Chalk Labs
Need help deploying taiyi-requirement?
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.
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-requirement
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.
About
Reviews
Write a reviewNo 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-requirement
What's inside
- Skill name
taiyi-requirement- Description
- TaiyiForge 第2阶段 — 需求分析,REQUIREMENT.md。四端通用。
- License
- MIT
- Instructions
- 243 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Files (1)
- SKILL.md
SKILL.md (first lines)
# taiyi-requirement — 需求分析
> 进入本阶段前请优先读 `.taiyi/changes/<slug>/PHASE-CONTEXT.md`(~500 tokens),不要全量加载上游工件。
## 框架集成
本阶段使用以下框架:
| 框架 | 用途 | 何时加载 |
|------|------|---------|
| **Harness** | 阶段门禁与推进(`status` → `continue`;legacy:`npx taiyi complete`) | 全程 |
| **OpenSpec** | 将 REQUIREMENT.md 同步到 openspec 格式 | 可选 |
**Superpowers / GStack / Spec-Kit / OMO** 在本阶段不涉及。
## 前置门禁(Pre-flight)
### 0.1 上游检查
- change 阶段已过关(`engineTruth.completedPhases` 含 `change` 或 `currentPhase` 已推进)
- 无跨 change 的 AC 冲突(`taiyi list` 检查其他活跃 change 的 scope)
### 0.2 Profile 判定
| Profile | REQUIREMENT.md 要求 |
|---------|-------------------|
| `full` | 完整:User Stories + AC(Given/When/Then) + 域语言 + Traceability |
| `api/ui` | User Stories + AC,域语言可选 |
| `lite` | 仅 AC 列表,可省 User Stories |
| `micro/spike` | 可跳过本阶段 |
| `nano` | 跳过 |
### 0.3 触发者检查
每个 FR 必须声明触发点:
- 每个 FR 必须填写 `trigger`(谁调用、什么时机)
- `trigger` 指向的 `caller_module` 不在本 change scope 中 → 填 `blocked_by` 标注依赖
- `blocked_by` 非空 → 本阶段不能过关,等依赖 change 完成后再继续
```
"functional_requirements": [{
"module": "orchestrator",
"items": [{
"id": "FR-T01",
"description": "track(slug,role,amount) 更新 pipeline.json tokenBudget.used",
"trigger": "executor.dispatch() 每次调用后",
"caller_module": "packages/orchestrator/src/executor.ts",
"blocked_by": "M4-executor"
}]
}]
```
`blocked_by` 非空时引擎会在 status 中报 blocker,阻止进入 design 阶段。
### 0.4 前置检查清单
- [ ] change 阶段已过关
- [ ] 理解 CHANGE Scope 和 Out of Scope 边界
- [ ] 每个 FR 有 trigger(谁调用、什么时机);caller 不在 scope 时填 blocked_by
---
## 步骤
### 工件契约
| 层 | 路径 | 职责 |
|----|------|------|
| **语义真源** | `requirement.json` | Zod(`src/schemas/requirement.ts`) |
| **生成视图** | `REQUIREMENT.md` | hbs(`src/templates/requirement.hbs`) |
| **流程** | 本 Skill | US / AC / 域语言 / Traceability 纪律 |
**工作流**:编辑 json → `scripts/taiyi-forge.sh render <slug> requirement` → `status` → `continue`。
详见 [`docs/taiyi/artifact-contract.md`](../../docs/taiyi/artifact-contract.md)。
### json 字段(Zod 摘要)
| 字段 | 要求 |
|------|------|
| `title` | 一句话概括核心需求 |
| `features` | 核心功能点列表 |
| `scope_out` | 明确排除项(对齐 CHANGE `scope.excludes`) |
| `acceptance_criteria` | ≥1 条;`id` + `description`;Given/When/Then 写在 description |
| `functional_requirements` | 可选;按模块组织 |
| `non_functional` | 可选;performance / security / availability |
| `error_rescue_map` | 可选;错误 → 用户可见 → 恢复 |
| `shadow_paths` / `non_happy_path_cases` | 可选;边界与非快乐路径 |
| `dependencies` | 可选;外部依赖与风险 |
| `evidence` | AC 标 `is_checked=true` 时必填 |
### 写作指引(填入 json,render 生成 REQUIREMENT.md)
### 1. 拆 User Stories
从 CHANGE.md Motivation + Scope 拆出用户故事。每条用标准格式:
```
## US-{N}: {标题}
As a **{角色}**
I want **{功能}**
So that **{价值}**
### Acceptance Criteria
**AC-{N}.{M}**: {描述}
Given {前置条件}
When {操作}
Then {预期结果}
```
**要求**:
- 每条 US 必须能追踪到 CHANGE.md 的 Motivation 或 Scope
- US 不写技术方案(不在需求层说"用 Redis")
### 2. 写 AC(Acceptance Criteria)
每条 AC 使用 Given/When/Then 格式:From Dong90/oh-my-taiyiforge, MIT.
