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.
add-uint-support
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture.
cargo-fuzz
cargo-fuzz is the de facto fuzzing tool for Rust projects using Cargo. Use for fuzzing Rust code with libFuzzer backend.
threejs-materials
Three.js materials - PBR, basic, phong, shader materials, material properties. Use when styling meshes, working with textures, creating custom shaders, or optimizing material performance.
add-malli-schemas
This skill provides specific guidance for adding Malli schemas to Metabase API endpoints. It includes concrete examples, common patterns, and step-by-step instructions for route params, query params, request bodies, and response schemas. The skill references actual code files and established patterns within the Metabase codebase.
sherlock-review
Provides a structured methodology for verifying code claims through systematic evidence collection and deductive reasoning. Includes investigation templates, checklists, and example scenarios for validating bug fixes, performance improvements, and edge case handling.
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
typescript-review
A specialized code review skill for TypeScript/JavaScript that enforces Metabase coding standards with clear guidelines and integration with existing tooling for consistent quality checks.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
claude-skill-bit-cli
A practical CLI reference skill for Bit component development platform that provides quick command syntax lookup, though it lacks interactive examples and detailed flag explanations.
context-driven-testing
This skill teaches context-driven testing principles, helping testers adapt their approach based on project specifics rather than blindly following 'best practices'. It provides concrete heuristics like SFDIPOT and RST tours, with examples for different project contexts (startup vs enterprise). The skill includes agent coordination patterns for implementing context-aware testing strategies.
Prompting
Meta-prompting system for dynamic prompt generation using templates, standards, and patterns. USE WHEN meta-prompting, template generation, prompt optimization, or programmatic prompt composition.
ask-questions-if-underspecified
Clarify requirements before implementing. Use when serious doubts araise.
playwright-local
Build browser automation and web scraping with Playwright on your local machine. Prevents 10 documented errors including CI timeout hangs, extension testing failures, and Ubuntu compatibility issues. Includes stealth mode for anti-bot bypass, authenticated sessions, infinite scroll handling, screenshot/PDF generation, and v1.57 Speedboard performance analysis. Use when: automating browsers, scraping protected sites, testing with real IPs, bypassing bot detection, generating screenshots/PDFs, or troubleshooting "target closed", "page.pause() hangs CI", "permission prompts block tests", or "Ubuntu 25.10 installation" errors.
api-spec-analyzer
This Skill analyzes OpenAPI specs to generate TypeScript interfaces and implementation code for frontend API integration. It provides concrete examples for API services, TanStack Query hooks, and error handling patterns specific to a project. It helps developers avoid common API integration errors by referencing the actual specification.
pinia
Pinia official Vue state management library, type-safe and extensible. Use when defining stores, working with state/getters/actions, or implementing store patterns in Vue apps.
context-engineering
A reference guide for managing context in LLM agent systems. It explains context components like system prompts and tool outputs, then provides concrete strategies like summarization and observation masking to reduce token usage. Includes practical examples for optimizing Claude commands and skills.
wheels-view-generator
Generates CFWheels view templates with correct query handling, form helpers, and association patterns. Specifically prevents common CFML errors like query/array confusion and incorrect form helper usage. Provides production-tested examples for index, show, form, and layout views.
condition-based-waiting
Provides a concrete pattern for replacing arbitrary timeouts in tests with condition polling. Fixes flaky tests by waiting for actual state changes instead of guessing timing. Includes clear before/after examples, decision flow, and common mistake patterns.
fix-lint
Helps fix oxlint errors and warnings in the OneKey codebase. Use when running yarn lint and encountering warnings, cleaning up code before committing, or fixing spellcheck, unused variable, or other linting warnings.
api-integration
A comprehensive guide for integrating OpenAPI specifications with React apps using MCP, featuring excellent type safety, query layer patterns, and practical implementation details.
coding-agent
This Skill provides programmatic control over coding agents (Codex, Claude Code, OpenCode, Pi) through bash commands with PTY support. It enables background process management, parallel task execution, and integrates with git workflows for code reviews and issue fixing. The documentation emphasizes critical requirements like PTY mode and git repo initialization.
claude-api
This skill provides detailed guidance for using the Claude Messages API with structured outputs, covering JSON schema validation, prompt caching, streaming, and tool use. It documents 12 common errors with specific solutions and keeps up with API changes like model deprecations and new beta features.
risk-based-testing
A well-structured, practical skill for implementing risk-based testing methodology with clear workflows, scoring systems, and agent integration for dynamic risk assessment.