企业官网建设流程全解析

Story [NNN]: [title]

【免费下载链接】Claude-Code-Game-StudiosTurn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.项目地址: https://gitcode.com/GitHub_Trending/cl/Claude-Code-Game-Studios

Epic: [epic name]Status: ReadyLayer: [Foundation / Core / Feature / Presentation]Type: [Logic | Integration | Visual/Feel | UI | Config/Data]Manifest Version: [date from control-manifest.md header]

Context

GDD:design/gdd/[filename].mdRequirement:TR-[system]-NNN(Requirement text lives indocs/architecture/tr-registry.yaml— read fresh at review time)

ADR Governing Implementation: [ADR-NNNN: title]ADR Decision Summary: [1-2 sentence summary of what the ADR decided]

Engine: [name + version] |Risk: [LOW / MEDIUM / HIGH]Engine Notes: [from ADR Engine Compatibility section — post-cutoff APIs, verification required]

Control Manifest Rules (this layer):

• Required: [relevant required pattern]
• Forbidden: [relevant forbidden pattern]
• Guardrail: [relevant performance guardrail]

Acceptance Criteria

From GDDdesign/gdd/[filename].md, scoped to this story:

• [criterion 1 — directly from GDD]
• [criterion 2]
• [performance criterion if applicable]

Implementation Notes

Derived from ADR-NNNN Implementation Guidelines:

[Specific, actionable guidance from the ADR. Do not paraphrase in ways that change meaning. This is what the programmer reads instead of the ADR.]

Out of Scope

Handled by neighbouring stories — do not implement here:

• [Story NNN+1]: [what it handles]

QA Test Cases

Written by qa-lead at story creation. The developer implements against these — do not invent new test cases during implementation.

[For Logic / Integration stories — automated test specs]:

• AC-1: [criterion text]
  • Given: [precondition]
  • When: [action]
  • Then: [assertion]
  • Edge cases: [boundary values / failure states]

[For Visual/Feel / UI stories — manual verification steps]:

• AC-1: [criterion text]
  • Setup: [how to reach the state]
  • Verify: [what to look for]
  • Pass condition: [unambiguous pass description]

Test Evidence

Story Type: [type]Required evidence:

• Logic:tests/unit/[system]/[story-slug]_test.[ext]— must exist and pass
• Integration:tests/integration/[system]/[story-slug]_test.[ext]OR playtest doc
• Visual/Feel:production/qa/evidence/[story-slug]-evidence.md+ sign-off
• UI:production/qa/evidence/[story-slug]-evidence.mdor interaction test
• Config/Data: smoke check pass (production/qa/smoke-*.md)

Status: [ ] Not yet created

Dependencies

• Depends on: [Story NNN-1 must be DONE, or "None"]
• Unlocks: [Story NNN+1, or "None"]

### 8.1 模板设计要点解读 - **Info 区块（frontmatter 式引用块）**：携带 Epic、Layer、Type、Manifest Version 五个元字段。Manifest Version 直接取 control manifest 头部日期——这一字段在 `/story-readiness` 中会被比对，版本陈旧会导致 NEEDS WORK 判定（见 [story-readiness 测试规格](https://link.gitcode.com/i/2946fc72e69619337cfb0e74857de1d4) Case 4：`Manifest Version: 2026-01-15` 与当前 `2026-03-10` 不匹配即被标记 ADVISORY 问题）。 - **Context 区**：TR-ID 只写 ID 不写需求原文，评审时从注册表实时读取（保证永远引用最新需求文本）；Engine Notes 专门搬运 ADR Engine Compatibility 章节中的 post-cutoff APIs 与验证要求。 - **Implementation Notes**：直接摘自 ADR Implementation Guidelines，**禁止以改变原意的方式转述**——程序员读它时读到的就是 ADR 原文的精髓。 - **Out of Scope**：明确邻接故事负责的范围，防止边界蔓延。 - **Test Evidence**：按 Story 类型给出差异化的证据路径，`Status: [ ] Not yet created` 表示证据尚未产出，由 `/dev-story` 在实现阶段填充。 ### 8.2 同步更新 EPIC.md 写完全部 Story 文件后，需把 `production/epics/[epic-slug]/EPIC.md` 中 "Stories: Not yet created" 一行替换为填充好的表格： ```markdown ## Stories | # | Story | Type | Status | ADR | |---|-------|------|--------|-----| | 001 | [title] | Logic | Ready | ADR-NNNN | | 002 | [title] | Integration | Ready | ADR-MMMM |

