visual-spec

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Visual Spec Skill

Visual Spec技能

Analyzes visual specifications based on user input and turns brief business requests into structured requirement output.

基于用户输入分析视觉规格，将简短的业务需求转换为结构化的需求输出。

When to Use

适用场景

Invoke this skill when:

Business side provided a very simple described requirements.
User runs
```
/vspec:new
```
to start a new requirement analysis flow.

在以下场景调用此技能：

业务方提供的需求描述非常简洁。
用户运行
```
/vspec:new
```
以启动新的需求分析流程。

What This Skill Defines

此技能的核心功能

Fill in details based on scenario-based-facilitation method.
Design the data models.
Generate UI mockups based on the details filled in.
Generate business logic details in visual formats.

基于场景引导法补充需求细节。
设计数据模型。
根据补充的细节生成UI原型图。
以可视化格式生成业务逻辑细节。

Commands

命令说明

/vspec:new

/vspec:new

Use this command to create a new requirement analysis session.

Language:

Read
```
/scheme.yaml
```
```
selected.language
```
(supports
```
en
```
,
```
zh
```
,
```
ja
```
; default to
```
en
```
if missing/invalid).
If the command argument or input explicitly provides
```
lang=<en|zh|ja>
```
, use that value for this run and update
```
selected.language
```
to it (update only that field).
```
zh-CN
```
should be treated as an alias of
```
zh
```
.

When

selected.language=en

, all headings in

/specs/background/original.md

must be English; normalize any non-English headings to:

# Raw Requirement

# Summary

# Business Context

# Core Features

# Pages & Interactions

# Data Model

# Business Logic

# Risks & Assumptions

# Open Questions

Flow: 0. Ensure

/docs/

exists, and ensure subfolders exist:

```
/docs/legacy/
```
```
/docs/current/
```
```
/docs/refine/
```
```
/docs/dependencies/
```
Do NOT create
```
/docs/change/
```
(it is deprecated). 0.2 If the user passes
```
lang=<en|zh|ja>
```
in the command arguments, set
```
/scheme.yaml
```
```
selected.language
```
to that value (update only that field, keep other fields and formatting unchanged).
```
zh-CN
```
should be treated as an alias of
```
zh
```
. 0.5 Create editable project constraints so the user can tweak them early (do not overwrite if they already exist):
Create
```
/scheme.yaml
```
with defaults (prototype stack selection + catalog) if missing
Create
```
/prototype_ui_convention.md
```
(same directory as
```
/scheme.yaml
```
) if missing

Ask the user to input the original requirement.
When the user presses Enter, treat the input as the raw requirement source.
Load the prompt file at
```
prompts/vspec_new/background.md
```
.
Use that prompt to analyze the requirement and expand the business context.
Write the raw requirement and background analysis output to
```
/specs/background/original.md
```
. 5.5 Create
```
/specs/background/question_and_answer.html
```
by copying
```
prompts/vspec_new/question_and_answer.html
```
(single-file HTML with inline CSS/JS) so the user can answer questions and write back to markdown.
Ask the user to answer the questions from the Open Questions section (use the section title in the selected language). The user should answer via
```
/specs/background/question_and_answer.html
```
(select
```
/specs/background/original.md
```
in the page and save back), then reply with a continuation signal (e.g.
```
继续
```
/
```
continue
```
). Then STOP. Do not load any subsequent prompts or generate any further artifacts before that.
After the user replies (answers or confirmed), load
```
prompts/vspec_new/stakeholders.md
```
to analyze stakeholders.
Write the stakeholder result to
```
/specs/background/stakeholder.md
```
(markdown table).
Load
```
prompts/vspec_new/roles.md
```
to analyze system user roles (direct users) and their work tasks.
Write the roles result to
```
/specs/background/roles.md
```
.
Load
```
prompts/vspec_new/terms.md
```
to extract key terms and definitions.
Write the terms result to
```
/specs/background/terms.md
```
(markdown table).
Load
```
prompts/vspec_new/flows.md
```
to analyze business workflows and generate PlantUML swimlane diagrams.
Write the diagrams to
```
/specs/flows/*.puml
```
.
Load
```
prompts/vspec_new/scenarios.md
```
to enumerate business scenarios by node combinations.
Write the scenarios result to
```
/specs/background/scenarios.md
```
(markdown table).
Load
```
prompts/vspec_new/details_pre_post.md
```
to create per-node detail folders and generate
```
pre_post.md
```
for each node.

Load

prompts/vspec_new/details_constraints.md

to generate

constraints.md

for each node.

Load

prompts/vspec_new/details_variations.md

to generate

variations.md

for each node.

Load

prompts/vspec_new/details_boundaries.md

to generate

boundaries.md

for each node.

Load

prompts/vspec_new/details_symmetry.md

to generate

symmetry.md

for each node.

