, or interface optimization.
pre-dev-dependency-map
A highly structured dependency mapping skill that enforces explicit technology choices with version control, security validation, and standards compliance through a rigorous gated workflow.
portfolio-roadmapping-bets
Use when managing multiple initiatives across time horizons (now/next/later, H1/H2/H3), balancing risk vs return across portfolio, sizing and sequencing bets with dependencies, setting exit/scale criteria for experiments, allocating resources across innovation types (core/adjacent/transformational), or when user mentions portfolio planning, roadmap horizons, betting framework, initiative prioritization, innovation portfolio, or resource allocation across horizons.
hypogenic
Automates scientific hypothesis generation from data and literature. Provides three methods: data-driven (HypoGeniC), literature-integrated (HypoRefine), and combined (Union). Includes PDF processing, iterative refinement, and performance caching. Published research shows 8-16% improvements over baselines.
news
This skill fetches and analyzes Anthropic's official news, providing structured technical and business insights. It follows a four-step workflow: news collection, multi-dimensional analysis, knowledge organization, and report generation. Includes templates for technical updates and business dynamics with practical frameworks like SWOT and 5W1H.
medical-research
This skill fetches recent PubMed papers on biomedical topics and generates structured summaries in plain English. It follows a clear template, defines technical terms, and includes disclaimers. It requires local Python script execution.
moai-library-mermaid
This skill enables Claude Code to generate Mermaid diagrams across 21 types using MCP Playwright for SVG/PNG rendering. It provides syntax examples, best practices, and integrates with MoAI-ADK workflows for architecture planning and documentation. Requires Node.js and Playwright setup.
Plugin Structure
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
cosmic-database
Access COSMIC cancer mutation database. Query somatic mutations, Cancer Gene Census, mutational signatures, gene fusions, for cancer research and precision oncology. Requires authentication.
biomni
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.
shadcn-management
Manage shadcn/ui components using MCP tools. Use when user needs to: (1) Add new shadcn components to a project (2) Build complex UI features requiring multiple components (3) Research component implementations and examples (4) Get component installation commands Triggers: "add shadcn", "shadcn component", "build UI with shadcn", "install component", "create form", "create dialog"
task-generator
Generate structured task lists from specs or requirements. IMPORTANT: After completing ANY spec via ExitSpecMode, ALWAYS ask the user: "Would you like me to generate a task list for this spec?" Use when user confirms or explicitly requests task generation from a plan/spec/PRD.
brenda-database
Provides programmatic access to the BRENDA enzyme database via SOAP API for retrieving kinetic parameters, reaction equations, and organism-specific enzyme data. Includes Python client examples for common biochemical queries like Km/kcat values and substrate specificity analysis.
ops-migration-planning
Provides a structured 8-phase workflow for infrastructure migration planning with detailed templates for discovery, assessment, planning, and execution. Includes practical checklists, risk registers, and cost analysis templates specifically for cloud and data center migrations.
security-auditor
A specialized security auditing tool that integrates multiple scanning utilities (Nessus, Qualys, OpenVAS, Prowler) to conduct comprehensive security assessments. It follows structured audit phases from planning to reporting, covers major compliance frameworks, and provides actionable remediation guidance.
create-destination
A step-by-step guide for creating walkerOS destination integrations with third-party analytics tools. It establishes a research-first approach with concrete examples before implementation, includes template selection, testing strategies, and documentation standards. The skill enforces a consistent development workflow across the project.