phyai

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.

去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。

Use this skill when implementing, porting, integrating, reproducing, or debugging support for a model in PHYAI. This includes translating architecture research into PHYAI code, adding model configuration, modeling modules, runners, schedulers, weight loading, layer reuse, focused tests, validation scripts, and implementation plans while respecting PHYAI model-development constraints.

Analyze a phyai .memory file or directory supplied by the user: parse what task/session it records, locate and inspect the referenced code repository when available, verify claims against local code and git history, and explain what the memory did, changed, validated, and left unresolved.

Generate a local phyai environment report for debugging system, Python, CUDA/GPU, dependency, workspace package, git, and PHYAI_* configuration issues. Use when asked to inspect, summarize, export, or diagnose the current phyai development/runtime environment.

Use this skill when the user provides a paper, arXiv link, technical report, model card, checkpoint name, GitHub repository, or local codebase and asks to research, explain, compare, or implement a model architecture. This skill guides architecture research for PHYAI: source collection, paper/code tracing, module decomposition, tensor shape analysis, dependency mapping, and implementation-oriented reporting.

Triage and resolve review comments on a GitHub PR — fetch all comment surfaces (issue / inline / review), validate each suggestion against upstream source rather than trusting blindly, present findings to the user before editing, then make focused changes and re-run tests. Use when the user asks to "check PR N's comments", "address review feedback", "resolve PR comments", or similar.