Ensure the per-node outputs are written under
```
/specs/background/scenario_details/
```
.
Load
```
prompts/vspec_new/dependencies.md
```
to analyze external dependency systems.
Write the dependencies result to
```
/specs/background/dependencies.md
```
.
Load
```
prompts/vspec_new/functions.md
```
to generate feature/function lists grouped by modules and external dependency systems.
Write the function lists to
```
/specs/functions/
```
.
Load
```
prompts/vspec_new/questions.md
```
to generate question lists and required business materials.
Write the questions result to
```
/specs/background/questions.md
```
(markdown list).
Load
```
prompts/harness/post_new_verify.md
```
to validate whether functions and scenario_details are complete (login/config/master-data/approval). If it outputs any issues, show the issue list and stop.
Return the structured analysis result and continue to the next requirement-design step.

使用此命令创建新的需求分析会话。

语言规则：

读取
```
/scheme.yaml
```
中的
```
selected.language
```
字段（支持
```
en
```
、
```
zh
```
、
```
ja
```
；若缺失或无效则默认使用
```
en
```
）。
如果命令参数或输入明确指定
```
lang=<en|zh|ja>
```
，则本次运行使用该值，并更新
```
selected.language
```
字段（仅更新此字段）。
```
zh-CN
```
视为
```
zh
```
的别名。

当

selected.language=en

时，

/specs/background/original.md

中的所有标题必须为英文；将非英文标题统一规范为：

# Raw Requirement

、

# Summary

、

# Business Context

、

# Core Features

、

# Pages & Interactions

、

# Data Model

、

# Business Logic

、

# Risks & Assumptions

、

# Open Questions

。

流程： 0. 确保

/docs/

```
/docs/legacy/
```
```
/docs/current/
```
```
/docs/refine/
```
```
/docs/dependencies/
```
请勿创建
```
/docs/change/
```
（该目录已废弃）。 0.2 如果用户在命令参数中传入
```
lang=<en|zh|ja>
```
，将
```
/scheme.yaml
```
中的
```
selected.language
```
字段设置为该值（仅更新此字段，保留其他字段和格式不变）。
```
zh-CN
```
视为
```
zh
```
的别名。 0.5 创建可编辑的项目约束文件，方便用户提前调整（若已存在则不覆盖）：
若
```
/scheme.yaml
```
缺失，则创建包含默认配置（原型技术栈选择+目录）的文件
若
```
/prototype_ui_convention.md
```
（与
```
/scheme.yaml
```
同目录）缺失，则创建该文件

请用户输入原始需求。
用户按下回车键后，将输入内容视为原始需求源。
加载提示词文件
```
prompts/vspec_new/background.md
```
。
使用该提示词分析需求并扩展业务背景。
将原始需求和背景分析结果写入
```
/specs/background/original.md
```
。 5.5 复制
```
prompts/vspec_new/question_and_answer.html
```
（内嵌CSS/JS的单文件HTML）创建
```
/specs/background/question_and_answer.html
```
，以便用户回答问题并写回markdown文件。
请用户回答“待确认问题”部分的问题（使用所选语言的章节标题）。用户需通过
```
/specs/background/question_and_answer.html
```
操作（在页面中选择
```
/specs/background/original.md
```
并保存），然后回复继续信号（如
```
继续
```
/
```
continue
```
）。之后停止操作，在用户回复前请勿加载后续提示词或生成更多产物。
用户回复（完成回答或确认）后，加载
```
prompts/vspec_new/stakeholders.md
```
分析利益相关方。
将利益相关方分析结果写入
```
/specs/background/stakeholder.md
```
（markdown表格）。
加载
```
prompts/vspec_new/roles.md
```
分析系统用户角色（直接用户）及其工作任务。
将角色分析结果写入
```
/specs/background/roles.md
```
。
加载
```
prompts/vspec_new/terms.md
```
提取关键术语及定义。
将术语提取结果写入
```
/specs/background/terms.md
```
（markdown表格）。
加载
```
prompts/vspec_new/flows.md
```
分析业务流程并生成PlantUML泳道图。
将流程图写入
```
/specs/flows/*.puml
```
。
加载
```
prompts/vspec_new/scenarios.md
```
通过节点组合枚举业务场景。
将场景枚举结果写入
```
/specs/background/scenarios.md
```
（markdown表格）。
加载
```
prompts/vspec_new/details_pre_post.md
```
创建每个节点的细节文件夹，并为每个节点生成
```
pre_post.md
```
。

加载

prompts/vspec_new/details_constraints.md

为每个节点生成

constraints.md

。

加载

prompts/vspec_new/details_variations.md

为每个节点生成

variations.md

。

加载

prompts/vspec_new/details_boundaries.md

为每个节点生成

boundaries.md

。

加载

prompts/vspec_new/details_symmetry.md

为每个节点生成

symmetry.md

。

确保每个节点的输出文件写入
```
/specs/background/scenario_details/
```
目录下。
加载
```
prompts/vspec_new/dependencies.md
```
分析外部依赖系统。
将依赖分析结果写入
```
/specs/background/dependencies.md
```
。
加载
```
prompts/vspec_new/functions.md
```
生成按模块和外部依赖系统分组的功能列表。
将功能列表写入
```
/specs/functions/
```
目录。
加载
```
prompts/vspec_new/questions.md
```
生成问题列表和所需业务材料清单。
将问题列表写入
```
/specs/background/questions.md
```
（markdown列表）。
加载
```
prompts/harness/post_new_verify.md
```
验证功能和场景细节是否完整（包含登录/配置/主数据/审批）。若输出问题列表，则展示问题并停止操作。
返回结构化分析结果，进入下一阶段的需求设计步骤。

/vspec:interview

/vspec:interview

Use this command to generate an interview outline / survey questionnaire for user research and requirement validation.

