product-prd-extract SKILL.md skillA
product-prd-extract from mingdui/ai-product-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mingdui/ai-product-skills/product-prd-extract@git:20261013.51f741bPins git:20261013.51f741b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mingdui/ai-product-skills
- Path
skills/product-prd-extract/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261013.51f741b, committed Oct 13, 2026
- First version recorded
- Oct 13, 2026
- Size
- 10,020 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
把 Word（.docx）PRD 或粘贴的 PRD 文本转成结构化 Markdown，落到 docs/prd/<feature-name>/prd.md，直接接进本仓库的链路。当用户提到「解析 PRD」「提取需求文档」「PRD 转结构化」「PRD 转 Markdown」「Word 转需求」「导入 PRD」，或直接丢来一个 .docx 要求分析时使用。适用于需求来源方只给了一份 Word 的情况；不需要解析 Word、要直接写 PRD 时用 prd-write 或 context-to-prd。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Word PRD 结构化 需求来源方给的常常是一份 Word——格式自由、信息分散、隐含假设多。本 Skill 把它转成结构化 Markdown 落到 `docs/prd/<feature-name>/prd.md`，让 `grill-with-prd`、各原型 skill、`acceptance-checklist` 能直接读。 **只做转换与结构化，不发明需求。** 原文没写的，一律标 `[UNKNOWN]`。 ## 使用边界 - **适用**：手上是 `.docx` 文件，或一大段粘贴过来的 PRD 文本。 - **不适用**： - 需求还停在口头、边界没问清 → 用 `requirement-clarify` - 需求已经清楚，要直接写 PRD → 用 `prd-write` 或 `context-to-prd` - 会议纪要、聊天记录 → 那不是 PRD，用 `context-to-prd` 更合适 ## 依赖与自动准备 `.docx` 本质是 ZIP 压缩的 XML，Read 工具读不了，所以本 skill 自带一个 Node 解析脚本。 **这是本仓库 11 个 skill 里唯一有运行环境要求的**，其余全是纯 Markdown。 脚本需要 Node.js ≥ 20 和三个开源解析库（`mammoth`、`jszip`、`xml2js`）。 ### 开工前先自检并准备——不要先问用户，先自己查 按顺序执行，**前一步成功就跳到下一步**。 **第 1 步：查 Node 是否可用** ```bash node --version ``` 有输出且 ≥ v20 → 进第 2 步。报 `command not found` 或版本过低 → 跳到第 3 步。 **第 2 步：查依赖是否已装** ```bash ls "<本 skill 目录>/scripts/node_modules" >/dev/null 2>&1 && echo 已装 || echo 未装 ``` 未装就**直接装，不必先征求同意**——但装之前用一句话说清你在装什么： > 解析 Word 需要先装 3 个开源解析库（mammoth / jszip / xml2js），几 MB，装一次以后不用再装。 ```bash npm --prefix "<本 skill 目录>/scripts" install ``` 装失败（无网络、npm 报错）**不要卡住**，直接走第 4 步，并说明失败原因。 **第 3 步：Node 不可用 → 给具体安装指引 + 退路** 不要只说「请先安装 Node」。给可照做的命令： | 平台 | 做法 | |---|---| …
Read the whole file at its exact version.
How to install
mdr add mingdui/ai-product-skills/product-prd-extract@sha256:78698061c618fc2fThe line at the top of this page pins the label git:20261013.51f741b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_eu5rldbuyi4jbymc)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, all committed on Oct 13, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261013.51f741b latest | 2026-10-13 | 51f741b | 10,020 B | A | view · diff |
| git:20261013.4d20990 | 2026-10-13 | 4d20990 | 9,675 B | A | view · diff |
| git:20261013.60e8978 | 2026-10-13 | 60e8978 | 9,682 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10020 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
mingdui/ai-product-skills · 12 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_eu5rldbuyi4jbymc GET https://markdownregistry.com/api/v1/resolve?ref=mingdui/ai-product-skills/product-prd-extract GET https://markdownregistry.com/api/v1/blob/78698061c618fc2f75cf4054e5e82ab94e16fafcbbcb6993db1788720ac13702
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.