visual-spec 0.1.10 → 0.1.11
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +1 -1
- package/docs/en-US/workflows.md +60 -6
- package/docs/ja-JP/workflows.md +57 -6
- package/docs/zh-CN/commands.md +1 -0
- package/docs/zh-CN/complicated.md +60 -0
- package/docs/zh-CN/getting-started.md +1 -0
- package/docs/zh-CN/structure.md +1 -1
- package/docs/zh-CN/workflows.md +60 -6
- package/package.json +2 -1
- package/skills/visual-spec/SKILL-ja-JP.md +11 -2
- package/skills/visual-spec/SKILL-zh-CN.md +36 -1
- package/skills/visual-spec/SKILL.md +36 -1
- package/skills/visual-spec/prompts/vspec_detail/index.html +923 -0
- package/skills/visual-spec/prompts/vspec_detail/index.md +66 -0
- package/skills/visual-spec/prompts/vspec_detail/job_logic.md +51 -0
- package/skills/visual-spec/prompts/vspec_detail/service_logic.md +55 -0
- package/skills/visual-spec/prompts/vspec_doc/doc.md +91 -0
- package/skills/visual-spec/prompts/vspec_more_q/question_and_answer.html +912 -0
- package/skills/visual-spec/prompts/vspec_new/question_and_answer.html +912 -0
- package/skills/visual-spec/prompts/vspec_upgrade/upgrade.md +4 -1
package/README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
This repo provides a requirements analysis and delivery assistant Skill. It offers a `/vspec:*` command-driven workflow that turns raw requirements into reviewable artifacts: specs, data models, runnable prototypes, detailed design, acceptance cases, tests, and integrated implementation inputs.
|
|
2
2
|
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.11 (2026-04-12)
|
|
4
4
|
|
|
5
5
|
## Installation
|
|
6
6
|
|
package/docs/en-US/workflows.md
CHANGED
|
@@ -5,8 +5,38 @@
|
|
|
5
5
|
- Provide the raw requirement input
|
|
6
6
|
- Answer open questions (key assumptions, scope, rules, dependencies)
|
|
7
7
|
- Get baseline artifacts under `/specs/`: roles, terms, flows, scenarios, function list, dependencies, questions
|
|
8
|
+
- Answer questions (HTML, recommended):
|
|
9
|
+
- `/vspec:new` generates an interactive Q&A page: `/specs/background/question_and_answer.html`
|
|
10
|
+
- Open the HTML, then pick:
|
|
11
|
+
- `/specs/background/original.md`
|
|
12
|
+
- `/specs/background/questions.md`
|
|
13
|
+
- Answer questions in the form UI and save back (if the browser supports File System Access API, it can overwrite; otherwise download and replace manually)
|
|
8
14
|
|
|
9
|
-
### 2.
|
|
15
|
+
### 2. More Questions (`/vspec:more-q`)
|
|
16
|
+
|
|
17
|
+
- Use when the question list is not enough or the requirement changed and you need more clarifications
|
|
18
|
+
- Input: `/specs/background/questions.md` (if missing, run `/vspec:new` first)
|
|
19
|
+
- Output: append new items to `/specs/background/questions.md` (new questions + how-to-answer)
|
|
20
|
+
- Answer questions (HTML, recommended):
|
|
21
|
+
- `/vspec:more-q` updates/generates the same Q&A page: `/specs/background/question_and_answer.html`
|
|
22
|
+
- Open the HTML, answer the newly appended questions, save back, then run `/vspec:refine-q`
|
|
23
|
+
|
|
24
|
+
### 3. Merge Answers (`/vspec:refine-q`)
|
|
25
|
+
|
|
26
|
+
- Use when the business has filled answers in `/specs/background/questions.md` and you want to merge them back into the canonical requirement
|
|
27
|
+
- Input: answered items in `/specs/background/questions.md` + `original.md`
|
|
28
|
+
- Output: append updates to `/specs/background/original.md` (adopted items + change log + latest wording)
|
|
29
|
+
|
|
30
|
+
### 4. Apply Refinements (`/vspec:refine`)
|
|
31
|
+
|
|
32
|
+
- Use when new information arrives during implementation and you need to update the canonical requirement and sync downstream artifacts
|
|
33
|
+
- Inputs:
|
|
34
|
+
- Default: `/docs/refine/*` (prefer `file_list.md`)
|
|
35
|
+
- Optional: files/directories passed as command arguments
|
|
36
|
+
- Prerequisite: `/specs/details/` must exist and be non-empty
|
|
37
|
+
- Outputs: append updates to `original.md` and update impacted `/specs/details/` and `/specs/prototypes/`
|
|
38
|
+
|
|
39
|
+
### 5. Detailed Specs (`/vspec:detail`)
|
|
10
40
|
|
|
11
41
|
- Using `/specs/functions/*` as input, generate per-function specs under `/specs/details/<function_slug>/`
|
|
12
42
|
- Goal: turn “requirements” into implementable design inputs:
|
|
@@ -14,8 +44,16 @@
|
|
|
14
44
|
- load/interaction/validation matrices
|
|
15
45
|
- post-submit checks/processing/navigation
|
|
16
46
|
- logging/notification matrices, MQ specs, import/export, cron jobs
|
|
47
|
+
- Extra output: `/specs/details/index.html` (left directory tree + right markdown-rendered reader; PlantUML rendered as diagrams)
|
|
48
|
+
|
|
49
|
+
### 6. Word Summary Doc (`/vspec:doc`)
|
|
17
50
|
|
|
18
|
-
|
|
51
|
+
- Use when you need a deliverable Word doc for review/circulation/archiving based on current artifacts
|
|
52
|
+
- Input: existing `/specs/**` artifacts (original/functions/details/models/flows, when available)
|
|
53
|
+
- Output: `/docs/current/requirement_detail.doc` (Word-openable `.doc`, single-file HTML)
|
|
54
|
+
- Note: this Word file is a read-only summary; make changes in the corresponding markdown files and rerun `/vspec:doc` to regenerate
|
|
55
|
+
|
|
56
|
+
### 7. Solution Verification (`/vspec:verify`)
|
|
19
57
|
|
|
20
58
|
- Prerequisite: `/specs/details/` exists and is non-empty
|
|
21
59
|
- Based on `/specs/` (functions + details + roles), generate:
|
|
@@ -31,29 +69,45 @@ Optional: segmented prototype generation
|
|
|
31
69
|
- `/vspec:proto-execute`: execution flow pages (including mobile `/m/*`)
|
|
32
70
|
- `/vspec:proto-crud`: config/master-data CRUD admin pages
|
|
33
71
|
|
|
34
|
-
###
|
|
72
|
+
### 8. Acceptance Cases (`/vspec:accept`)
|
|
35
73
|
|
|
36
74
|
- Generate acceptance cases into `/specs/acceptance/`
|
|
37
75
|
- Goal: define acceptance criteria and coverage (happy path, exceptions, boundaries, RBAC, data permissions)
|
|
38
76
|
|
|
39
|
-
###
|
|
77
|
+
### 9. Automated Tests (`/vspec:append-test`)
|
|
40
78
|
|
|
41
79
|
- Read acceptance cases and the repo’s existing test stack
|
|
42
80
|
- Generate a minimal runnable set of E2E/API/unit tests
|
|
43
81
|
- Note: this step only generates/adds test code to improve coverage; it does not run test commands (e.g. mvn test).