Flow:

Load
```
prompts/vspec_interview/interview.md
```
.
Generate the questionnaire markdown and write it to
```
/docs/current/interview_questionnaire.md
```
.

使用此命令生成用于用户研究和需求验证的访谈大纲/调查问卷。

流程：

加载
```
prompts/vspec_interview/interview.md
```
。

生成问卷markdown文件并写入

/docs/current/interview_questionnaire.md

。

/vspec:i-word

/vspec:i-word

Use this command to generate a Word-openable

.docx

(single-file HTML) version of the interview questionnaire.

Flow:

Ensure

/docs/current/interview_questionnaire.md

exists; if missing, ask the user to run

/vspec:interview

first.

Load

prompts/vspec_interview/interview_word.md

Write the Word file to

/docs/current/interview_questionnaire.docx

使用此命令生成可在Word中打开的

.docx

格式（单文件HTML）访谈问卷。

流程：

确保

/docs/current/interview_questionnaire.md

存在；若缺失，请用户先运行

/vspec:interview

。

加载

prompts/vspec_interview/interview_word.md

。

将Word格式文件写入

/docs/current/interview_questionnaire.docx

。

/vspec:refine

/vspec:refine

Use this command to refine and update the requirement based on refine materials stored under

/docs/refine/

, or based on one or more input files/directories provided as command arguments.

Flow: 0. Ensure

/specs/details/

exists and is non-empty; if missing, stop and ask the user to run

/vspec:detail

first.

Read refine inputs:
- If command arguments are provided, treat them as refine input sources (files/directories).
- Otherwise:
  - Prefer
```
/docs/refine/refine.md
```
    (if present).
  - If
```
/docs/refine/refine.md
```
    is missing, ask the user to paste the refinement content (what to change) in the prompt window, and treat that pasted content as the refine input.
  - You may additionally read
```
/docs/refine/
```
    as supporting materials when explicitly referenced/needed (prefer
```
/docs/refine/file_list.md
```
    if present; else read files in name order).
If
```
prompts/vspec_refine/refine.md
```
is missing, stop immediately and do nothing.
Load
```
prompts/vspec_refine/refine.md
```
to apply the refinement, update the canonical requirement, and update impacted artifacts.
Append the refinement result to
```
/specs/background/original.md
```
, and update impacted
```
/specs/details/
```
and
```
/specs/prototypes/
```
accordingly; if
```
/specs/backend/
```
exists and is non-empty, sync-update impacted backend code as well.

使用此命令基于

/docs/refine/

目录下的优化材料，或命令参数提供的一个/多个输入文件/目录，优化并更新需求。

流程： 0. 确保

/specs/details/

目录存在且非空；若缺失，停止操作并请用户先运行

/vspec:detail

。

读取优化输入源：
- 若提供命令参数，则将其视为优化输入源（文件/目录）。
- 若未提供命令参数：
  - 优先读取
```
/docs/refine/refine.md
```
    （若存在）。
  - 若
```
/docs/refine/refine.md
```
    缺失，请用户在提示窗口粘贴优化内容（需修改的部分），并将粘贴内容视为优化输入源。
  - 当明确需要时，可额外读取
```
/docs/refine/
```
    下的支持材料（优先读取
```
/docs/refine/file_list.md
```
    ；若不存在则按文件名顺序读取文件）。
若
```
prompts/vspec_refine/refine.md
```
缺失，立即停止操作且不执行任何内容。
加载
```
prompts/vspec_refine/refine.md
```
应用优化，更新标准需求及受影响的产物。
将优化结果追加到
```
/specs/background/original.md
```
，并相应更新受影响的
```
/specs/details/
```
和
```
/specs/prototypes/
```
目录；若
```
/specs/backend/
```
存在且非空，同步更新受影响的后端代码。

/vspec:refine-q

/vspec:refine-q

Use this command to refine and update the requirement based on answered questions.

Flow:

If
```
/specs/background/questions.md
```
is missing, stop immediately and do nothing.
If
```
/specs/background/questions.md
```
contains no pending/unanswered questions, stop immediately and do nothing.
Read
```
/specs/background/questions.md
```
and pick answered items.
Load
```
prompts/vspec_refine/refine_q.md
```
to merge answers into the canonical requirement.
Append the refinement result to
```
/specs/background/original.md
```
.
Update
```
/specs/background/questions.md
```
to mark items that are treated as answered in this run:
- Wrap the answer and status values with
```
<mark>...</mark>
```
  (use the field names in the selected language) so answered items are visually highlighted.

