专门用于在对话结束时，根据用户反馈和对话内容总结优化并迭代现有 Skills 的核心工具。它通过吸取对话中的“精华”（如成功的解决方案、失败的教训、特定的代码规范）来持续演进 Skills 库。

Comprehensive Tailwind CSS utility-first styling patterns including responsive design, layout utilities, flexbox, grid, spacing, typography, colors, and modern CSS best practices. Use when styling...

Shared TypeScript best practices for Designer and Electron subsystems.

Self-evolving skill that enables Canifi to create, install, and manage new skills autonomously

Build accessible, responsive, and performant frontend components with design system best practices, modern CSS, and framework-agnostic patterns.

Search and recommend Claude Code skills from trusted marketplaces

Design effective user onboarding flows that drive activation, adoption, and retention

Senior Design System Architect & Token Engineer for 2026. Specialized in layered design tokens, Tailwind 4 CSS-first themes, and headless UI orchestration using Radix. Expert in building...

Design tools that agents can use effectively, including when to reduce tool complexity. Use when creating, optimizing, or reducing agent tool sets.

Claude Code skill for detecting and synchronizing Node.js version specifications across project files

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise...

Expert customer lifecycle marketing guidance for retention, expansion, and advocacy. Use when designing onboarding programs, creating upsell strategies, preventing churn, building referral...

Expert growth product management guidance for SaaS applications. Use when designing growth loops, optimizing activation and onboarding, building retention systems, creating referral mechanics,...

Expert product strategist for vision, strategy, and market positioning. Use when defining product vision, assessing product-market fit, sizing market opportunities (TAM/SAM/SOM), competitive...

This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge,...

This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents,...

Expert community-led growth and community management guidance. Use when building developer communities, Discord/Slack communities, online communities, managing community platforms, designing...

Guide for security-related Agent Skills including penetration testing, code auditing, threat hunting, and forensics skills.

Upgrade any skill to v5 Hybrid format using decision theory + modal logic

My catalogue of Skills.md