|
|
44
82
|
|
|
45
|
-
###
|
|
83
|
+
### 10. Integrated Implementation (`/vspec:impl`)
|
|
46
84
|
|
|
47
85
|
- Read specs, details, models, and dependencies
|
|
48
86
|
- Generate integrated backend + frontend code following repo conventions (API contract → backend implementation → frontend integration)
|
|
49
87
|
|
|
50
|
-
###
|
|
88
|
+
### 11. Quality Check (`/vspec:qc`)
|
|
89
|
+
|
|
90
|
+
- Run a quality check on artifacts under `/specs/`
|
|
91
|
+
- Output: `/specs/qc_report.md`
|
|
92
|
+
|
|
93
|
+
### 12. Planning (`/vspec:plan`)
|
|
51
94
|
|
|
52
95
|
- Split functions and scenarios into user stories, estimate effort, and build iteration schedules
|
|
53
96
|
- Outputs:
|
|
54
97
|
- `/specs/plan/plan_estimate.md`
|
|
55
98
|
- `/specs/plan/plan_schedule.html`
|
|
56
99
|
|
|
100
|
+
### 13. Upgrade / Retrofit (`/vspec:upgrade`)
|
|
101
|
+
|
|
102
|
+
- Use when you need to retrofit/upgrade based on materials under `/docs/` (legacy/current)
|
|
103
|
+
- Entry list: `/docs/current/file_list.md` (generated if missing)
|
|
104
|
+
- Output: generate/update `/specs/` following the `/vspec:new` structure and sync tech selections to `/scheme.yaml`
|
|
105
|
+
|
|
106
|
+
### 14. MRD Pack (`/vspec:mrd`)
|
|
107
|
+
|
|
108
|
+
- Generate market/competitor/user/product-design pack
|
|
109
|
+
- Output directory: `/docs/market/` (market/competitors/users/product_design)
|
|
110
|
+
|
|
57
111
|
## Installation (skills.sh)
|
|
58
112
|
|
|
59
113
|
```bash
|
package/docs/ja-JP/workflows.md
CHANGED
|
@@ -5,34 +5,85 @@
|
|
|
5
5
|
- 生の要件を入力
|
|
6
6
|
- 前提・範囲・ルール・依存関係などの確認質問に回答
|
|
7
7
|
- `/specs/` にベースライン成果物(roles/terms/flows/scenarios/functions/dependencies/questions)を生成
|
|
8
|
+
- 質問への回答(HTML、推奨):
|
|
9
|
+
- `/vspec:new` は対話式 Q&A ページを生成:`/specs/background/question_and_answer.html`
|
|
10
|
+
- HTML を開き、以下を選択:
|
|
11
|
+
- `/specs/background/original.md`
|
|
12
|
+
- `/specs/background/questions.md`
|
|
13
|
+
- フォームで回答し保存して md に反映(ブラウザが File System Access API に対応していれば直接上書き、未対応ならダウンロードして手動で置換)
|
|
14
|
+
|
|
15
|
+
### 2. 追加質問(`/vspec:more-q`)
|
|
16
|
+
|
|
17
|
+
- 質問が不足している、または要件が変わって追加確認が必要な場合に使う
|
|
18
|
+
- 入力:`/specs/background/questions.md`(無い場合は先に `/vspec:new`)
|
|
19
|
+
- 出力:`/specs/background/questions.md` に追記(追加質問 + 回答手順)
|
|
20
|
+
- 質問への回答(HTML、推奨):
|
|
21
|
+
- `/vspec:more-q` は同じ Q&A ページを更新/生成:`/specs/background/question_and_answer.html`
|
|
22
|
+
- HTML を開き、追加された質問に回答して保存し、最後に `/vspec:refine-q` を実行
|
|
23
|
+
|
|
24
|
+
### 3. 回答の取り込み(`/vspec:refine-q`)
|
|
25
|
+
|
|
26
|
+
- `questions.md` に記入した回答を要件口径へ取り込む
|
|
27
|
+
- 入力:回答済みの `/specs/background/questions.md` + `original.md`
|
|
28
|
+
- 出力:`/specs/background/original.md` へ追記(採用項目 + 変更点 + 最新口径)
|
|
29
|
+
|
|
30
|
+
### 4. 追補の適用(`/vspec:refine`)
|
|
31
|
+
|
|
32
|
+
- 実装中の追加情報/明確化を反映し、口径と下流成果物を同期する
|
|
33
|
+
- 入力:
|
|
34
|
+
- 既定:`/docs/refine/*`(`file_list.md` があれば優先)
|
|
35
|
+
- 任意:コマンド引数で指定したファイル/ディレクトリ
|
|
36
|
+
- 前提:`/specs/details/` が存在し空でない
|
|
37
|
+
- 出力:`original.md` へ追記 + 影響する `/specs/details/` と `/specs/prototypes/` を更新
|
|
8
38
|
|
|
9
|
-
###
|
|
39
|
+
### 5. 詳細 spec(`/vspec:detail`)
|
|
10
40
|
|
|
11
41
|
- `/specs/functions/*` を入力に、機能ごとの仕様を `/specs/details/<function_slug>/` に生成
|
|
12
42
|
- 目標:要件を実装可能な設計入力へ変換
|
|
43
|
+
- 追加出力:`/specs/details/index.html`(左にディレクトリツリー、右に Markdown レンダリング。PlantUML は図としてレンダリング)
|
|
44
|
+
|
|
45
|
+
### 6. Word 要約ドキュメント(`/vspec:doc`)
|
|
46
|
+
|
|
47
|
+
- 既存成果物を集約してレビュー/回覧/保管用の Word 文書を生成する
|
|
48
|
+
- 入力:既存の `/specs/**`(original/functions/details/models/flows など。存在するものを読む)
|
|
49
|
+
- 出力:`/docs/current/requirement_detail.doc`(Word で開ける `.doc`、単一 HTML)
|
|
50
|
+
- 注意:この Word は要約用(直接編集しない)。修正は対応する markdown を更新し、`/vspec:doc` を再実行して再生成する
|
|
13
51
|
|
|
14
|
-
###
|
|
52
|
+
### 7. 検証(`/vspec:verify`)
|
|
15
53
|
|
|
16
54
|
- 前提:`/specs/details/` が存在し空でない
|
|
17
55
|
- `/specs/models/*.md` と、`/scheme.yaml` の選択に従った実行可能プロトタイプを `/specs/prototypes/` に生成
|
|
18