使用此命令基于已回答的问题优化并更新需求。

流程：

若
```
/specs/background/questions.md
```
缺失，立即停止操作且不执行任何内容。
若
```
/specs/background/questions.md
```
中没有待处理/未回答的问题，立即停止操作且不执行任何内容。
读取
```
/specs/background/questions.md
```
并筛选已回答的问题。
加载
```
prompts/vspec_refine/refine_q.md
```
将回答合并到标准需求中。
将优化结果追加到
```
/specs/background/original.md
```
。
更新
```
/specs/background/questions.md
```
，标记本次运行中已处理的回答项：
- 使用
```
<mark>...</mark>
```
  包裹回答内容和状态值（使用所选语言的字段名），使已回答项在视觉上突出显示。

/vspec:more-q

/vspec:more-q

Use this command to generate more clarification questions and append them to

/specs/background/questions.md

Flow:

If
```
/specs/background/questions.md
```
is missing, stop and ask the user to run
```
/vspec:new
```
first.
Load
```
prompts/vspec_more_q/more_q.md
```
to generate additional questions (avoid duplicates and continue numbering).
Append the new items to
```
/specs/background/questions.md
```
(do not rewrite existing items).
Provide a clear instruction for the user to answer the questions and then run
```
/vspec:refine-q
```
.

使用此命令生成更多澄清问题并追加到

/specs/background/questions.md

。

流程：

若
```
/specs/background/questions.md
```
缺失，停止操作并请用户先运行
```
/vspec:new
```
。
加载
```
prompts/vspec_more_q/more_q.md
```
生成额外问题（避免重复，延续编号）。
将新问题追加到
```
/specs/background/questions.md
```
（不重写现有内容）。
向用户提供明确说明：回答问题后运行
```
/vspec:refine-q
```
。

/vspec:detail

/vspec:detail

Use this command to expand requirement details based on the function list.

Language:

Read
```
/scheme.yaml
```
```
selected.language
```
(supports
```
en
```
,
```
zh
```
,
```
ja
```
; default to
```
en
```
if missing/invalid).
All generated spec documents under
```
/specs/
```
must use the selected language consistently (headings, tables, field descriptions, statuses, button names, messages).

Flow:

Read the feature/function list from
```
/specs/functions/*
```
.
- You must iterate every function row across all files under
```
/specs/functions/
```
  (not just core.md), so no module or external-system function is missed.

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).

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.
- 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).
- 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:
  - For
```
Web
```
    /
```
Mobile
```
    /
```
Web+Mobile
```
    steps: always generate
```
page_load.md
```
    and
```
interaction.md
```
    .
  - For
```
Backend
```
    steps: always generate
```
service_logic.md
```
    (service logic: inputs/outputs, rules, states, APIs/events, errors, idempotency).
  - For
```
Job
```
    steps: always generate
```
job_logic.md
```
    (job logic: trigger/schedule, data scope, retries/compensation, observability, failure handling).
- Always generate the baseline docs:
  - ```
  rbac.md
```
  : RBAC permissions down to page areas and controls.
- ```
data_permission.md
```
    : data permission rules and scope.
- Page-only:
  - ```
  page_load.md
```
  : page loading logic.
- ```
interaction.md
```
    : page interaction logic.
  - ```
  validation_matrix.md
```
  : validation logic in matrix format (only for submit-type pages/actions; if the page has no submit/save/approve/reject/cancel/change actions, skip).
- ```
post_submit_check.md
```
    : checks after submit (if the page has submit).
  - ```
  post_submit_processing.md
```
  : processing logic after submit (if the page has submit).
- ```
post_submit_navigation.md
```
    : post-submit return and navigation (if the page has submit).
- Conditional (generate only if involved by the current function’s logic/scenarios/models/dependencies):
  - ```
  logging_matrix.md
```
  : operation/audit logging (only when the business requires change history retention, compliance audit, or non-repudiation; otherwise skip).
- ```
decision_matrix.md
```
    : decision matrix (决策矩阵) for operation availability under each status (if there is a status machine and operations vary by status/role).
  - ```
  notification_matrix.md
```
  : notifications (if there is any notification requirement).
- ```
mq.md
```
    : MQ topics/events/message schema/reliability details (if there is async events, queues, or cross-system eventing).
  - ```
  file_import.md
```
  : file import details (if there is any import entry/requirement).
- ```
file_export.md
```
    : file export details (if there is any export entry/requirement).
  - ```
  formula.md
```
  : calculation formulas and metric semantics (if there are any calculations/metrics).
- ```
expression_tree.md
```
    : expression tree (HTML) (if there is multi-level nested branching logic).
- ```
code_rules.md
```
  : numbering/code generation rules (if any codes/serial numbers are generated/assigned).
- ```
payment.md
```
  : payment and refund details (if there is any payment/refund/settlement/reconciliation logic).
- ```
auth.md
```
  : account/login details (if there is any non-SSO login/account/password flow).
- ```
judgemental_matrix.md
```
  : judgemental matrix (判定矩阵) for multi-factor logic branching (if 2+ factors jointly decide outcomes).
- Module-level (generate at most once per module, and only if involved):
  - ```
  timeline.md
```
  : time-axis visualization (HTML) for overall flow impact analysis (only when there is long time-span logic that affects flow decisions, e.g. effective/expiry, deadlines, grace periods, cross-day rules).
- ```
state_machine.md
```
    : status list + transitions + PlantUML state diagram (overall; not per function).
  - ```
  nfp.md
```
  : non-functional requirements summary for the module (overall; not per function).
- ```
cron_job.md
```
    : scheduled jobs summary for the module (overall; not per function).