More from Dong90/oh-my-taiyiforge
- 0.712score
taiyi-orchestrator
Dong90
TaiyiForge 统一入口 — 意图解析、阶段路由、Token预算、工件预检。Use when 用户说"开始/继续/审查/测试/设计"等流程相关意图。
SkillCFreshness: C★ 859Claude Code +9 - 0.710score
taiyi-compress
Dong90
TaiyiForge 辅助 — Token 压缩编排:/taiyi:token compress + Superpowers subagent + ECC strategic-compact / handoff。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-restyle
Dong90
TaiyiForge 辅助 — UI 视觉改版任务清单(ui-restyle-tasks)。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-plan
Dong90
TaiyiForge /taiyi:plan — 项目规划入口:把 README/PRD 拆解为独立 change 清单,推荐 profile 和依赖关系。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-architect
Dong90
TaiyiForge 辅助 — 架构决策记录 ADR(长期影响决策的可追溯补充)。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-diagram-c4
Dong90
TaiyiForge 辅助 — 从代码反推 C4 架构文档(Observed/Inferred 分层 · Mermaid 真源)。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-diagram-pipeline
Dong90
TaiyiForge 辅助 — 架构图三步流水线编排(C4 真源 → 工程图同步 → PNG 渲染)。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-diagram-flow
Dong90
TaiyiForge 辅助 — 业务流程图 / 状态机 / 序列图(Mermaid flowchart)。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-diagram-render
Dong90
TaiyiForge 辅助 — 将 C4/architecture Mermaid 渲染为 SVG/PNG(视觉审查 · 不改架构边界)。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-evolve
Dong90
TaiyiForge 辅助 — 实现后架构与文档同步(architecture-sync)。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-reanalyze
Dong90
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。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-ultrawork
Dong90
TaiyiForge ultrawork — 并行切片 + Cursor Task 自动派发契约(对标 OMC ultrawork + spawn_agent)
SkillCFreshness: C★ 859Claude Code +9
Signals
- Stars
- 859
- Forks
- 22
- Open issues
- 1
- Last commit (this folder)
- Jul 11, 2026 (3 months ago)
- Last release
- Jul 15, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Dong90/oh-my-taiyiforge
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Dong90
- 0.712score
taiyi-orchestrator
Dong90
TaiyiForge 统一入口 — 意图解析、阶段路由、Token预算、工件预检。Use when 用户说"开始/继续/审查/测试/设计"等流程相关意图。
SkillCFreshness: C★ 859Claude Code +9 - 0.710score
taiyi-compress
Dong90
TaiyiForge 辅助 — Token 压缩编排:/taiyi:token compress + Superpowers subagent + ECC strategic-compact / handoff。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-architect
Dong90
TaiyiForge 辅助 — 架构决策记录 ADR(长期影响决策的可追溯补充)。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-diagram-c4
Dong90
TaiyiForge 辅助 — 从代码反推 C4 架构文档(Observed/Inferred 分层 · Mermaid 真源)。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-diagram-flow
Dong90
TaiyiForge 辅助 — 业务流程图 / 状态机 / 序列图(Mermaid flowchart)。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9 - 0.706score
taiyi-diagram-pipeline
Dong90
TaiyiForge 辅助 — 架构图三步流水线编排(C4 真源 → 工程图同步 → PNG 渲染)。OpenCode / Claude / Codex / Cursor 通用。
SkillCFreshness: C★ 859Claude Code +9
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-requirement 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.
Cite this page
taiyi-requirement skill. Agent Mart. https://agentmart.dev/skills/dong90-taiyi-requirement (last updated 2026-10-24)