56
|
|
|
19
|
-
###
|
|
57
|
+
### 8. 受入ケース(`/vspec:accept`)
|
|
20
58
|
|
|
21
59
|
- `/specs/acceptance/` に受入テストケースを生成
|
|
22
60
|
|
|
23
|
-
###
|
|
61
|
+
### 9. 自動テスト(`/vspec:append-test`)
|
|
24
62
|
|
|
25
63
|
- 受入ケースと既存テストスタックを読み、E2E/API/単体テストの最小セットを生成
|
|
26
64
|
- 注意:テスト実行は行わず、コード生成/追記のみ
|
|
27
65
|
|
|
28
|
-
###
|
|
66
|
+
### 10. 統合実装(`/vspec:impl`)
|
|
29
67
|
|
|
30
68
|
- specs/details/models/dependencies を読み、リポジトリの規約に沿った統合コードを生成
|
|
31
69
|
|
|
32
|
-
###
|
|
70
|
+
### 11. 品質チェック(`/vspec:qc`)
|
|
71
|
+
|
|
72
|
+
- `/specs/` 配下の成果物を品質チェックし、`/specs/qc_report.md` を生成
|
|
73
|
+
|
|
74
|
+
### 12. 見積・排期(`/vspec:plan`)
|
|
33
75
|
|
|
34
76
|
- 機能一覧とシナリオをもとに見積・排期(HTML)を生成
|
|
35
77
|
|
|
78
|
+
### 13. アップグレード/改修(`/vspec:upgrade`)
|
|
79
|
+
|
|
80
|
+
- `/docs/` 配下の資料(legacy/current)に基づき、`/vspec:new` と同様の構造で `/specs/` を再生成/更新
|
|
81
|
+
- 入口:`/docs/current/file_list.md`(無ければテンプレを生成)
|
|
82
|
+
|
|
83
|
+
### 14. MRD(`/vspec:mrd`)
|
|
84
|
+
|
|
85
|
+
- 市場/競合/ユーザー/プロダクト設計の分析パックを生成し、`/docs/market/` に書き出す
|
|
86
|
+
|
|
36
87
|
## インストール(skills.sh)
|
|
37
88
|
|
|
38
89
|
```bash
|
package/docs/zh-CN/commands.md
CHANGED
|
@@ -20,6 +20,7 @@
|
|
|
20
20
|
|
|
21
21
|
- 适用场景:刚拿到需求且信息不完整,需要快速形成“可评审的共同语言”
|
|
22
22
|
- 关键输出:干系人、角色、术语、流程、场景、功能清单、开放问题
|
|
23
|
+
- 原始材料归档:如果你有原始材料文件(PRD/需求文档/流程说明/字段口径/模板/协议/截图/样例数据等),统一放在 `/docs/current/`(便于后续 refine/upgrade/verify/impl 等命令按约定读取与引用)
|
|
23
24
|
- 目录初始化:创建 `/docs/` 及其子目录(legacy/current/refine/templates/texts/assets)用于输入归档与后续命令使用
|
|
24
25
|
- 提示:生成“开放问题/待确认问题”后,你可以把回答工作委托给 AI 先给出建议答案,你只需要逐条确认/修改即可(推荐做法:先让 AI 代答一版,再由业务确认口径)
|
|
25
26
|
|
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
# 复杂输入材料(Word/Excel 等)的归档与使用
|
|
2
|
+
|
|
3
|
+
当你的需求不是“一段文字”,而是多份原始材料(Word/Excel/PDF/流程图/截图/样例数据/协议等)时,建议把这些材料统一归档到 `/docs/`,并通过约定目录与清单文件让 Skill 能够稳定引用与复用。
|
|
4
|
+
|
|
5
|
+
## 1. `/docs/current/`:本次需求/迭代的原始材料
|
|
6
|
+
|
|
7
|
+
把“本次要分析的输入材料”放到 `/docs/current/`,并尽量保持结构清晰、可追溯、可复用。
|
|
8
|
+
|
|
9
|
+
推荐做法:
|
|
10
|
+
- 用子目录按来源/主题组织(可选):`/docs/current/prd/`、`/docs/current/rules/`、`/docs/current/ui/`、`/docs/current/data/`、`/docs/current/api/`
|
|
11
|
+
- 文件名建议包含:来源、主题、版本或日期,例如:
|
|
12
|
+
- `prd_v3_2026-04-12.docx`
|
|
13
|
+
- `field_mapping_v1.xlsx`
|
|
14
|
+
- `process_overview_v2.pdf`
|
|
15
|
+
- `ui_screenshots_2026-04-12/`(多张截图可用目录)
|
|
16
|
+
- 如果你有“材料入口清单”,放在:`/docs/current/file_list.md`
|
|
17
|
+
- `/vspec:upgrade` 会读取/生成该文件,并按清单顺序读取输入
|
|
18
|
+
- 即使 `/vspec:upgrade` 会扫描 `/docs/legacy/`,你仍然应该在 `file_list.md` 中把“你认为最重要/最权威”的材料排在前面
|
|
19
|
+
|
|
20
|
+
常见材料放置建议:
|
|
21
|
+
- Word/Doc/PRD:放 `prd/` 或根目录,强调“口径优先级”
|
|
22
|
+
- Excel(字段口径、枚举、映射表、权限矩阵、接口清单):放 `rules/` 或 `data/`
|
|
23
|
+
- PDF(历史说明/流程/合规材料):放 `prd/` 或 `rules/`
|
|
24
|
+
- 截图/原型/设计稿:放 `ui/` 或 `assets/`
|
|
25
|
+
- 样例数据(CSV/JSON):放 `data/`
|
|
26
|
+
|
|
27
|
+
## 2. `/docs/legacy/`:升级/重构场景的遗留系统材料
|
|
28
|
+
|
|
29
|
+
当你做的是“升级/重构/迁移”,遗留系统材料应该放在 `/docs/legacy/`(包含子目录)。例如:
|
|
30
|
+
- 旧系统功能说明、页面截图、交互说明
|
|
31
|
+
- 旧 RBAC/权限模型、数据权限口径
|
|
32
|
+
- 旧接口文档、事件/MQ 定义、对账规则
|
|
33
|
+
- 旧表结构/字段定义、枚举表、状态机
|
|
34
|
+
|
|
35
|
+
`/vspec:upgrade` 的用法要点:
|
|
36
|
+
- 会递归扫描 `/docs/legacy/` 及其子目录,把其中的文档当作原始输入资料
|
|
37
|
+
- 若发现 `/docs/current/file_list.md` 未覆盖的 legacy 文件,会先把它们追加进 `file_list.md`,再读取并参与抽取
|
|
38
|
+
- 你仍然可以通过 `/docs/current/file_list.md` 来“控制阅读顺序”和“强调哪些文件更权威”,避免被大量 legacy 资料淹没
|
|
39
|
+
|
|
40
|
+
## 3. `/docs/dependencies/`:外部依赖系统文档库
|
|
41
|
+
|
|
42
|
+
当你的需求依赖外部系统(例如 SSO/CRM/ERP/支付/消息/地图/库存等),建议把这些依赖系统的“稳定资料”沉淀到 `/docs/dependencies/`,作为长期复用的知识库。
|
|
43
|
+
|
|
44
|
+
推荐放入:
|
|
45
|
+
- 对方系统的接口说明、字段字典、错误码、鉴权方式
|
|
46
|
+
- 回调/事件/MQ 消息定义、签名校验、幂等规则
|
|
47
|
+
- 业务对账规则、结算口径、对接注意事项
|
|
48
|
+
- 版本更新记录与差异说明(如有)
|
|
49
|
+
|
|
50
|
+
与 `/docs/current/` 的区别:
|
|
51
|
+
- `/docs/current/`:本次迭代的输入(更可能频繁变动)
|
|
52
|
+
- `/docs/dependencies/`:依赖系统的“相对稳定资料”(用于多次迭代复用)
|
|
53
|
+
|
|
54
|
+
## 4. 推荐操作顺序(有多份材料时)
|
|
55
|
+
|
|
56
|
+
1. 把材料放入 `/docs/current/`(需要升级/重构则同时整理 `/docs/legacy/`)