Write only the generated (involved) detail documents:

Per-function:

/specs/details/<module_slug>/<logic_type>/<function_slug>.(md|html)

Module-level:

/specs/details/<module_slug>/<logic_type>/<module_slug>.(md|html)

Load
```
prompts/vspec_detail/index.md
```
to generate a single-page viewer
```
/specs/details/reader.html
```
:
- Left: directory tree based on
```
/specs/details/
```
- Right: markdown-rendered reading pane
- Render PlantUML diagrams (do not show raw PlantUML text)

使用此命令基于功能列表扩展需求细节。

语言规则：

读取
```
/scheme.yaml
```
中的
```
selected.language
```
字段（支持
```
en
```
、
```
zh
```
、
```
ja
```
；若缺失或无效则默认使用
```
en
```
）。
```
/specs/
```
目录下生成的所有规格文档必须统一使用所选语言（标题、表格、字段描述、状态、按钮名称、提示信息）。

流程：

从
```
/specs/functions/*
```
读取功能列表。
- 必须遍历
```
/specs/functions/
```
  下所有文件中的每一行功能（不仅仅是core.md），确保没有遗漏任何模块或外部系统功能。

读取可用的支持产物：

/specs/background/*

、

/specs/flows/*.puml

、

/specs/background/scenario_details/

、

/specs/background/roles.md

，以及已有的

/specs/models/*.md

（若存在）。

针对每个功能（页面或非页面任务），先确定实际涉及的细节产物，再仅生成这些产物；不为未涉及的部分生成文档。
- 覆盖要求：对于遍历的每一行功能，必须至少生成
```
rbac.md
```
  和
```
data_permission.md
```
  。若无法生成，则输出明确错误并停止操作（不得静默跳过）。
- 步骤类型要求：必须从功能行中确定步骤类型（如终端类型/页面 vs 后端 vs 任务），并生成对应的逻辑产物；不得跳过逻辑：
  - 对于
```
Web
```
    /
```
Mobile
```
    /
```
Web+Mobile
```
    步骤：必须生成
```
page_load.md
```
    和
```
interaction.md
```
    。
  - 对于
```
Backend
```
    步骤：必须生成
```
service_logic.md
```
    （服务逻辑：输入/输出、规则、状态、API/事件、错误、幂等性）。
  - 对于
```
Job
```
    步骤：必须生成
```
job_logic.md
```
    （任务逻辑：触发/调度、数据范围、重试/补偿、可观测性、故障处理）。
- 必须生成基线文档：
  - ```
  rbac.md
```
  ：细化到页面区域和控件的RBAC权限。
- ```
data_permission.md
```
    ：数据权限规则和范围。
- 仅页面类步骤需生成：
  - ```
  page_load.md
```
  ：页面加载逻辑。
- ```
interaction.md
```
    ：页面交互逻辑。
  - ```
  validation_matrix.md
```
  ：矩阵格式的验证逻辑（仅适用于提交类页面/操作；若页面无提交/保存/审批/拒绝/取消/修改操作，则跳过）。
- ```
post_submit_check.md
```
    ：提交后的检查逻辑（若页面有提交操作）。
  - ```
  post_submit_processing.md
```
  ：提交后的处理逻辑（若页面有提交操作）。
- ```
post_submit_navigation.md
```
    ：提交后的返回与导航逻辑（若页面有提交操作）。
- 条件生成（仅当当前功能的逻辑/场景/模型/依赖涉及到才生成）：
  - ```
  logging_matrix.md
```
  ：操作/审计日志（仅当业务需要保留变更历史、合规审计或不可否认性时生成；否则跳过）。
- ```
decision_matrix.md
```
    ：各状态下操作可用性的决策矩阵（若存在状态机且操作因状态/角色而异）。
  - ```
  notification_matrix.md
```
  ：通知规则（若存在任何通知需求）。
- ```
mq.md
```
    ：MQ主题/事件/消息 schema/可靠性细节（若存在异步事件、队列或跨系统事件）。
  - ```
  file_import.md
```
  ：文件导入细节（若存在任何导入入口/需求）。
- ```
file_export.md
```
    ：文件导出细节（若存在任何导出入口/需求）。
  - ```
  formula.md
```
  ：计算公式和指标语义（若存在任何计算/指标）。
- ```
expression_tree.md
```
    ：表达式树（HTML格式）（若存在多级嵌套分支逻辑）。
  - ```
  code_rules.md
```
  ：编号/代码生成规则（若存在任何代码/序列号生成/分配逻辑）。
- ```
payment.md
```
    ：支付与退款细节（若存在任何支付/退款/结算/对账逻辑）。
  - ```
  auth.md
```
  ：账户/登录细节（若存在非SSO登录/账户/密码流程）。
- ```
judgemental_matrix.md
```
    ：多因素逻辑分支的判定矩阵（若2个及以上因素共同决定结果）。
- 模块级生成（每个模块最多生成一次，仅当涉及到才生成）：
  - ```
  timeline.md
```
  ：时间轴可视化（HTML格式），用于整体流程影响分析（仅当存在影响流程决策的长周期逻辑时生成，如生效/过期、截止日期、宽限期、跨天规则）。
- ```
state_machine.md
```
    ：状态列表+转换关系+PlantUML状态图（全局，而非每个功能单独生成）。
  - ```
  nfp.md
```
  ：模块的非功能性需求汇总（全局，而非每个功能单独生成）。
- ```
cron_job.md
```
    ：模块的定时任务汇总（全局，而非每个功能单独生成）。

