Research and Audits

智能多主题深度研究工具，自动分析材料并生成系统化研究文档。支持任意材料输入，通过 并行启动多个独立研究 Agent 进行深度检索，形成精简的研究知识库。

You are Claudeception: a continuous learning system that extracts reusable knowledge from work sessions and codifies it into new Claude Code skills. This enables autonomous improvement over time.

Use this skill whenever you are dealing with Node.js code to obtain domain-specific knowledge for building robust, performant, and maintainable Node.js applications.

Create a comprehensive company profile that extracts executive insights, product strategy, transformation initiatives, and organizational dynamics from publicly available sources. Use this to understand competitive landscape, evaluate partnership opportunities, benchmark best practices, prepare for interviews, or...

Safely clean up accumulated git worktrees and local branches by categorizing them into: safely deletable (merged), potentially related (similar themes), and active work (keep).

Differential analysis to verify commits address security findings without introducing bugs.

Source details, install context, and public review data are available on the full page.

Build games in small steps and validate every change. Treat each iteration as: implement → act → pause → observe → adjust.

Package: @vercel/before-and-after Never use before-and-after (wrong package).

Automatically fetch latest library/framework documentation for Claude Code via Context7 API

Create engaging, authentic LinkedIn posts that drive meaningful engagement and establish thought leadership.

Analyze website performance using Google Analytics data to provide actionable insights and improvement recommendations.

Generate hierarchical AGENTS.md files. Root + complexity-scored subdirectories.

Maestro is not a tool; it is a Governance Protocol that transforms an AI agent from a reactive coder into a proactive Elite Software Architect . It enforces discipline, maintains project continuity, and orchestrates specialized expertise.

NEVER access files outside the current working directory (CWD). All source scanning, reading, and vault output MUST stay within CWD and its subdirectories. If the user provides an external path, ask them to copy the files into CWD first.

Build RAG (Retrieval Augmented Generation) pipelines via inference.sh CLI.

This skill enables creation of high-quality academic research documents with proper scholarly standards, verified peer-reviewed sources, and IEEE-format citations.

使用此 skill 处理已有中文 LaTeX 学位论文项目中的定向问题。保持低摩擦：先判断最小匹配模块，再运行对应脚本，最后以论文审阅友好的格式返回问题和建议。

Campaign performance analysis with engagement metrics, ROI calculations, and platform benchmarks.

The web renderer is in packages/web-renderer and the test suite is in packages/web-renderer/src/test .

基于 AI 智能分析的文档配图生成工具。无需依赖特定格式，自动理解内容并生成专业配图。

Source details, install context, and public review data are available on the full page.

Performance optimization and composition patterns for React components. Contains 33 rules across 6 categories focused on reducing re-renders, optimizing bundles, component composition, and avoiding common React pitfalls.

Create investor-ready pitch deck visuals via inference.sh CLI.