|
|
57
|
+
2. 如材料较多:先整理 `/docs/current/file_list.md`(按“权威性/优先级”排序)
|
|
58
|
+
3. 运行 `/vspec:new`(生成 `/specs/background/original.md` 与问题清单)
|
|
59
|
+
4. 需要继承 legacy/当前材料并生成新 specs:运行 `/vspec:upgrade`
|
|
60
|
+
5. 需要汇总成 Word:运行 `/vspec:doc` 输出到 `/docs/current/requirement_detail.doc`
|
package/docs/zh-CN/structure.md
CHANGED
|
@@ -11,7 +11,7 @@ Skill 会按命令阶段逐步在 `/specs/` 下生成产物,并维护少量项
|
|
|
11
11
|
<your-project>/
|
|
12
12
|
├─ docs/ # 输入归档(/vspec:new 会创建)
|
|
13
13
|
│ ├─ legacy/ # 遗留系统材料(功能、权限、交互、API 等)
|
|
14
|
-
│ ├─ current/ #
|
|
14
|
+
│ ├─ current/ # 本次迭代新增/补充材料(也包括 /vspec:new 引用的原始材料文件:PRD/需求文档/流程说明/字段口径/模板/协议/截图/样例数据等)
|
|
15
15
|
│ │ └─ file_list.md # upgrade 入口清单(/vspec:upgrade 读取/生成)
|
|
16
16
|
│ ├─ dependencies/ # 外部依赖系统文档库(已有依赖系统说明,推荐)
|
|
17
17
|
│ ├─ refine/ # 补充/澄清输入(/vspec:refine 读取)
|
package/docs/zh-CN/workflows.md
CHANGED
|
@@ -5,8 +5,38 @@
|
|
|
5
5
|
- 输入原始需求
|
|
6
6
|
- 回答开放问题(关键假设、范围、规则、依赖)
|
|
7
7
|
- 在 `/specs/` 下得到第一版产物:角色、术语、流程、场景、功能清单、依赖、问题清单
|
|
8
|
+
- 提问回答(HTML 方式,推荐):
|
|
9
|
+
- `/vspec:new` 会生成交互式问答页:`/specs/background/question_and_answer.html`
|
|
10
|
+
- 打开该 HTML 后,分别选择:
|
|
11
|
+
- `/specs/background/original.md`
|
|
12
|
+
- `/specs/background/questions.md`
|
|
13
|
+
- 在页面里用表单回答问题并保存回写(浏览器支持写入时可直接覆盖写回;否则下载后手动替换)
|
|
8
14
|
|
|
9
|
-
### 2.
|
|
15
|
+
### 2. 补充问题(`/vspec:more-q`)
|
|
16
|
+
|
|
17
|
+
- 适用场景:问题清单还不够,或需求发生变更,需要补充更多“待确认问题”
|
|
18
|
+
- 输入:`/specs/background/questions.md`(不存在则先 `/vspec:new`)
|
|
19
|
+
- 输出:追加写入 `/specs/background/questions.md`(新增问题 + 回答指引)
|
|
20
|
+
- 提问回答(HTML 方式,推荐):
|
|
21
|
+
- `/vspec:more-q` 会更新/生成交互式问答页:`/specs/background/question_and_answer.html`
|
|
22
|
+
- 打开该 HTML,用表单继续回答新增问题,保存回写后再执行 `/vspec:refine-q`
|
|
23
|
+
|
|
24
|
+
### 3. 合并问答(`/vspec:refine-q`)
|
|
25
|
+
|
|
26
|
+
- 适用场景:业务已在 `/specs/background/questions.md` 填写答案,需要合并回需求并形成新口径
|
|
27
|
+
- 输入:`/specs/background/questions.md`(已回答项)+ `original.md`
|
|
28
|
+
- 输出:追加更新到 `/specs/background/original.md`(采纳项 + 变更清单 + 最新口径)
|
|
29
|
+
|
|
30
|
+
### 4. 应用补充材料(`/vspec:refine`)
|
|
31
|
+
|
|
32
|
+
- 适用场景:实现中出现新信息/澄清,需要更新需求口径并同步更新详情与原型,且保留可追溯性
|
|
33
|
+
- 输入:
|
|
34
|
+
- 默认:`/docs/refine/*`(优先 `file_list.md`)
|
|
35
|
+
- 可选:命令参数指定文件/目录
|
|
36
|
+
- 前置条件:`/specs/details/` 必须存在且非空
|
|
37
|
+
- 输出:追加更新到 `original.md` + 更新受影响的 `/specs/details/` 与 `/specs/prototypes/`
|
|
38
|
+
|
|
39
|
+
### 5. 详细规格(`/vspec:detail`)
|
|
10
40
|
|
|
11
41
|
- 以 `/specs/functions/*` 为输入,在 `/specs/details/<function_slug>/` 下生成单功能规格
|
|
12
42
|
- 目标:把“需求”转成可实现的设计输入:
|
|
@@ -14,8 +44,16 @@
|
|
|
14
44
|
- 加载/交互/校验矩阵
|
|
15
45
|
- 提交后检查/处理/跳转
|
|
16
46
|
- 日志/通知矩阵、MQ、导入导出、定时任务
|
|
47
|
+
- 额外输出:`/specs/details/index.html`(左侧目录树 + 右侧 Markdown 渲染阅读;PlantUML 渲染为图)
|
|
48
|
+
|
|
49
|
+
### 6. Word 汇总文档(`/vspec:doc`)
|
|
17
50
|
|
|
18
|
-
|
|
51
|
+
- 适用场景:把当前已有的规格产物汇总成可交付的 Word 文档,用于评审/流转/归档
|
|
52
|
+
- 输入:现有 `/specs/**` 产物(original/functions/details/models/flows 等,存在则读取)
|
|
53
|
+
- 输出:`/docs/current/requirement_detail.doc`(Word 可打开的 `.doc`,HTML 单文件)
|
|
54
|
+
- 提示:该 Word 只是汇总,不建议直接修改;修改应回到对应的 markdown 文件,修改后重新 `/vspec:doc` 生成新版本
|
|
55
|
+
|
|
56
|
+
### 7. 方案验证(`/vspec:verify`)
|
|
19
57
|
|
|
20
58
|
- 前置条件:`/specs/details/` 存在且非空
|
|
21
59
|
- 基于 `/specs/`(functions + details + roles)生成:
|
|
@@ -31,29 +69,45 @@
|
|
|
31
69
|
- `/vspec:proto-execute`:执行流页面(包含移动端 `/m/*`)
|
|
32
70
|
- `/vspec:proto-crud`:配置/主数据 CRUD 管理页
|
|
33
71
|
|
|
34
|
-
###
|
|
72
|
+
### 8. 验收用例(`/vspec:accept`)
|
|
35
73
|
|
|
36
74
|
- 在 `/specs/acceptance/` 下生成验收用例
|
|
37
75
|
- 目标:定义验收口径与覆盖范围(主流程、异常、边界、RBAC、数据权限)
|
|
38
76
|
|
|
39
|
-
###
|
|
77
|
+
### 9. 自动化测试(`/vspec:append-test`)
|
|
40
78
|
|
|
41
79
|
- 读取验收用例与仓库现有测试技术栈
|
|
42
80
|
- 生成最小可运行的一组 E2E/API/单测
|
|
43
81
|
- Note:该步骤只生成/补齐测试代码以提升覆盖率,不负责执行测试命令(例如 mvn test)。
|
|
44
82
|
|
|
45
|
-
###
|
|
83
|
+
### 10. 集成实现(`/vspec:impl`)
|
|
46
84
|
|
|
47
85
|
- 读取 specs、details、models、dependencies
|
|
48
86
|
- 按仓库约定生成后端 + 前端联调代码(API 合同 → 后端实现 → 前端对接)