仅写入已生成的（涉及到的）细节文档：

每个功能：

/specs/details/<module_slug>/<logic_type>/<function_slug>.(md|html)

模块级：

/specs/details/<module_slug>/<logic_type>/<module_slug>.(md|html)

加载
```
prompts/vspec_detail/index.md
```
生成单页查看器
```
/specs/details/reader.html
```
：
- 左侧：基于
```
/specs/details/
```
  的目录树
- 右侧：markdown渲染的阅读面板
- 渲染PlantUML图（不显示原始PlantUML文本）

/vspec:doc

/vspec:doc

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/

Language:

Read
```
/scheme.yaml
```
```
selected.language
```
(supports
```
en
```
,
```
zh
```
,
```
ja
```
; default to
```
en
```
if missing/invalid).
The generated Word document must use the selected language consistently (titles, headings, field labels, table headers).

Flow:

Ensure
```
/docs/current/
```
exists.

Read the existing artifacts when available:

Canonical requirement:
```
/specs/background/original.md
```
Function list:
```
/specs/functions/*
```
Detail specs:
```
/specs/details/**
```

Roles & permissions:

/specs/background/roles.md

/specs/details/**/rbac.md

Data permission:
```
/specs/details/**/data_permission.md
```

Scenarios & flows:

/specs/background/scenarios.md

/specs/background/scenario_details/**

/specs/flows/*.puml

Dependencies:
```
/specs/background/dependencies.md
```
Models:
```
/specs/models/*.md
```

Load
```
prompts/vspec_doc/doc.md
```
and generate the doc as a Word-openable single HTML file.
Write the output file to:
```
/docs/current/requirement_detail.docx
```
.

使用此命令生成Word文档（可在Word中打开的单文件HTML格式

.doc

），将需求细节产物汇总为可交付文档，并写入

/docs/current/

目录下。

语言规则：

读取
```
/scheme.yaml
```
中的
```
selected.language
```
字段（支持
```
en
```
、
```
zh
```
、
```
ja
```
；若缺失或无效则默认使用
```
en
```
）。
生成的Word文档必须统一使用所选语言（标题、副标题、字段标签、表格表头）。

流程：

确保
```
/docs/current/
```
目录存在。

读取可用的现有产物：

标准需求：
```
/specs/background/original.md
```
功能列表：
```
/specs/functions/*
```
细节规格：
```
/specs/details/**
```

角色与权限：

/specs/background/roles.md

、

/specs/details/**/rbac.md

数据权限：
```
/specs/details/**/data_permission.md
```

场景与流程：

/specs/background/scenarios.md

、

/specs/background/scenario_details/**

、

/specs/flows/*.puml

依赖：
```
/specs/background/dependencies.md
```
模型：
```
/specs/models/*.md
```

加载
```
prompts/vspec_doc/doc.md
```
并生成可在Word中打开的单HTML格式文档。
将输出文件写入：
```
/docs/current/requirement_detail.docx
```
。

/vspec:verify

/vspec:verify

Use this command to generate models and a runnable prototype for validation.

Language:

Read
```
/scheme.yaml
```
```
selected.language
```
(supports
```
en
```
,
```
zh
```
,
```
ja
```
; default to
```
en
```
if missing/invalid).
Generate
```
/specs/models/
```
docs and all prototype UI copy in the selected language consistently.

Flow: 0. Ensure

/specs/details/

exists and is non-empty; if missing, stop and output the prerequisite message: “Run /vspec:detail to generate /specs/details/ before /vspec:verify”.