九、写盘后的收尾与下一步交接（Step 7）

所有文件写入完成后，使用AskUserQuestion结合上下文给出下一步选项。检查逻辑：

• 检查production/epics/中是否还有其他没有 Story 的 Epic，并列出它们；
• 若当前是最后一个 Epic，则把/sprint-plan加入选项。

Widget 选项（按适用条件裁剪）：

• [A] Start implementing — run /story-readiness [first-story-path]（推荐）
• [B] Create stories for [next-epic-slug] — run /create-stories [slug]（仅当其他 Epic 尚无 Story 时）
• [C] Plan the sprint — run /sprint-plan（仅当所有 Epic 都有 Story 时）
• [D] Stop here for this session

输出需附注："Work through stories in order — each story'sDepends on:field tells you what must be DONE before you can start it."

写盘结束后（无论是否批准），输出最终裁决：

• Verdict: COMPLETE— [N] stories written toproduction/epics/[epic-slug]/. Run/story-readiness→/dev-storyto begin implementation.
• Verdict: BLOCKED— user declined. No story files written.

十、协作协议：六条纪律

本技能通过六条协作协议约束交互行为，防止越界：

1. Read before presenting— 静默加载全部输入后再展示故事清单；
2. Ask once— 整个 Epic 的故事一次性汇总呈现，不逐条询问；
3. Warn on blocked stories— 写入前标记任何带 Proposed ADR 的故事；
4. Ask before writing— 写文件前获得整批故事集的批准；
5. No invention— 验收标准来自 GDD、实现说明来自 ADR、规则来自控制清单，零虚构；
6. Never start implementation— 本技能止步于 Story 文件层，绝不进入实现。

第 5、6 条与lead-programmer的职责边界相互印证（lead-programmer 测试规格 明确其不拥有游戏设计决策权，也不直接写业务代码）；实际实现由/dev-story委派给专科 agent 完成，dev-story 测试规格 断言"Skill routes implementation to the correct specialist agent — it does not write source code directly"。

十一、行为契约的仓库级验证：五条测试用例

CCGS Skill Testing Framework/skills/pipeline/create-stories.md以 5 条用例把本技能的行为固化为可回归验证的契约，这既是该技能被"Skill Testing Framework"纳管的方式，也是理解其边界最直接的源码级证据：

Protocol Compliance 清单还额外验证了：所有上下文（EPIC、GDD、ADR、manifest、TR 注册表）在起草前加载完毕；故事草稿在"May I write"前完整展示；控制清单规则逐故事引用而非杜撰；以及以/story-readiness→/dev-story结束交接。

十二、在管线中的完整位置：一次端到端视角

把本技能放回 CCGS 全流程，其前后衔接一目了然：

/create-control-manifest （定义各 layer 的 Required/Forbidden/Guardrail 规则） ↓ /create-epics [system] （已批准 GDD → EPIC.md，按 layer 组织） ↓ /create-stories [epic-slug] ★ 本文主题：EPIC.md → 多个 story-NNN-*.md ↓ /story-readiness [story-path] （四维校验：Design / Architecture / Scope / DoD，产出 READY / NEEDS WORK / BLOCKED） ↓ /dev-story [story-path] （委派专科 agent 实现，验证验收标准，full 模式含 LP-CODE-REVIEW） ↓ /story-done （核对 TR 注册表最新需求文本与证据后关闭故事）

【免费下载链接】Claude-Code-Game-StudiosTurn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.项目地址: https://gitcode.com/GitHub_Trending/cl/Claude-Code-Game-Studios