Drawing Review Cn

中国建筑工程施工图图纸会审（图纸自审）专家技能。用于对一整套施工图（建筑/结构/给排水/电气/ 暖通/智能化/室内装修/景观园林/海绵/基坑支护/亮化等专业）开展系统性自审，产出可直接上会签认的图纸会审问题清单与记录表。适用场景： (1) 用户说“帮我做图纸会审”“图纸自审”“审图”“挑图纸问题”“出问题清单”“会审记录” (2) 一次性给出一个装满施工图的文件夹（PDF/DWG），要求找出各专业图纸问题 (3) 要求列出“哪个专业、哪张图纸、哪个部位、什么问题、怎么解决”并做跨专业比较 (4) 需要生成图纸会审记录表（Word/Excel，含设计回复/处理结果/闭环状态列） (5) 需要核查图纸集完整性：图纸目录、图号体系、版本冲突、签章有效性 (6) 仿古建筑 / 木结构 / 文旅 / 文物遗址类项目的专项会审

5 starsImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add Wonggeff/drawing-review-cn --skill drawing-review-cn

Manual install

git clone --depth 1 https://github.com/Wonggeff/drawing-review-cn.git /tmp/drawing-review-cn
mkdir -p ~/.claude/skills
cp -r /tmp/drawing-review-cn/. ~/.claude/skills/drawing-review-cn

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 图纸会审（施工图自审）执行技能

## 0. 核心原则

1. **以经施工图审查机构盖章的图纸集为准**。设计院提供的 CAD 常为更早版本；两者数值不一致时，
   施工与采购以盖章版为准，差异列为问题要求书面确认。
2. **每条问题必须有可核查的定位**：专业 + 图号/图名 + 部位（轴线/标高/房间/表格行）。
   证据不足写“需设计确认”，**不得编造**。
3. **跨专业比较是本技能的核心价值**：单专业挑错容易，跨专业对撞（基准标高、标高体系、
   预留预埋、防火分区编号、面积口径、版本与范围界面）才是会审会议的重点。
4. **区分“设计错误”与“设计范围问题”**：先确认某专业/某单体是否在本次设计范围内，
   再判断缺失是否为问题。
5. 涉及结构安全、消防、文物安全的条目，结论应以**设计单位书面答复与施工图审查机构复核意见**为准。

## 1. 标准执行流程（七步）

```
① 台账 → ② 取证能力 → ③ 基础图通读 → ④ 专业分册并行审查 → ⑤ 项目级/跨专业核查
→ ⑥ 合并去重与分级 → ⑦ 出交付物（问题清单 + 明细 + 会审记录表）
```

详细步骤、检查项与输出物见 **[references/01-审查流程与交付物.md](references/01-审查流程与交付物.md)**。

关键要点：
- **第①步** 用 `scripts/ledger.py` 从文件路径生成图纸台账（专业、图号、文件夹），统计各分册张数，
  识别重复归档、缺号、同名图。
- **第②步** 先建立取证能力再读图。中国施工图 PDF 常见两种情况：
  ①文字层编码损坏（CAD 出图缺 ToUnicode，抽取为乱码）→ 改用 **DWG 全量文字提取**；
  ②正文为矢量轮廓或扫描件，无文字层 → **渲染为 PNG 后图像识读**。
  见 **[references/04-图纸取证方法与工具.md](references/04-图纸取证方法与工具.md)**。
- **第③步** 必须先通读基础图：设计总说明、总平面图、设计依据、防火设计说明、防水专篇、
  各专业设计说明。**项目级矛盾（面积、标高体系、防火分区、设计范围）几乎全部在这一步暴露。**
- **第④步** 按专业分册并行派发子代理，每个子代理一份专业审查要点（见 references/02）+
  统一的 9 列输出格式。**并发上限通常为 8，需分批派发。**
- **第⑤步** 由主代理亲自做跨专业核查（清单见 references/03），不可外包——这是最需要全局视野的部分。
- **第⑥步** 用 `scripts/merge_findings.py` 合并各分册为统一编号清单并统计。
- **第⑦步** 用 `scripts/make03.py` 出明细清单、`scripts/make_docs.py` 出 Word/Excel 会审记录表。

