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.
playbook
A SQLite-based system for storing and retrieving successful CFN Loop execution patterns. It tracks agent configurations, iteration counts, and feedback themes to optimize future workflow runs. Includes similarity matching and auto-update from retrospectives.
Debugging
A structured debugging framework that enforces root cause analysis before fixes. It provides a four-phase process with specific techniques for different scenarios like deep stack errors. The framework prevents random fixes and requires verification before completion claims.
frontend
An expert frontend development assistant specializing in React, Vue, and Angular frameworks. It provides guidance on building components, state management, routing, TypeScript, styling, and performance optimization to create modern, efficient, and visually appealing web applications.
version-aligner
Aligns versions across multiple repositories using lockstep, independent, or umbrella strategies, enforces semantic versioning rules, detects conflicts, suggests version bumps based on commits, and validates cross-repo compatibility for consistent releases.
nodejs-backend
A Node.js/TypeScript backend development expert specializing in building robust APIs and server applications using Express, Fastify, and NestJS, with comprehensive capabilities in database integration, authentication, real-time features, and production-ready error handling.
serverless-recommender
An intelligent serverless platform recommender that analyzes project context and workload patterns to provide tailored recommendations for AWS Lambda, Azure Functions, GCP Cloud Functions, Firebase, and Supabase, including cost estimates and suitability assessments.
pm-closure-validation
A quality gate skill that validates increment readiness for closure using a 3-gate framework, ensuring all critical tasks are complete, tests are passing, and documentation is updated before final approval.
tdd-expert
This skill provides comprehensive Test-Driven Development expertise, guiding users through the red-green-refactor cycle, BDD practices, and TDD patterns to build robust, well-designed software with confidence and high test coverage.
kafka-mcp-integration
Provides expert guidance for integrating Kafka with MCP servers, supporting four implementations with auto-detection, configuration examples, and clear recommendations on when to use MCP versus direct code.
github-sync
This skill provides guidance for setting up two-way synchronization between SpecWeave specifications and GitHub Projects, automatically syncing changes for team visibility and project management, but does not perform the actual sync operation.
tdd-workflow
This skill coordinates Test-Driven Development workflows by detecting TDD intent and offering guided red-green-refactor cycles. It routes users to appropriate tools like the tdd-orchestrator agent or structured commands, providing TDD education and best practices.
context-optimizer
Context Optimizer is a second-pass tool that analyzes user prompts to surgically remove irrelevant specifications, agents, and skills from loaded context, achieving over 80% token reduction through intelligent, intent-based filtering.
fluxwing-screenshot-importer
Import UI screenshots and generate uxscii components automatically using vision analysis. Use when user wants to import, convert, or generate .uxm components from screenshots or images.
help-skill
A template for generating help documentation for Claude Skills plugins. It provides structured sections for skill overviews, commands, quick start guides, and search functionality. The template uses placeholders that get replaced with actual plugin information.
error-handling-patterns
Provides concrete error handling patterns for Python, TypeScript, and Rust with practical examples like custom exception hierarchies, Result types, retry decorators, and async error handling. Focuses on building resilient applications with clear guidance on when to use different approaches.
debugging-strategies
This skill provides a structured methodology for debugging software issues, covering systematic processes, mindset, and tool-specific examples for JavaScript, Python, and Go. It teaches how to reproduce problems, form hypotheses, and use debuggers effectively.
kafka-cli-tools
This skill provides expert guidance on Kafka CLI tools (kcat, kcli, kaf, kafkactl) for producing/consuming messages, managing topics, and troubleshooting, including installation, command examples, and authentication setups.
deep-learning
PyTorch, TensorFlow, neural networks, CNNs, transformers, and deep learning for production
skill-creator
Provides structured guidance for creating Claude Skills with clear templates and progressive disclosure patterns. Includes practical examples for scripts, references, and assets organization. Helps developers extend Claude's capabilities with specialized workflows and tool integrations.
smart-rules
Automatically loads relevant project documentation based on task keywords. Scans project files to create category mappings, then matches user prompts to load only needed rules. Triggers after TodoWrite or before implementation tasks to ensure developers have proper context.
2_skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
literature-engineer
Multi-route literature expansion + metadata normalization for evidence-first surveys. Produces a large candidate pool (`papers/papers_raw.jsonl`, target ≥200) with stable IDs and provenance, ready for dedupe/rank + citation generation. **Trigger**: evidence collector, literature engineer, 文献扩充, 多路召回, snowballing, cited by, references, 200篇, 元信息增强, provenance. **Use when**: 需要把候选文献扩充到 ≥200 篇并补齐可追溯 meta（survey pipeline 的 Stage C1，写作前置 evidence）。 **Skip if**: 已经有高质量 `papers/papers_raw.jsonl`（≥200 且每条都有稳定标识+来源记录）。 **Network**: 可离线（靠 imports）；雪崩/在线检索需要网络。 **Guardrail**: 不允许编造论文；每条记录必须带稳定标识（arXiv id / DOI / 可信 URL）和 provenance；不写 output/ prose。
create-skill
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends CoPilot's capabilities with specialized knowledge, workflows, or tool integrations.
beautiful-mermaid
Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.