Code review feedback is often verbose and repetitive, burying actionable items in polite filler. This skill formats each review finding as a single line with exact location, problem, and fix.

Large memory files like CLAUDE.md waste tokens on every AI session start. This skill compresses them by about 46 percent while keeping all technical content intact.

Developers spend too much time writing verbose commit messages. This skill generates terse, professional Conventional Commits in under 50 characters while preserving the reasoning behind each change.

AI assistants often produce verbose responses that waste tokens and increase costs. Caveman mode cuts output tokens by 65 to 75 percent while preserving full technical accuracy and code quality.

Long coding sessions exhaust context window when verbose subagent outputs pile up. Cavecrew provides a decision framework for delegating to specialized caveman-style subagents that return compressed output, extending context lifespan by 60% across many delegations.

Research branches pile up and become difficult to manage. This skill automatically detects, merges, and organizes research findings from Claude Code Web sessions into actionable GitHub issues.

React Flow node configuration requires careful attention to handle IDs, edge styles, and resize behavior. This skill provides step-by-step guidance to create consistent, debuggable workflow nodes.

UI polish updates often drift into redesign, changing the character of your work. This skill delivers precise, restrained visual polish that sharpens hierarchy, spacing, and readability while keeping your original design intent completely intact.

Building correct, performant React Flow v12 canvases requires deep knowledge of custom nodes, handles, edges, and viewport management. This skill provides version-specific best practices and a structured review workflow to help developers avoid common pitfalls and produce production-ready workflow UIs.

This skill automates conversion of Pencil design files (.pen) into production-ready frontend code. Designers and developers save hours of manual markup by preserving layout, typography, and visual fidelity from design to code.

Product teams struggle to decide what UI actions to show after a user completes a task. This skill provides a structured framework to model actions from user intent, placing them at the right scope and priority level.

Design-to-code translation often produces unstructured components that break repository architecture and design-system rules. This skill converts Figma or Pencil designs into production-ready code using Feature-Sliced Design layers, Tailwind v4 tokens, and accessibility standards while respecting existing project contracts.

Web developers need to verify accessibility, SEO, and quality before deploying updates. This skill performs a structured browser audit covering WCAG 2.2 AA compliance, Lighthouse checks, keyboard navigation, and critical UX issues.

Casely eliminates 40% of QA engineering time by converting requirement documents into structured test cases. It learns your team's writing style from examples and exports TestRail-ready Excel files.

Building brand assets for Next.js projects is repetitive and error-prone. This skill scans your project, generates a full checklist with exact specifications, and imports all assets with correct metadata configuration.

Generic brainstorming often produces obvious or impractical ideas. This skill provides a structured methodology for transforming abstract problems into novel, feasible solutions through analogical "mastication" and multi-stage refinement.

Managing plugin releases manually leads to forgotten changelog updates and inconsistent versioning. This skill automates the entire release workflow including version bump detection, changelog generation, and git tag creation.

Transform content into engaging Xiaohongshu-style infographic series. Auto-selects visual styles and layouts based on content analysis. Generates 1-10 cartoon-style images optimized for the Xiaohongshu platform.

Users struggle to transform written content into visual presentations. This skill analyzes content, generates comprehensive slide outlines with style specifications, and produces individual slide images using AI image generation.

Converts any webpage to clean markdown using Chrome browser automation. Supports dynamic pages requiring login and outputs structured markdown with metadata.