## 2. 问题分类与严重程度（统一口径）

| 类别 | 含义 | 处理方式 |
|---|---|---|
| **A 设计错误** | 违反强制性条文、计算错误、明显设计错误 | 设计出变更图；涉及强制性标准的须重新报审 |
| **B 图纸矛盾** | 平立剖不一致、图与表不符、专业间矛盾、版本冲突 | 设计书面确认 |
| **C 深度不足** | 节点不清、尺寸/做法缺失、说明空白、无法指导施工 | 设计补充说明或详图 |

Read the full skill on GitHub

Details

Skill name: drawing-review-cn
Repository: Wonggeff/drawing-review-cn
Repo updated: 26 September 2026

FAQ

What does the Drawing Review Cn skill do?

How do I install the Drawing Review Cn skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Wonggeff/drawing-review-cn --skill drawing-review-cn. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Drawing Review Cn popular?

It lives in Wonggeff/drawing-review-cn, which has 5 GitHub stars and 0 forks.

Related skills

Grok Video Editing

AlizayAyesha/grok-video-editing-skill

Record a product demo on a Linux desktop, cut it into feature clips, and render an on-brand 1080p motion-graphics promo video entirely with code (ffmpeg + HTML Canvas + headless Chromium via Playwright + a procedural audio mix). Use when asked to make a product demo, launch video, or social promo themed to a website's colors and fonts.

Images, Video & Audio

Demo Video

surajshetty3416/demo-video-skill

Produce a polished, ScreenStudio-style 60fps product demo video of a web app with a tiny, dependency-light pipeline — Playwright frame capture + a multiprocess Pillow compositor streaming into ffmpeg (no Node/Remotion). Drives the app one step per frame so playback is true 60fps regardless of capture speed, then renders a gradient background, a rounded window with a soft shadow, a crisp vector cursor, click pulses, keyboard-shortcut keycaps, and a cinematic push-in that scales the whole window and eases out at the end; HD=1 re-renders the same capture at retina resolution. Also ingests hand-dr

Images, Video & Audio

Hyper3d Documentary

xiaohuailabs/hyper3d-documentary

用 Hyper3D（Rodin Gen-2.5）把一个科普题材做成可分享的单文件网页 3D 纪录片：需求问答 → 写脚本 → 生参考图 → 生成 3D 模型 → 模型库审核 → 动画成片，外加一个项目总览管理页。

Images, Video & Audio

Construction Video Prompt Engineering

XuJinghao221/construction-video-prompt-skill

Generate copy-ready English and Chinese positive/negative prompts for engineering video clips after identifying the clip type and requested output frame size. First/last frame files are optional and are normally supplied later to the video model; use this skill for construction actions, viewpoint transitions, static showcases, stage boundaries, object continuity, camera stability, action direction, and repair of observed failures. Do not use for generic cinematic prompts, frame creation, video generation, or full video editing.

Images, Video & Audio

Image Gen

behzadsp/claude-code-image-gen

Generate images from text prompts through OpenAI (gpt-image-2.5), Google Gemini (gemini-3-pro-image), Higgsfield, Black Forest Labs FLUX, or any OpenAI-compatible endpoint such as xAI Grok or Recraft. Use when the user asks to generate, create, render, or make an image, hero image, illustration, logo concept, OG image, poster, thumbnail, or social card, when a project has placeholder images to replace, or when the user names an image model or asks which image providers are available.

Images, Video & Audio

Cherina Pod

realchendahuang/cherina-pod

Turn any podcast episode into a listening-practice lesson for language learners — an offline player page (line-by-line playback, loop, blind listening, word-by-word highlight), a printable bilingual handout, and key-phrase notes. Default is English audio with Chinese translation; Chinese audio with English translation also works. Use when the user wants to practise listening with a podcast, e.g. "把这期播客做成精听课", "用播客练听力", "做一份听力讲义", "播客精听", "make a listening lesson from this podcast".

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.