requirement-analysis SKILL.md skillA
requirement-analysis from wikkygao/requirement-analysis is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wikkygao/requirement-analysis/requirement-analysis@v2.0.0Pins v2.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wikkygao/requirement-analysis
- Path
SKILL.md- Versions recorded
- 10
- Latest version
- v2.0.0, committed Oct 22, 2026
- First version recorded
- Sep 1, 2026
- Size
- 25,944 bytes
- Repository stars
- 11
- License
- none declared
多格式需求文档分析与整合。自动解析 Markdown、Excel、Word、思维导图文件，智能去重和补充需求信息，生成标准化的 PRD.md 文档。大文件采用分层提取避免上下文溢出；支持用户指定子目录输出；支持完整版/业务摘要版模板。可选集成 prototype-designer 生成原生或 HTML 原型；T8 只决定产出形态，不选择具体设计工具。适用场景：用户有多个需求来源需要整合、需要从零梳理需求、需要将模糊想法转化为结构化 PRD、需要可视化原型。触发词：需求分析、分析需求、整理需求、PRD、需求文档、需求梳理、梳理需求、可视化原型、页面设计。.
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
# 需求分析技能
<workflow>
## 工作流
```mermaid
graph TD
START([用户请求]) --> SR{{场景识别}}
SR -->|检测 PRD.md 存在| Mode{工作模式}
Mode -->|无 PRD| T0["T0: 模式选择"]
Mode -->|有 PRD| T0
T0 --> T1["T1: 文档扫描"]
T1 --> HasNL{含自然语言?}
HasNL -->|是| T1_5["T1.5: 对话式需求提取"]
HasNL -->|否| T2["T2: 文档解析与功能提取"]
T1_5 --> T2
T2 --> T3["T3: 智能整合(去重/冲突/补充)"]
T3 -->|🔴 CHECKPOINT| T4["T4: INVEST 质量评估"]
T4 --> T5["T5: 需求澄清"]
T5 -->|🔴问题未清零| T5
T5 -->|🔴全部清零| T6["T6: 最终确认"]
T6 -->|🔴 CHECKPOINT| T7["T7: 生成 PRD.md"]
T7 -->|🔴 CHECKPOINT| T8{"需要可视化原型?"}
T8 -->|否| END([完成])
T8 -->|是| T8_Form{"选择产出形态?"}
T8_Form -->|原生设计文件| T8_Native["T8: 交给 prototype-designer 选择原生工具"]
T8_Form -->|仅 HTML| T8_Html["T8: 生成可交互 HTML 原型"]
T8_Native --> END
T8_Html --> END
```
> 分工标注: `[LLM 决策]` 语义/交互 | `[Script]` 确定性脚本 | `[LLM→Script]` 决策后脚本执行
### 场景识别
| 条件 | 场景 | 入口 Task |
| ------------------ | ------------------ | ------- |
| 工作区无 PRD.md，默认 | 标准模式 (standard) | T0 |
| 工作区无 PRD.md，用户选择快速 | 快速模式 (quick) | T0 |
| 工作区已有 PRD.md | 增量模式 (incremental) | T0 |
### 跳过规则
…Read the whole file at its exact version.
How to install
mdr add wikkygao/requirement-analysis/requirement-analysis@sha256:ac751a1a068bc98cThe line at the top of this page pins the label v2.0.0, 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_jnis2b64bknhehfj)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Sep 1, 2026 and Oct 22, 2026, about one every 6 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.0.0 latest | 2026-10-22 | e253e38 | 25,944 B | A | view · diff |
| v1.3.2 | 2026-10-22 | 2774075 | 25,131 B | A | view · diff |
| v1.2.4 | 2026-10-22 | 2747584 | 25,131 B | A | view · diff |
| v1.2.3 | 2026-10-22 | 326bb6d | 25,131 B | A | view · diff |
| v1.2.2 | 2026-09-20 | c642634 | 24,440 B | A | view · diff |
| v1.2.1 | 2026-09-17 | 01d8ff8 | 23,785 B | A | view · diff |
| v1.2.0 | 2026-09-07 | cdebe14 | 23,654 B | A | view · diff |
| v1.1.0 | 2026-09-01 | 0ac3d07 | 20,743 B | A | view · diff |
| v1.0.0 | 2026-09-01 | 84c13ce | 20,743 B | A | view · diff |
| v1.0.0 | 2026-09-01 | cd76e35 | 20,519 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 (25944 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
wikkygao/requirement-analysis · 11 stars · license none declared · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_jnis2b64bknhehfj GET https://markdownregistry.com/api/v1/resolve?ref=wikkygao/requirement-analysis/requirement-analysis GET https://markdownregistry.com/api/v1/blob/ac751a1a068bc98c60f2165c2f50253e956e734c28e58ff0d1e508690d4f6387
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.