AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Source To Spec

skill-yuaicode-ai-skills-source-to-spec · by YuAICode

把 PDF / 飞书文档 / 会议纪要 / 长文本收敛成"可落地需求"spec(与 slack-to-spec 同一套模板)。当用户说"把这份文档/纪要/PDF 整理成需求 / 出个 spec"时触发。抽取需求点、决策(含被推翻方案)、待定问题,产出结构化、可追溯、能直接喂开发的 markdown。

↗ Repository
— No reviews yet
0 installs
39 views
0.0% view→install

Install

$ agentstack add skill-yuaicode-ai-skills-source-to-spec

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-yuaicode-ai-skills-source-to-spec)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Source To Spec? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

source-to-spec — 文档/纪要 → 可落地需求

slack-to-spec 的姊妹篇:输入从 Slack 换成 PDF / 飞书 doc / 会议纪要 / 任意长文本,产出同一套 spec。 核心同样不是"总结",而是 抓决策(尤其被推翻/取代的方案)+ 拎隐藏的开发需求 + 划开工红线。

何时触发

用户说"把这份文档/纪要/PDF 整理成需求 / 出个 spec / 这个会议纪要拆成开发任务"。

用法

/source-to-spec

流程

  1. 读源:
  • PDF / 图片 / Word → 直接读(读不到的扫描件如实标"待补",不臆造)。
  • 飞书 doc → 有飞书 MCP 就用工具读正文;否则请用户导出/粘贴。
  • 纯文本 / 会议纪要 → 直接处理。
  • 多个来源 → 合并,并在 §来源 标清每条出处。
  1. 抽取:需求点、决策(谁拍的板/依据/有没有反转)、待定问题、隐藏需求(一句"目前没有,需后续做"要升级成 AC)。
  2. 合成 spec:按下面模板产出。
  3. 落盘 + 报告:写到 -spec.md(或问用户放 docs/prd//docs/plans/);报告读了什么、明确列出"读不到、需人补"的缺口。

Spec 模板

#  — 可落地需求 (Spec)

> 来源:
> 状态:草稿 V0.1(待  拍板)

## 1. 背景 / 要解决什么
## 2. 决策日志 ★最容易丢 / 核心
| # | 决策 | 结论 | 拍板人 | 依据/时间 | 被撤销/取代的方案 |
|---|---|---|---|---|---|
> 反转/撤销单独标出(删除线 + 取代时间)——回溯"为啥这么定"的关键。

## 3. 需求点(可验收)
### 3.x  — P0/P1,
- [ ] ACn: 

## 4. 影响面 / Blast radius
## 5. 开放问题(未拍板,别开工对应模块)
## 6. 时间线
## 7. 来源(可回溯)
-

硬规则

  1. 决策日志必须有"被撤销/取代的方案"——上午定下午改的要留痕 + 注明时间。
  2. 区分可读 vs 不可读来源:读不到的(扫描件/加密 PDF)如实标缺口,绝不编。
  3. 不臆断:拿不准标"待确认/待补"。
  4. 拎隐藏需求:埋在长文里的"需后续开发"升级成明确 AC。
  5. 划开工红线:未拍板的(端选型/合规/金额/命名)进 §5,标"别开工对应模块"。
  6. 产出中文 + 英文,不引入其他自然语言。
  7. 只读 + 只产出本地文档,不碰任何线上系统。

衔接

spec 出来后,可直接喂 writing-plans skill 出开发计划 → TDD 执行。 与 [slack-to-spec](../slack-to-spec) 共用模板;来源是 Slack 频道时用那个。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in AI & ML