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.
nano-banana-pro
A CLI wrapper for Google's Gemini 3 Pro Image API that generates and edits images. It saves files locally, supports 1K-4K resolutions, and outputs a MEDIA: line for automatic attachment in chat interfaces. Requires a GEMINI_API_KEY and uv package manager.
ui-ux-pro-max
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.
fda-database
This skill provides Python-based access to the FDA's openFDA API, enabling queries for drug adverse events, medical device clearances, food recalls, and substance identification. It includes specific methods for different FDA data categories and demonstrates practical use cases for regulatory analysis and safety research.
latchbio-integration
Provides guidance for using Latch, a Python framework for building and deploying bioinformatics workflows as serverless pipelines. Covers workflow creation with decorators, cloud data management, resource configuration, and integration with Nextflow/Snakemake. Includes practical examples for RNA-seq, GPU tasks, and registry integration.
deepchem
Provides DeepChem integration for molecular property prediction, drug discovery, and materials science. Includes data loaders for SMILES/SDF files, multiple featurization methods (fingerprints, graphs, descriptors), and pre-built models for ADMET/toxicity prediction. Offers workflow examples for GNNs, transfer learning, and molecule generation.
cobrapy
Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.
woocommerce-dev-cycle
Provides concrete commands and workflows for WooCommerce plugin development, including running PHP/JS tests, linting, and fixing code style. It centralizes scattered documentation into actionable steps for the standard dev cycle.
tests-maintenance
Maintains IdeaVim test suite quality. Reviews disabled tests, ensures Neovim annotations are documented, and improves test readability. Use for periodic test maintenance.
cosmos-vulnerability-scanner
Scans Cosmos SDK blockchains for 9 consensus-critical vulnerabilities including non-determinism, incorrect signers, ABCI panics, and rounding errors. Use when auditing Cosmos chains or CosmWasm contracts. (project, gitignored)
auditing-pre-release-security
Audits security and supply-chain risk between two git refs, 预发布安全审计
drizzle-orm-d1
Build type-safe D1 databases with Drizzle ORM. Includes schema definition, migrations with Drizzle Kit, relations, and D1 batch API patterns. Prevents 18 errors including SQL BEGIN failures, cascade data loss, 100-parameter limits, and foreign key issues. Use when: defining D1 schemas, managing migrations, bulk inserts, or troubleshooting D1_ERROR, BEGIN TRANSACTION, foreign keys, "too many SQL variables".
openai-agents
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11 documented errors. Use when: building agents with tools, voice agents with WebRTC, multi-agent workflows, or troubleshooting MaxTurnsExceededError, tool call failures, reasoning defaults, JSON output leaks.
reasoningbank-intelligence
This skill implements a ReasoningBank system for AI agents to learn from task outcomes, recognize patterns, and optimize strategies. It provides methods for recording experiences, recommending approaches, and enabling continuous improvement through meta-learning and transfer learning capabilities.
deep-analysis
A comprehensive code investigation skill that provides structured workflows for deep codebase analysis using semantic search and detective agents, with clear prerequisites and phased execution.
new-track
This skill guides users through creating structured development tracks with specifications and hierarchical plans. It enforces a spec-before-plan workflow, reads project context files, and integrates with a TodoWrite system for progress tracking. The interactive Q&A approach ensures requirements are captured before planning begins.
tester-detective
This skill uses AST callers analysis via claudemem to identify test coverage gaps, find which tests call specific functions, and detect untested code. It provides concrete commands for test discovery and prioritizes high-PageRank untested functions as critical issues.
session-isolation
A well-structured pattern for isolating workflow artifacts using session-based directories, preventing file collisions in multi-agent Claude workflows with clear backward compatibility.
openrouter-trending-models
This skill fetches weekly trending programming models from OpenRouter rankings, providing model IDs, context windows, pricing, and usage stats. It helps developers select appropriate AI models for code review tasks and cost optimization. The script outputs structured JSON with metadata and summary statistics.
cross-plugin-detective
A well-structured integration guide that standardizes detective skill usage across plugins, enforcing indexed memory patterns and providing clear role-to-skill mappings for consistent code investigation workflows.
claudish-usage
A skill for AI agents to delegate Claude Code execution to external models via Claudish CLI, enforcing sub-agent patterns to prevent context pollution. It provides decision trees, agent selection guides, and file-based workflows for using models like Grok, GPT-5, and Gemini through OpenRouter.
exploratory-testing
Provides structured templates and heuristics for exploratory testing, including SFDPOT and FEW HICCUPPS frameworks. Helps testers create focused charters, discover edge cases, and document findings systematically. Useful for manual testing sessions where automated tests may miss issues.
implementation-planning
A skill that generates structured implementation plans following TDD principles. It breaks down features into phases with Prime, Test, Implement, Validate cycles, links tasks to PRD/SDD specifications, and identifies parallel work opportunities. Focuses on activities and dependencies without time estimates.
video-subtitle-cutter
A powerful AI-powered video editing tool that automates the removal of filler words and pauses from videos using speech transcription and intelligent analysis.
youtube-studio
Automates YouTube Studio tasks like video uploads and thumbnail management through Chrome MCP. Provides step-by-step workflows for uploading videos, compressing thumbnails under 2MB, and managing channel content. Includes troubleshooting tips for common Chrome MCP issues.