Skip to content
Agentmart
Submit a tool

taiyi-reanalyze

TaiyiForge 辅助 — 重新理解已有需求工件,找出矛盾、缺口、歧义。OpenCode / Claude / Codex / Cursor 通用。

Skill by Dong90

IndexedMIT★ 859
Write a review

Chalk Labs

Need help deploying taiyi-reanalyze?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/dong90-taiyi-reanalyze

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

TaiyiForge 辅助 — 重新理解已有需求工件,找出矛盾、缺口、歧义。OpenCode / Claude / Codex / Cursor 通用。

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/taiyi-reanalyze

What's inside

Skill name
taiyi-reanalyze
Description
TaiyiForge 辅助 — 重新理解已有需求工件,找出矛盾、缺口、歧义。OpenCode / Claude / Codex / Cursor 通用。
License
MIT
Instructions
147 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# taiyi-reanalyze

## 目的

当需求文档写了一段时间后,团队对需求的理解可能已经变化。这个技能重新阅读 CHANGE.md 和 REQUIREMENT.md,找出其中的矛盾、缺口和模糊点,产出一份「二次理解」报告。

## 何时使用

reanalyze 跑在 requirement 写完之后、dev 开始之前:

```
change → requirement → /taiyi:sp reanalyze(重新理解)
                │               │
                ▼               ▼ 产出 REANALYZE.md
              design → ui-design → task → dev → ...
                              │
              缺口/歧义 → 回到 requirement 补 AC
```

| 信号 | 建议 |
|------|------|
| change 写完后放了一周以上才开始 dev | 必跑 |
| 多人协作,中间有人改过 scope | 必跑 |
| requirement 写到一半觉得不对劲 | 必跑 |
| review 阶段发现设计和需求对不上 | 必跑 |
| 刚写完 change,记忆还新鲜 | 跳过 |

## 何时不用

- 刚写完 change 和 requirement,记忆清晰
- 只有 1-2 个 AC 的简单 change
- micro/nano profile 的变更(文档太少,没东西可重分析)

## 输入

- `.taiyi/changes/<slug>/CHANGE.md`
- `.taiyi/changes/<slug>/REQUIREMENT.md`
- (可选)`CONTEXT.md` 代码情报
- (可选)上游 README/PRD

## 输出

一份重新分析报告,写到 `.taiyi/changes/<slug>/REANALYZE.md` 或直接在聊天里展示。

格式:
```markdown
# Reanalyze: <slug>

> 重分析日期 · 原始 change 日期 · 间隔 X 天

## 重新理解

用一句话重述这个 change 要解决什么问题。

## 一致性检查

| 检查项 | 状态 | 说明 |
|--------|------|------|
| CHANGE 和 REQUIREMENT 的范围一致 | ✅ | |
| AC 覆盖了所有 scope 条目 | ❌ | 缺少「权限校验」的 AC |
| 设计方案的假设在代码情报中成立 | ⚠️ | CONTEXT 标记了风险区 |
| 没有自相矛盾的 AC | ✅ | |

## 缺口

列出 REQUIREMENT 中应该覆盖但没覆盖的内容:
1. **缺口 1**:XXX 场景没有 AC
2. **缺口 2**:未定义错误处理策略

## 歧义

列出表述不清、有多种理解的内容:
1. **歧义 1**:「支持多种登录方式」—— 具体哪几种?oauth 还是手机号?
2. **歧义 2**:「高性能」—— 量化标准是什么?

## 建议

- 补充 AC:「XXX」
- 向产品确认:「YYY」
- 缩小 scope:「ZZZ 放到下一期」
```

## 执行步骤

### 1. 重新阅读

把 CHANGE.md 和 REQUIREMENT.md 当成第一次读:
- 用一句话概括这个 change 的**核心问题**
- 列出你理解中的**关键约束**(时间、依赖、不可碰的部分)

### 2. 交叉校验

| 核对 | 方法 |
|------|------|
| CHANGE vs REQUIREMENT | 每个 scope 条目在 REQUIREMENT 中有对应的 AC 吗? |
| AC 完整性 | happy path / error path / edge case 都覆盖了吗? |
| 假设 vs 现实 | CONTEXT.md 中的代码现实是否推翻了设计假设? |
| 自洽性 | AC 之间有没有互相矛盾的? |

### 3. 找缺口

重点关注:
- 错误处理:每个 AC 的失败场景定义了吗?
- 非功能需求:性能、安全、可观测性?
- 边界条件:空输入、超大数据、并发?

### 4. 找歧义

- 模糊词:「支持」「优化」「完善」→ 要求具体化
- 未定义术语:「用户」「订单」→ 确认定义
- 隐含假设:「登录后才能用」→ 显式写出来

### 5. 产出建议

- 需要补充的 AC
- 需要向上游确认的问题
- 建议缩小 scope 的部分

### 6. 自动修复(报告展示后询问)

From Dong90/oh-my-taiyiforge, MIT.

More from Dong90/oh-my-taiyiforge

Signals

Stars
859
Forks
22
Open issues
1
Last commit (this folder)
Jun 27, 2026 (4 months ago)
Last release
Jul 15, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Dong90

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get taiyi-reanalyze running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying taiyi-reanalyze?

CallGet help
Cite this page

taiyi-reanalyze skill. Agent Mart. https://agentmart.dev/skills/dong90-taiyi-reanalyze (last updated 2026-10-24)