CoderSkills/.agents/skills/standardize-wiki-docs/SKILL.md
Use when converting wiki-exported requirement documents (containing docx, xlsx, md, images) into standardized templates (functional requirement docs + FAQ docs), with a gaps checklist for product managers to supplement missing information.
npx skillsauth add songsunny00/myskills standardize-wiki-docsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
将 Wiki 导出的混合格式需求文档(md、docx、xlsx、图片)阅读梳理后,按标准化模板输出结构化的功能需求文档和 FAQ 文档,并自动识别信息缺失部分生成待补充清单。
用户调用:/standardize-wiki-docs
需要两个输入:
WikiResource/V1.0.0/01-样本中心产品设计文档,也可以是整个版本目录如 WikiResource/V1.0.0)标准模版/)如果用户未提供路径,逐一询问。
digraph flow {
rankdir=TB;
"接收输入路径" -> "扫描目录结构";
"扫描目录结构" -> "是版本目录还是模块目录?" [shape=diamond];
"是版本目录还是模块目录?" -> "遍历所有子模块目录" [label="版本目录"];
"是版本目录还是模块目录?" -> "处理单个模块" [label="模块目录"];
"遍历所有子模块目录" -> "处理单个模块" [label="逐个"];
"处理单个模块" -> "第一步:解析文档";
"第一步:解析文档" -> "第二步:阅读理解";
"第二步:阅读理解" -> "第三步:填充功能需求文档";
"第三步:填充功能需求文档" -> "第四步:生成FAQ文档";
"第四步:生成FAQ文档" -> "第五步:识别缺失信息";
"第五步:识别缺失信息" -> "第六步:生成待补充清单";
"第六步:生成待补充清单" -> "输出结果";
}
parse_docs.py 将 docx/xlsx 转为可读文本:
python .claude/skills/standardize-wiki-docs/parse_docs.py "<需求文档路径>" --latest
_parsed/ 子目录.md 文件,直接用 Read 工具读取优先级规则:
converted_markdown/ 目录,优先读取其中的 md 文件作为主文档--latest 参数自动处理)_parsed/images/(docx提取)、assets/、media/、converted_markdown/media/ 等子目录_parsed/images_recognized.md,每张图片记录:文件路径、图片类型、关键信息必须完整阅读所有文档后再开始整理,包括 _parsed/images_recognized.md,建立全景理解:
Excel 内容处理要点:
图片内容处理:结合 _parsed/images_recognized.md 理解UI布局、流程关系和数据流向
读取标准模板 标准化模板-功能需求文档.md,按模板结构逐节填充:
| 模板章节 | 填充来源 | 填充要点 | |---------|---------|---------| | 文档元数据 | 原文档基本信息 | 文档ID按 REQ-[项目]-[编号] 格式生成,关键词从内容提取 | | §1 需求概述 | PRD 背景章节 | 提取问题描述、业务价值、目标用户 | | §2 功能总览 | PRD 功能列表 + 流程图 | 核心功能一句话列表、整体流程图 | | §3 功能详细说明 | PRD 功能描述 + 规则 + 异常 + 图片 | 按功能点组织,每个功能点包含5个子章节:功能描述、适用场景、操作流程(含UI截图)、业务规则(仅该功能特有的)、异常处理 | | §4 数据规则与权限 | 字段规则 Excel + PRD 权限章节 | 跨功能的公共数据规则表格、权限角色矩阵 | | §5 界面原型 | 图片识别结果 | 页面位置、交互说明、原型链接(具体截图已嵌入各功能点的操作流程中) | | §6 非功能性需求 | PRD 非功能章节 | 性能、兼容性、安全要求 | | §7 依赖关系 | 跨模块引用分析 | 前置依赖、影响范围 | | §8 验收标准 | 测试用例 Excel | 功能验收点、测试用例 | | §9 FAQ | 常见问题提取 | 从需求中提炼用户可能的问题 |
图片引用规则(按类型区分处理):
**原型截图**:

> 页面说明:顶部查询区域,中部数据列表,底部分页控件
**流程图**:

**流程说明**:
1. 用户填写信息 → 系统校验
2. 校验通过 → 保存 → 生成编号
3. 校验失败 → 提示错误 → 返回修改
其他填充原则:
[待补充][来源:图片识别],提醒产品经理校验读取标准模板 标准化模板-FAQ问答文档.md,从需求文档中提炼 FAQ:
FAQ 提取来源:
FAQ 编号规则:FAQ-[模块缩写]-[序号]
对照标准模板,逐节检查是否有信息缺失:
必须检查的缺失项:
将所有缺失信息整理为 JSON,然后运行:
python .claude/skills/standardize-wiki-docs/generate_gaps.py "<JSON文件路径>" "<输出Excel路径>"
JSON 格式:
[
{
"id": 1,
"module": "所属模块",
"section": "对应模板章节",
"field": "缺失的具体字段/内容",
"priority": "必填|建议补充|可选",
"context": "当前已有的相关信息(帮助产品经理理解上下文)",
"suggestion": "建议补充的方向或示例"
}
]
每个模块生成:
<模块目录>/
_parsed/
images_recognized.md # 所有图片的识别记录(第一步生成)
*.txt # docx/xlsx 解析结果
_standardized/
功能需求文档.md # 按标准模板填充,含图片引用和文字描述
FAQ问答文档.md # 按标准模板生成的FAQ文档
待补充清单_YYYYMMDD.xlsx # 缺失信息清单
| 问题 | 处理方式 |
|------|---------|
| 图片无法识别 | 在文档中标注 [图片无法识别,请人工补充],并加入待补充清单 |
| Excel 文件损坏 | 跳过该文件,在待补充清单中记录 |
| 多版本文档内容冲突 | 以最新版本为准,在文档中标注版本来源 |
| 模板中某章节完全无对应内容 | 保留章节标题,内容填 [待补充],加入待补充清单 |
| 需求文档路径下无子模块 | 将整个目录视为单个模块处理 |
development
Skill Vetter — ClawHub Security-first vetting protocol for AI agent skills. Never install a skill without vetting it first. When to Use - Before installing any skill from ClawdHub - Before running skills from GitHub repos - When evaluating skills shared by other agents - Anytime you're asked to install unknown code Vetting Protocol Step 1: Source Check Questions to answer: - [ ] Where did this skill come from? - [ ] Is the author known/reputable? - [ ] How many downloads/stars does it have?
tools
Use when the user wants to add a record into a DingTalk table through an automation webhook, especially when they describe the record in natural language, provide a Markdown file path as the content source, or need field validation, a field-summary preview, and explicit confirmation before sending. Image recognition is opt-in — only enabled when the user explicitly requests it.
development
Use when reviewing novel chapters or manuscripts for logic consistency, character authenticity, plot cohesion, foreshadowing payoff, emotional resonance, narrative vividness, and content compliance. Also triggers for first-chapter editorial audits against web novel platform submission standards. Triggers on requests like "check the story", "review this chapter", "is this consistent with character", "improve story flow", "add foreshadowing", "check content safety", "前三章审核", "过稿检查", "开篇钩子", "审查前三章", or "editorial submission check".
tools
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.