Browse Skills

Automatically refines recently modified code to improve clarity, consistency, and maintainability while preserving all functionality. Applies project-specific standards and enhances readability without altering behavior.

Refactor high-complexity React components by extracting custom hooks, splitting into sub-components, simplifying conditionals, and isolating data logic. Use when static analysis shows complexity > 50 or line count > 300.

Reviews frontend code (React, TypeScript) for quality, performance, and business logic issues using a defined checklist, supporting both staged and file-targeted reviews.

Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities. Triggers on testing, spec files, coverage, Vitest, RTL, unit tests, integration tests, or write/review test requests.

Enforces citation requirements, source grounding, and 'I don't know' behavior to reduce hallucination. Toggle on for research that needs factual accuracy.

Run and troubleshoot privacy-preserving, local DSPy RLM security audits for large legacy .NET codebases. Use when asked to scan repositories for vulnerabilities, tune RLM/tool limits, fix truncation/stall issues, or produce actionable markdown/json audit outputs without loading entire codebases into model context.

Build, launch, and drive the wayfinder-maps server with a headless browser to verify changes end-to-end. Suitable for validating map visualization, interactions, and cross-browser behavior.

Provides a shared vocabulary and principles for designing deep modules with small interfaces and high leverage. Use when structuring code for testability, maintainability, and AI-navigability.

Scans a codebase for architectural friction and proposes deepening refactors that improve locality, testability, and AI navigability. Use it when you want a visual review of shallow modules and coupled seams.

Review code changes against repo coding standards and spec requirements in two isolated axes (Standards and Spec). Use when reviewing branches, WIP, or requesting a diff review from a specific point.

Reviews videos, images, posts, audio, articles, subtitles, and live scripts before publishing to Douyin, Xiaohongshu, Weixin Video Accounts, or Kuaishou. Use it to check risk, required disclosures, sources, rights, and platform-specific edits.

Scans codebases for common AI-generated code patterns like duplicated helpers, try-import fallbacks, and speculative abstractions. Helps clean up AI slop through guided refactoring with test safety.