|
|
49
87
|
|
|
50
|
-
###
|
|
88
|
+
### 11. 质量检查(`/vspec:qc`)
|
|
89
|
+
|
|
90
|
+
- 对 `/specs/` 下产物做质量检查
|
|
91
|
+
- 输出:`/specs/qc_report.md`
|
|
92
|
+
|
|
93
|
+
### 12. 估算与排期(`/vspec:plan`)
|
|
51
94
|
|
|
52
95
|
- 把功能与场景拆成用户故事,估算工作量,并生成迭代排期
|
|
53
96
|
- 输出:
|
|
54
97
|
- `/specs/plan/plan_estimate.md`
|
|
55
98
|
- `/specs/plan/plan_schedule.html`
|
|
56
99
|
|
|
100
|
+
### 13. 升级/改造(`/vspec:upgrade`)
|
|
101
|
+
|
|
102
|
+
- 适用场景:基于遗留系统材料做“升级/重构/迁移”分析,继承必要部分并生成新规格
|
|
103
|
+
- 入口清单:`/docs/current/file_list.md`(缺失时生成模板)
|
|
104
|
+
- 输出:生成/更新 `/specs/`(沿用 `/vspec:new` 结构)+ 同步技术选型到 `/scheme.yaml`
|
|
105
|
+
|
|
106
|
+
### 14. MRD 分析包(`/vspec:mrd`)
|
|
107
|
+
|
|
108
|
+
- 输出市场/竞品/用户/产品设计分析包
|
|
109
|
+
- 输出目录:`/docs/market/`(market/competitors/users/product_design)
|
|
110
|
+
|
|
57
111
|
## 独立使用质量规范(不依赖 `/vspec:qc`)
|
|
58
112
|
|
|
59
113
|
内置质检标准文件位于(任选其一,取你当前环境中存在的路径):
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "visual-spec",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.11",
|
|
4
4
|
"description": "AI skill: visual-spec (/vspec:* commands) for requirement analysis, prototyping, detailing, testing, and planning.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"type": "commonjs",
|
|
@@ -23,6 +23,7 @@
|
|
|
23
23
|
"skills/visual-spec/prompts/vspec_new/",
|
|
24
24
|
"skills/visual-spec/prompts/vspec_more_q/",
|
|
25
25
|
"skills/visual-spec/prompts/vspec_mrd/",
|
|
26
|
+
"skills/visual-spec/prompts/vspec_doc/",
|
|
26
27
|
"skills/visual-spec/prompts/vspec_plan/",
|
|
27
28
|
"skills/visual-spec/prompts/vspec_qc/",
|
|
28
29
|
"skills/visual-spec/prompts/vspec_refine/",
|
|
@@ -83,7 +83,11 @@ Flow:
|
|
|
83
83
|
|
|
84
84
|
### `/vspec:detail`
|
|
85
85
|
|
|
86
|
-
機能一覧に基づき要件詳細を展開します(`/specs/details/`
|
|
86
|
+
機能一覧に基づき要件詳細を展開します(`/specs/details/` に生成)。各ステップの種別(端=Web/Mobile/Web+Mobile/Backend/Job)を判定し、対応するロジック詳細を必ず生成します(ロジックを省略しない)。あわせて、Markdown/PlantUML をレンダリングできる閲覧用 `index.html` を `/specs/details/index.html` に生成します。
|
|
87
|
+
|
|
88
|
+
### `/vspec:doc`
|
|
89
|
+
|
|
90
|
+
要件成果物(`/specs/**`)を集約し、Word で直接開ける単一ファイルの Word 文書(HTML 形式の `.doc`)を `/docs/current/requirement_detail.doc` に生成します。
|
|
87
91
|
|
|
88
92
|
### `/vspec:verify`
|
|
89
93
|
|
|
@@ -107,7 +111,7 @@ Flow:
|
|
|
107
111
|
|
|
108
112
|
### `/vspec:upgrade`
|
|
109
113
|
|
|
110
|
-
`/docs/` 配下の資料(legacy/current)に基づき、`/vspec:new` と同様の構造で `/specs/`
|
|
114
|
+
`/docs/` 配下の資料(legacy/current)に基づき、`/vspec:new` と同様の構造で `/specs/` を再生成/更新します。あわせて、`/docs/legacy/` 配下(サブディレクトリ含む)を再帰的にスキャンし、原資料として取り込みます。
|
|
111
115
|
|
|
112
116
|
### `/vspec:plan`
|
|
113
117
|
|
|
@@ -137,6 +141,7 @@ MRD(市場/競合/ユーザー/プロダクト設計)分析パックを生
|
|
|
137
141
|
- `prompts/vspec_mrd/mrd.md`
|
|
138
142
|
- `prompts/vspec_refine/refine.md`
|
|
139
143
|
- `prompts/vspec_refine/refine_q.md`
|
|
144
|
+
- `prompts/vspec_doc/doc.md`
|
|
140
145
|
- `prompts/vspec_verify/model.md`
|
|
141
146
|
- `prompts/vspec_verify/prototype.md`
|
|
142
147
|
- `prompts/vspec_verify/validation.md`
|
|
@@ -144,6 +149,8 @@ MRD(市場/競合/ユーザー/プロダクト設計)分析パックを生
|
|
|
144
149
|
- `prompts/vspec_detail/data_permission.md`
|
|
145
150
|
- `prompts/vspec_detail/page_load.md`
|
|
146
151
|
- `prompts/vspec_detail/interaction.md`
|
|
152
|
+
- `prompts/vspec_detail/index.md`
|
|
153
|
+
- `prompts/vspec_detail/index.html`
|
|
147
154
|
- `prompts/vspec_detail/timeline.md`
|
|
148
155
|
- `prompts/vspec_detail/formula.md`
|
|
149
156
|
- `prompts/vspec_detail/expression_tree.md`
|
|
@@ -154,6 +161,8 @@ MRD(市場/競合/ユーザー/プロダクト設計)分析パックを生
|
|
|
154
161
|
- `prompts/vspec_detail/post_submit_processing.md`
|
|
155
162
|
- `prompts/vspec_detail/post_submit_navigation.md`
|
|
156
163
|
- `prompts/vspec_detail/mq.md`
|
|
164
|
+
- `prompts/vspec_detail/service_logic.md`
|
|
165
|
+
- `prompts/vspec_detail/job_logic.md`
|
|
157
166
|
- `prompts/vspec_detail/logging_matrix.md`
|
|
158
167
|
- `prompts/vspec_detail/notification_matrix.md`
|
|
159
168
|
