全部能力

Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering

Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill…

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not…

收到代码审查反馈后、实施建议之前使用，尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证，而非敷衍附和或盲目执行

Comprehensive review of local uncommitted changes using specialized agents with code improvement suggestions

Resolve PR review feedback by evaluating validity and fixing issues in parallel. Use when addressing PR review comments, resolving review threads, or fixing…

Generate structured HTML from authoring analysis for AEM Edge Delivery Services. Creates section structure, applies block tables, handles metadata, and manages…

Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation

Correctly call native (C/C++) libraries from .NET using P/Invoke and LibraryImport. Covers function signatures, string marshalling, memory lifetime, SafeHandle, and cross-platform patterns. USE FOR: writing new P/Invoke or LibraryImport declarations, reviewing or debugging existing native interop code, wrapping a C or C++ library for use in .NET, diagnosing crashes, memory leaks, or corruption at the managed/native boundary. DO NOT USE FOR: COM interop, C++/CLI mixed-mode assemblies, or pure managed code with no native dependencies.

Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis

Identify section boundaries and content sequences within a scraped webpage for AEM Edge Delivery Services import. Performs two-level analysis (sections, then…

Analyze content sequences within a section and provide neutral descriptions for AEM Edge Delivery Services. Invoked per section during page import to identify…

Guide for diagnosing and improving MSBuild project evaluation performance. Only activate in MSBuild/.NET build context. USE FOR: builds slow before any…

Run human-in-the-loop review loops over markdown via Proof (proofeditor.ai) — share, view, comment on, edit, and sync collaborative docs. Use when the user…

Analyze content sequences and determine authoring approach (default content vs blocks). Validates block selection and section styling for import/migration to…

Comprehensive pull request review using specialized agents

Preview and verify imported content in local AEM Edge Delivery Services dev server. Validates rendering, compares with original page, and troubleshoots common…

Run comprehensive agent-native architecture review with scored principles

根据迪士尼12原则（适配Web）审查动画代码。用于审查动效、实现动画或检查动画质量时。输出…

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI…