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.
requirements-analysis
This skill helps create and validate Product Requirements Documents using a structured template and iterative review cycles. It focuses on defining what to build and why, avoiding technical implementation details. Includes parallel agent research, multi-angle validation, and a detailed checklist.
scientific-schematics
Generates scientific diagrams for publications using Nano Banana Pro AI with Gemini 3 Pro quality review. Implements smart iteration that only regenerates images if they don't meet document-specific quality thresholds. Includes detailed guidelines for journal formatting and accessibility.
geo-database
Provides programmatic access to NCBI GEO database for gene expression data. Enables searching, downloading, and parsing microarray/RNA-seq datasets (GSE, GSM, GPL) with Python libraries like GEOparse and Biopython. Includes examples for data retrieval, metadata extraction, and expression analysis workflows.
CreateCLI
Generates TypeScript CLI tools with three-tier architecture based on complexity. Provides templates for manual parsing (Tier 1), Commander.js (Tier 2), and references for oclif (Tier 3). Includes workflows for creating new CLIs, adding commands, and upgrading tiers. Follows specific conventions for Bun runtime and JSON output.
react-ui-patterns
Provides concrete React patterns for loading states, error handling, and form submissions. Includes specific code examples showing correct vs. wrong implementations, decision trees for loading indicators, and anti-patterns to avoid. Focuses on user experience principles like never showing stale UI and always surfacing errors.
add-cuda-kernel
Step-by-step tutorial for adding new CUDA kernels to FlashInfer
pr-review
Security-first PR review checklist for this repo. Use when reviewing diffs/PRs, especially changes involving auth, networking, sensitive data, or dependency/lockfile updates. Focus on secret/PII leakage risk, supply-chain risk (npm + node_modules inspection), cross-platform architecture (extension/mobile/desktop/web), and React performance (hooks + re-render hotspots). Avoid UI style nitpicks. PR Review.
panda-css
A Claude skill that generates Panda CSS code from natural language descriptions. It helps developers create CSS-in-JS styles with proper syntax, supports responsive design patterns, and provides utility class recommendations for common styling tasks.
eks
AWS EKS Kubernetes management for clusters, node groups, and workloads. Use when creating clusters, configuring IRSA, managing node groups, deploying applications, or integrating with AWS services.
TanStack Router
Build type-safe, file-based React routing with TanStack Router. Supports client-side navigation, route loaders, and TanStack Query integration. Prevents 20 documented errors including validation structure loss, param parsing bugs, and SSR streaming crashes. Use when implementing file-based routing patterns, building SPAs with TypeScript routing, or troubleshooting devtools dependency errors, type safety issues, Vite bundling problems, or Docker deployment issues.
tiptap
Build rich text editors with Tiptap - headless editor framework with React and Tailwind v4. Covers SSR-safe setup, image uploads, prose styling, and collaborative editing. Use when creating blog editors, comment systems, or Notion-like apps, or troubleshooting SSR hydration errors, typography issues, or image upload problems.
seo-meta
Generate complete SEO meta tags for every page. Covers title patterns, meta descriptions, Open Graph, Twitter Cards, and JSON-LD structured data (LocalBusiness, Service, FAQ, BreadcrumbList). Use when: building pages, adding social sharing, implementing structured data, optimizing for search engines.
claudemem-search
Provides semantic code search and AST-based structural analysis for codebases. Features include symbol location, call graph analysis, PageRank ranking, and version-aware command fallbacks. Outputs machine-readable format for agent integration.
browser-debugging
A comprehensive browser debugging skill that provides systematic UI testing, visual analysis, and debugging workflows using Chrome Extension MCP tools with optional external vision models for enhanced validation.
wheels-debugging
Provides specific solutions for common CFWheels framework errors like 'No matching function found' and 'Missing argument name'. Includes debugging tools like enabling debug output and using browser MCP tools for UI testing. Focuses on practical fixes with clear code examples.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
playwright-testing
An exceptionally practical and opinionated guide for writing reliable Playwright tests, emphasizing complete coverage, deterministic waits, and strategic mocking with clear anti-patterns and actionable solutions.
sag
A CLI wrapper for ElevenLabs TTS that adds macOS-style 'say' command UX with voice tagging, audio normalization, and playback features. It simplifies voice generation for developers who need programmatic TTS access with local audio output.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
denario
Denario automates scientific research workflows from data analysis to LaTeX paper generation using a multi-agent system. It guides users through idea generation, methodology development, computational experiments, and publication formatting with examples for time-series and ML projects.
dspy-ruby
Provides detailed guidance for DSPy.rb, a Ruby framework for building type-safe LLM applications. Covers signatures, modules, multiple predictors, provider configuration, testing, and deployment patterns with concrete code examples. Focuses on programming LLMs rather than manual prompting.
honesty
This skill sets a behavioral expectation for Claude to provide direct, unfiltered feedback during code reviews and technical discussions. It explicitly requests blunt honesty when users are wrong, preventing overly polite or non-critical responses. The skill functions as a meta-instruction rather than a tool.
implementation-planner
Generates structured implementation plans by analyzing codebases and GitHub issues. It spawns parallel research agents to gather context, follows language-specific guidelines, and produces four templated documents: research notes, context files, task checklists, and final plans. Useful for feature development and refactoring.
n8n-expression-testing
This skill validates n8n expression syntax, tests with sample data, and identifies common errors like undefined property access and type mismatches. It provides safe coding patterns, security checks for dangerous functions, and performance tips for array operations. The quick reference card and error/fix examples help developers write reliable expressions.