- `prompts/vspec_detail/nfp.md`
|
|
@@ -118,6 +118,10 @@ description: "将原始需求分析为可评审的视觉规格,并生成相关
|
|
|
118
118
|
2. 尽可能读取可用的上下文产物:`/specs/background/*`、`/specs/flows/*.puml`、`/specs/background/scenario_details/`、`/specs/background/roles.md`,以及已有的 `/specs/models/*.md`(若存在)。
|
|
119
119
|
3. 对每个功能(页面或非页面任务),先判断哪些详情产物真正涉及,再只生成涉及的部分;对不涉及的部分不得生成空文档。
|
|
120
120
|
- 覆盖性要求(必须):对遍历到的每个功能点,必须至少产出 `rbac.md` 与 `data_permission.md`(按规则写入对应路径);若因信息不足无法产出,必须输出可见错误并停止,而不是静默跳过。
|
|
121
|
+
- Step 类型要求(必须):你必须从功能行的“说明”中解析 step 的类型(端=Web/Mobile/Web+Mobile/Backend/Job),并生成对应的逻辑细节文档;不得跳过逻辑部分:
|
|
122
|
+
- 对 `端=Web` / `端=Mobile` / `端=Web+Mobile`:必须生成 `page_load.md` 与 `interaction.md`(页面加载 + 交互逻辑是必需的)。
|
|
123
|
+
- 对 `端=Backend`:必须生成 `service_logic.md`(服务端逻辑:输入输出、规则、状态、接口/事件、错误与幂等/一致性)。
|
|
124
|
+
- 对 `端=Job`:必须生成 `job_logic.md`(作业逻辑:触发/频率、数据范围、重试/补偿、可观测性、失败处理)。
|
|
121
125
|
- 始终生成基础文档:
|
|
122
126
|
- `rbac.md`:RBAC 权限下沉到页面区域与控件级。
|
|
123
127
|
- `data_permission.md`:数据权限规则与范围。
|
|
@@ -149,6 +153,32 @@ description: "将原始需求分析为可评审的视觉规格,并生成相关
|
|
|
149
153
|
4. 仅写入生成的(涉及的)详情文档:
|
|
150
154
|
- 单功能:`/specs/details/<module_slug>/<logic_type>/<function_slug>.(md|html)`
|
|
151
155
|
- 模块级:`/specs/details/<module_slug>/<logic_type>/<module_slug>.(md|html)`
|
|
156
|
+
5. 加载 `prompts/vspec_detail/index.md` 生成单页阅读入口:`/specs/details/index.html`
|
|
157
|
+
- 左侧:按 `/specs/details/` 目录结构生成目录树
|
|
158
|
+
- 右侧:以 Markdown 渲染方式阅读详情内容
|
|
159
|
+
- 遇到 PlantUML 必须渲染成图(不得展示源码文本)
|
|
160
|
+
|
|
161
|
+
### `/vspec:doc`
|
|
162
|
+
|
|
163
|
+
用于生成“需求详细文档”的 Word 文件(Word 可打开的单文件 `.doc`,HTML 格式),并写入到 `/docs/current/` 目录下。
|
|
164
|
+
|
|
165
|
+
语言:
|
|
166
|
+
- 读取 `/scheme.yaml` 的 `selected.language`(支持 `en`、`zh`、`ja`;若缺失/非法则按 `en` 处理;`zh-CN` 视为 `zh` 的别名)。
|
|
167
|
+
- 生成的 Word 文档必须统一使用所选语言(标题、章节名、字段名、表头与说明文字)。
|
|
168
|
+
|
|
169
|
+
流程:
|
|
170
|
+
1. 确保 `/docs/current/` 存在。
|
|
171
|
+
2. 尽可能读取已有产物作为输入:
|
|
172
|
+
- 需求口径:`/specs/background/original.md`
|
|
173
|
+
- 功能清单:`/specs/functions/*`
|
|
174
|
+
- 需求详情:`/specs/details/**`
|
|
175
|
+
- 角色与权限:`/specs/background/roles.md`、`/specs/details/**/rbac.md`
|
|
176
|
+
- 数据权限:`/specs/details/**/data_permission.md`
|
|
177
|
+
- 场景与流程:`/specs/background/scenarios.md`、`/specs/background/scenario_details/**`、`/specs/flows/*.puml`
|
|
178
|
+
- 外部依赖:`/specs/background/dependencies.md`
|
|
179
|
+
- 数据模型:`/specs/models/*.md`
|
|
180
|
+
3. 加载 `prompts/vspec_doc/doc.md`,生成 Word 可打开的单文件 HTML 文档。
|
|
181
|
+
4. 将输出写入:`/docs/current/requirement_detail.doc`。
|
|
152
182
|
|
|
153
183
|
### `/vspec:verify`
|
|
154
184
|
|
|
@@ -242,7 +272,7 @@ Note:Pro 版支持更广泛的质量检测能力(例如更完整的原型/
|
|
|
242
272
|
|
|
243
273
|
流程:
|
|
244
274
|
1. 确保 `/docs/current/file_list.md` 入口文件存在;若缺失则按模板生成。
|
|
245
|
-
2. 读取 `/docs/current/file_list.md`,再按顺序读取 `/docs/` 下列出的输入(通常 `/docs/legacy/*`、`/docs/current/*`,可选 `/docs/templates/*`、`/docs/texts/*`、`/docs/assets/*`)并抽取结构化信息(功能、依赖、UI
|
|
275
|
+
2. 读取 `/docs/current/file_list.md`,再按顺序读取 `/docs/` 下列出的输入(通常 `/docs/legacy/*`、`/docs/current/*`,可选 `/docs/templates/*`、`/docs/texts/*`、`/docs/assets/*`)并抽取结构化信息(功能、依赖、UI 风格、角色/权限、技术规格)。另外,必须递归扫描 `/docs/legacy/` 及其子目录下的文档,作为原始输入资料(即使尚未被 `file_list.md` 显式列出);当发现 `file_list.md` 未覆盖的 legacy 文件时,先把它们追加写入 `/docs/current/file_list.md`,再读取并参与抽取。
|
|
246
276
|
3. 若 `/specs/background/original.md` 已存在,则将其视为当前需求口径并作为 diff 基线(继承/新增/变更/废弃)。
|
|
247
277
|
4. 加载 `prompts/vspec_upgrade/upgrade.md`,按 `/vspec:new` 产物约定生成/更新 `/specs/`。
|
|
248
278
|
5. 将抽取到的技术规格同步到 `/scheme.yaml`,供 `/vspec:verify` 与 `/vspec:impl` 使用。
|
|
@@ -294,6 +324,7 @@ Note:Pro 版支持更广泛的质量检测能力(例如更完整的原型/
|
|
|
294
324
|
- `prompts/vspec_new/questions.md`:生成 `/specs/background/questions.md` 的提示词。
|
|
295
325
|
- `prompts/vspec_refine/refine.md`:`/vspec:refine` 使用的提示词。
|
|
296
326
|
- `prompts/vspec_refine/refine_q.md`:`/vspec:refine-q` 使用的提示词。
|
|
327
|
+
- `prompts/vspec_doc/doc.md`:`/vspec:doc` 使用的提示词,用于生成 Word 可打开的 `.doc`(HTML)需求详细文档到 `/docs/current/`。
|
|
297
328
|