If
```
/specs/background/questions.md
```
exists and contains unanswered questions, ask the user to answer them before continuing (allow skip per question, but ensure none remains unanswered).
Load
```
prompts/vspec_verify/model.md
```
to generate data models.
Write model files to
```
/specs/models/*.md
```
.
Generate a runnable page prototype based on functions, details, models, and roles; the prototype tech stack can be selected via
```
/scheme.yaml
```
(auto-created with defaults if missing).
- Load
```
prompts/vspec_verify/prototype.md
```
  for the prototype generation rules (must follow
```
scheme.yaml
```
  stack; do not output html-only).
Write the prototype to
```
/specs/prototypes/
```
.
Load
```
prompts/harness/post_verify_stack_verify.md
```
to validate whether the prototype frontend stack matches
```
/scheme.yaml
```
. If it outputs any issues, show the issue list and stop.
Load
```
prompts/vspec_verify/validation.md
```
to generate a scenario validation web page.
Write the validation page to
```
/specs/prototypes/
```
and provide a
```
scenario.html
```
entry for access.
Load
```
prompts/vspec_verify/entries.md
```
to generate an entry page and write it to
```
/specs/prototypes/entries.html
```
(do not link it from any menu/header).
Load
```
prompts/harness/post_verify_mobile_selection_check.md
```
to ensure mobile data selection uses a picker page (list-based), not dropdown Select. If it outputs any issues, show the issue list and stop.
Load
```
prompts/harness/post_verify_price_format_check.md
```
to validate money/price formatting (right aligned, 2 decimals, thousand separators). If it outputs any issues, show the issue list and stop.
Load
```
prompts/harness/post_verify_click_check.md
```
to detect clickable UI elements that do nothing. If it outputs any issues, show the issue list and stop.
Load
```
prompts/harness/post_verify_verify.md
```
to validate the prototype completeness. If it outputs any issues, show the issue list and stop.

使用此命令生成模型和可运行的原型以进行验证。

语言规则：

读取
```
/scheme.yaml
```
中的
```
selected.language
```
字段（支持
```
en
```
、
```
zh
```
、
```
ja
```
；若缺失或无效则默认使用
```
en
```
）。
```
/specs/models/
```
下的文档和所有原型UI文案必须统一使用所选语言。

流程： 0. 确保

/specs/details/

目录存在且非空；若缺失，停止操作并输出前置要求提示：“请先运行/vspec:detail生成/specs/details/，再运行/vspec:verify”。

若
```
/specs/background/questions.md
```
存在且包含未回答的问题，请用户先回答这些问题（允许跳过单个问题，但确保无未回答问题遗留）。
加载
```
prompts/vspec_verify/model.md
```
生成数据模型。
将模型文件写入
```
/specs/models/*.md
```
。
基于功能、细节、模型和角色生成可运行的页面原型；原型技术栈可通过
```
/scheme.yaml
```
选择（若缺失则自动创建默认配置）。
- 加载
```
prompts/vspec_verify/prototype.md
```
  获取原型生成规则（必须遵循
```
scheme.yaml
```
  指定的技术栈；不得仅输出html）。
将原型写入
```
/specs/prototypes/
```
目录。
加载
```
prompts/harness/post_verify_stack_verify.md
```
验证原型前端技术栈是否与
```
/scheme.yaml
```
匹配。若输出问题列表，则展示问题并停止操作。
加载
```
prompts/vspec_verify/validation.md
```
生成场景验证网页。
将验证页面写入
```
/specs/prototypes/
```
目录，并提供
```
scenario.html
```
入口供访问。
加载
```
prompts/vspec_verify/entries.md
```
生成入口页面并写入
```
/specs/prototypes/entries.html
```
（请勿从任何菜单/页眉链接此页面）。
加载
```
prompts/harness/post_verify_mobile_selection_check.md
```
确保移动端数据选择使用选择器页面（基于列表），而非下拉选择框。若输出问题列表，则展示问题并停止操作。
加载
```
prompts/harness/post_verify_price_format_check.md
```
验证金额/价格格式（右对齐、保留2位小数、千位分隔符）。若输出问题列表，则展示问题并停止操作。
加载
```
prompts/harness/post_verify_click_check.md
```
检测无响应的可点击UI元素。若输出问题列表，则展示问题并停止操作。
加载
```
prompts/harness/post_verify_verify.md
```
验证原型完整性。若输出问题列表，则展示问题并停止操作。

/vspec:qc

/vspec:qc

Use this command to run a quality check on the generated requirement artifacts under

/specs/

Note: The Pro edition supports broader quality checks (e.g. more post-run prototype/implementation verifications) and requires a paid plan.

Language:

Read
```
/scheme.yaml
```
```
selected.language
```
(supports
```
en
```
,
```
zh
```
,
```
ja
```
; default to
```
en
```
if missing/invalid).
The QC report
```
/specs/qc_report.md
```
must use the selected language consistently.

Flow:

Read built-in standard at
```
prompts/vspec_qc/quality_standard.md
```
.
If a requirement quality error book exists under project
```
qc/
```
, generate/update project root
```
quality_standard.md
```
based on it.
If project root
```
quality_standard.md
```
exists, merge it as supplementary/overriding standard.
Load
```
prompts/vspec_qc/qc.md
```
and generate a non-conformance checklist.
Write the report to
```
/specs/qc_report.md
```
.

使用此命令对

/specs/

目录下生成的需求产物进行质量检查。

注意：专业版支持更全面的质量检查（如更多运行后原型/实现验证），需要付费订阅。

语言规则：

读取
```
/scheme.yaml
```
中的
```
selected.language
```
字段（支持
```
en
```
、
```
zh
```
、
```
ja
```
；若缺失或无效则默认使用
```
en
```
）。
QC报告
```
/specs/qc_report.md
```
必须统一使用所选语言。

流程：

读取内置标准
```
prompts/vspec_qc/quality_standard.md
```
。
若项目
```
qc/
```
目录下存在需求质量错误手册，则基于该手册生成/更新项目根目录下的
```
quality_standard.md
```
。
若项目根目录下存在
```
quality_standard.md
```
，则将其合并为补充/覆盖标准。
加载
```
prompts/vspec_qc/qc.md
```
生成不符合项检查清单。
将报告写入
```
/specs/qc_report.md
```
。

/vspec:accept

/vspec:accept

Use this command to generate acceptance test cases.