- `prompts/vspec_verify/model.md`:生成 `/specs/models/*.md` 的提示词。
|
|
298
329
|
- `prompts/vspec_verify/prototype.md`:生成按选栈的可运行原型工程(`/specs/prototypes/`)的提示词(必须遵循 `scheme.yaml`)。
|
|
299
330
|
- `prompts/vspec_verify/validation.md`:生成 `scenario.html` 场景评审页的提示词。
|
|
@@ -301,6 +332,8 @@ Note:Pro 版支持更广泛的质量检测能力(例如更完整的原型/
|
|
|
301
332
|
- `prompts/vspec_detail/data_permission.md`:生成数据权限详情的提示词。
|
|
302
333
|
- `prompts/vspec_detail/page_load.md`:生成页面加载逻辑的提示词。
|
|
303
334
|
- `prompts/vspec_detail/interaction.md`:生成页面交互逻辑的提示词。
|
|
335
|
+
- `prompts/vspec_detail/index.md`:生成 `/specs/details/index.html` 单页阅读入口(Markdown/PlantUML 渲染)的提示词。
|
|
336
|
+
- `prompts/vspec_detail/index.html`:`/specs/details/index.html` 的固定 HTML 模板(用于稳定生成:目录树 + Markdown 渲染)。
|
|
304
337
|
- `prompts/vspec_detail/timeline.md`:生成时间轴 HTML 的提示词。
|
|
305
338
|
- `prompts/vspec_detail/formula.md`:生成公式说明的提示词。
|
|
306
339
|
- `prompts/vspec_detail/expression_tree.md`:生成表达式树 HTML 的提示词。
|
|
@@ -311,6 +344,8 @@ Note:Pro 版支持更广泛的质量检测能力(例如更完整的原型/
|
|
|
311
344
|
- `prompts/vspec_detail/post_submit_processing.md`:生成提交后处理的提示词。
|
|
312
345
|
- `prompts/vspec_detail/post_submit_navigation.md`:生成提交后跳转规则的提示词。
|
|
313
346
|
- `prompts/vspec_detail/mq.md`:生成 MQ 设计的提示词。
|
|
347
|
+
- `prompts/vspec_detail/service_logic.md`:生成 `端=Backend` 功能点的服务端逻辑细节(service logic)的提示词。
|
|
348
|
+
- `prompts/vspec_detail/job_logic.md`:生成 `端=Job` 功能点的作业逻辑细节(job logic)的提示词。
|
|
314
349
|
- `prompts/vspec_detail/logging_matrix.md`:生成日志矩阵的提示词。
|
|
315
350
|
- `prompts/vspec_detail/notification_matrix.md`:生成通知矩阵的提示词。
|
|
316
351
|
- `prompts/vspec_detail/nfp.md`:生成非功能需求的提示词。
|
|
@@ -125,6 +125,10 @@ Flow:
|
|
|
125
125
|
2. Read supporting artifacts when available: `/specs/background/*`, `/specs/flows/*.puml`, `/specs/background/scenario_details/`, `/specs/background/roles.md`, and existing `/specs/models/*.md` (if any).
|
|
126
126
|
3. For each function (page or non-page job), first determine which detail artifacts are actually involved, then only generate those artifacts; do not generate documents for non-involved parts.
|
|
127
127
|
- Coverage requirement: for every function row you iterate, you must generate at least `rbac.md` and `data_permission.md`. If you cannot, output an explicit error and stop (do not silently skip).
|
|
128
|
+
- Step type requirement: you must determine the step type from the function row (e.g. terminal type / page vs backend vs job), and generate the corresponding logic artifacts; do not skip logic:
|
|
129
|
+
- For `Web` / `Mobile` / `Web+Mobile` steps: always generate `page_load.md` and `interaction.md`.
|
|
130
|
+
- For `Backend` steps: always generate `service_logic.md` (service logic: inputs/outputs, rules, states, APIs/events, errors, idempotency).
|
|
131
|
+
- For `Job` steps: always generate `job_logic.md` (job logic: trigger/schedule, data scope, retries/compensation, observability, failure handling).
|
|
128
132
|
- Always generate the baseline docs:
|
|
129
133
|
- `rbac.md`: RBAC permissions down to page areas and controls.
|
|
130
134
|
- `data_permission.md`: data permission rules and scope.
|
|
@@ -156,6 +160,32 @@ Flow:
|
|
|
156
160
|
4. Write only the generated (involved) detail documents:
|
|
157
161
|
- Per-function: `/specs/details/<module_slug>/<logic_type>/<function_slug>.(md|html)`
|
|
158
162
|
- Module-level: `/specs/details/<module_slug>/<logic_type>/<module_slug>.(md|html)`
|
|
163
|
+
5. Load `prompts/vspec_detail/index.md` to generate a single-page viewer `/specs/details/index.html`:
|
|
164
|
+
- Left: directory tree based on `/specs/details/`
|
|
165
|
+
- Right: markdown-rendered reading pane
|
|
166
|
+
- Render PlantUML diagrams (do not show raw PlantUML text)
|
|
167
|
+
|
|
168
|
+
### `/vspec:doc`
|
|
169
|
+
|
|
170
|
+
Use this command to generate a Word document (Word-openable single-file `.doc` in HTML format) that aggregates the requirement detail artifacts into a deliverable doc, and write it under `/docs/current/`.
|
|
171
|
+
|
|
172
|
+
Language:
|
|
173
|
+
- Read `/scheme.yaml` `selected.language` (supports `en`, `zh`, `ja`; default to `en` if missing/invalid).
|
|
174
|
+
- The generated Word document must use the selected language consistently (titles, headings, field labels, table headers).
|
|
175
|
+
|
|
176
|
+
Flow:
|
|
177
|
+
1. Ensure `/docs/current/` exists.
|
|
178
|
+
2. Read the existing artifacts when available:
|
|
179
|
+
- Canonical requirement: `/specs/background/original.md`
|
|
180
|
+
- Function list: `/specs/functions/*`
|
|
181
|
+
- Detail specs: `/specs/details/**`
|
|
182
|
+
- Roles & permissions: `/specs/background/roles.md`, `/specs/details/**/rbac.md`
|
|
183
|
+
- Data permission: `/specs/details/**/data_permission.md`
|
|
184
|
+
- Scenarios & flows: `/specs/background/scenarios.md`, `/specs/background/scenario_details/**`, `/specs/flows/*.puml`
|
|
185
|
+
- Dependencies: `/specs/background/dependencies.md`
|
|
186
|
+
- Models: `/specs/models/*.md`
|
|
187
|
+
3. Load `prompts/vspec_doc/doc.md` and generate the doc as a Word-openable single HTML file.
|
|
188
|
+
4. Write the output file to: `/docs/current/requirement_detail.doc`.
|
|
159
189
|
|
|
160
190
|
### `/vspec:verify`
|
|
161
191
|
|
|
@@ -249,7 +279,7 @@ Language:
|
|
|
249
279
|
|
|
250
280
|
Flow:
|
|
251
281
|
1. Ensure the input entry file exists at `/docs/current/file_list.md`; if missing, generate it with the expected input list template.
|
|
252
|
-
2. Read `/docs/current/file_list.md`, then read the listed sources under `/docs/` (typically `/docs/legacy/*`, `/docs/current/*`, optionally `/docs/templates/*`, `/docs/texts/*`, `/docs/assets/*`) in order and extract structured information (functions, dependencies, UI style, roles/permissions, technical spec).
|
|
282
|
+
2. Read `/docs/current/file_list.md`, then read the listed sources under `/docs/` (typically `/docs/legacy/*`, `/docs/current/*`, optionally `/docs/templates/*`, `/docs/texts/*`, `/docs/assets/*`) in order and extract structured information (functions, dependencies, UI style, roles/permissions, technical spec). Additionally, you must recursively scan `/docs/legacy/` and all its subdirectories and treat those documents as raw input materials (even if they are not explicitly listed yet); when you find legacy files not in `file_list.md`, append them into `/docs/current/file_list.md` and then read them.
|
|
253
283
|
3. If `/specs/background/original.md` exists, treat it as the current canonical requirement and use it as baseline for diff (inherit/new/change/deprecate).
|
|
254
284
|
4. Load `prompts/vspec_upgrade/upgrade.md` and generate/update artifacts under `/specs/`, reusing `/vspec:new` output conventions.
|
|
255
285
|
5. Sync extracted technical spec into `/scheme.yaml` so it can be used by `/vspec:verify` and `/vspec:impl`.
|
|
@@ -303,6 +333,7 @@ Flow:
|
|
|
303
333
|
- `prompts/vspec_mrd/mrd.md`: the prompt used by `/vspec:mrd` to generate market/user/competitor/product docs under `/docs/market/`.
|
|
304
334
|
- `prompts/vspec_refine/refine.md`: the prompt used by `/vspec:refine` to refine the requirement based on `refine.md`.
|
|
305
335
|
- `prompts/vspec_refine/refine_q.md`: the prompt used by `/vspec:refine-q` to refine the requirement based on answered questions.
|
|
336
|
+
- `prompts/vspec_doc/doc.md`: the prompt used by `/vspec:doc` to generate a Word-openable `.doc` (HTML) requirement detail document under `/docs/current/`.
|
|
306
337
|
- `prompts/vspec_verify/model.md`: the prompt used by `/vspec:verify` to generate `/specs/models/*.md`.
|
|
307
338
|
- `prompts/vspec_verify/prototype.md`: the prompt used by `/vspec:verify` to generate the stack-selected runnable prototype under `/specs/prototypes/` (must follow `scheme.yaml`).
|
|
308
339
|
- `prompts/vspec_verify/validation.md`: the prompt used by `/vspec:verify` to generate the validation web page with a `scenario.html` entry.
|
|
@@ -310,6 +341,8 @@ Flow:
|
|
|
310
341
|
- `prompts/vspec_detail/data_permission.md`: the prompt used by `/vspec:detail` to generate data permission detail docs.
|
|
311
342
|
- `prompts/vspec_detail/page_load.md`: the prompt used by `/vspec:detail` to generate page loading logic docs.
|
|
312
343
|
- `prompts/vspec_detail/interaction.md`: the prompt used by `/vspec:detail` to generate page interaction logic docs.
|
|
344
|
+
- `prompts/vspec_detail/index.md`: the prompt used by `/vspec:detail` to generate `/specs/details/index.html` as a markdown/PlantUML-rendered viewer.
|
|
345
|
+
- `prompts/vspec_detail/index.html`: the fixed HTML template used by `/vspec:detail` to stabilize `/specs/details/index.html` generation (directory tree + markdown renderer).
|
|
313
346
|
- `prompts/vspec_detail/timeline.md`: the prompt used by `/vspec:detail` to generate time-axis HTML docs.
|
|
314
347
|
- `prompts/vspec_detail/formula.md`: the prompt used by `/vspec:detail` to generate formula docs.
|
|
315
348
|
- `prompts/vspec_detail/expression_tree.md`: the prompt used by `/vspec:detail` to generate expression tree docs.
|
|
@@ -320,6 +353,8 @@ Flow:
|
|
|
320
353
|
- `prompts/vspec_detail/post_submit_processing.md`: the prompt used by `/vspec:detail` to generate post-submit processing docs.
|
|
321
354
|
- `prompts/vspec_detail/post_submit_navigation.md`: the prompt used by `/vspec:detail` to generate post-submit navigation docs.
|
|
322
355
|
- `prompts/vspec_detail/mq.md`: the prompt used by `/vspec:detail` to generate MQ message design docs.
|
|
356
|
+
- `prompts/vspec_detail/service_logic.md`: the prompt used by `/vspec:detail` to generate backend service logic docs for `Backend` steps.
|
|
357
|
+
- `prompts/vspec_detail/job_logic.md`: the prompt used by `/vspec:detail` to generate job logic docs for `Job` steps.
|
|
323
358
|
- `prompts/vspec_detail/logging_matrix.md`: the prompt used by `/vspec:detail` to generate logging matrix docs.
|
|
324
359
|
- `prompts/vspec_detail/notification_matrix.md`: the prompt used by `/vspec:detail` to generate notification matrix docs.
|
|
325
360
|
- `prompts/vspec_detail/nfp.md`: the prompt used by `/vspec:detail` to generate non-functional requirements docs.
|