Language:

Read
```
/scheme.yaml
```
```
selected.language
```
(supports
```
en
```
,
```
zh
```
,
```
ja
```
; default to
```
en
```
if missing/invalid).
All acceptance documents under
```
/specs/acceptance/
```
must use the selected language consistently.

Flow:

Read

/specs/functions/*

/specs/background/scenarios.md

/specs/background/scenario_details/

/specs/background/roles.md

/specs/models/*.md

Load
```
prompts/vspec_accept/accept.md
```
to generate acceptance test cases covering core flows, exceptions, boundary, permissions, and data scope.
Write results to
```
/specs/acceptance/
```
(one subfolder per function) and generate an index at
```
/specs/acceptance/index.md
```
.

使用此命令生成验收测试用例。

语言规则：

读取
```
/scheme.yaml
```
中的
```
selected.language
```
字段（支持
```
en
```
、
```
zh
```
、
```
ja
```
；若缺失或无效则默认使用
```
en
```
）。
```
/specs/acceptance/
```
目录下的所有验收文档必须统一使用所选语言。

流程：

读取

/specs/functions/*

、

/specs/background/scenarios.md

、

/specs/background/scenario_details/

、

/specs/background/roles.md

、

/specs/models/*.md

。

加载
```
prompts/vspec_accept/accept.md
```
生成覆盖核心流程、异常场景、边界情况、权限和数据范围的验收测试用例。
将结果写入
```
/specs/acceptance/
```
目录（每个功能对应一个子文件夹），并在
```
/specs/acceptance/index.md
```
生成索引。

/vspec:append-test

/vspec:append-test

Use this command to generate automation test code based on acceptance cases and specs.

Language:

Read
```
/scheme.yaml
```
```
selected.language
```
(supports
```
en
```
,
```
zh
```
,
```
ja
```
; default to
```
en
```
if missing/invalid).
Test case titles/descriptions should follow the selected language as much as possible.

Flow:

Read
```
/specs/acceptance/
```
,
```
/specs/functions/*
```
,
```
/specs/details/
```
, and detect the existing test frameworks in the repository.
Load
```
prompts/vspec_test/test.md
```
to generate automation tests using the existing frameworks and conventions.
Write test code to the project test directories (or
```
/tests/
```
if no standard exists) and ensure it can run with existing scripts.
Load
```
prompts/harness/post_append_test_coverage_check.md
```
to verify whether test coverage is sufficiently complete; if it outputs any issues, continue.
If issues exist, rerun
```
/vspec:append-test
```
once focusing only on the missing items from the issue list, then rerun the coverage check.
If issues still exist after the second coverage check, show the issue list and stop.
This command generates/adds tests to improve coverage; it does not execute test commands.

使用此命令基于验收用例和规格文档生成自动化测试代码。

语言规则：

读取
```
/scheme.yaml
```
中的
```
selected.language
```
字段（支持
```
en
```
、
```
zh
```
、
```
ja
```
；若缺失或无效则默认使用
```
en
```
）。
测试用例标题/描述应尽可能遵循所选语言。

流程：

读取
```
/specs/acceptance/
```
、
```
/specs/functions/*
```
、
```
/specs/details/
```
，并检测仓库中已有的测试框架。
加载
```
prompts/vspec_test/test.md
```
使用现有框架和规范生成自动化测试代码。
将测试代码写入项目测试目录（若无标准目录则写入
```
/tests/
```
），并确保可通过现有脚本运行。
加载
```
prompts/harness/post_append_test_coverage_check.md
```
验证测试覆盖率是否足够完整；若输出问题列表，则继续操作。
若存在问题，重新运行
```
/vspec:append-test
```
一次，仅聚焦于问题列表中的缺失项，然后重新运行覆盖率检查。
若第二次覆盖率检查后仍存在问题，则展示问题列表并停止操作。
此命令生成/添加测试以提升覆盖率；不执行测试命令。

/vspec:impl

/vspec:impl

Use this command to generate integrated frontend/backend code based on the specs.

Flow:

Read

/specs/functions/*

/specs/details/

/specs/models/*.md

/specs/background/dependencies.md

, and detect the current frontend/backend stacks and code conventions.

Load
```
prompts/vspec_impl/implement.md
```
and implement backend-first: generate a runnable backend project under
```
/specs/backend/
```
(health check + core APIs/services), then generate frontend integration after backend APIs are available.
Write code only under
```
/specs/
```
with minimal diffs and keep it reviewable; backend must be under
```
/specs/backend/
```
and prototype frontend under
```
/specs/prototypes/
```
.
Load
```
prompts/harness/post_impl_verify.md
```
to validate backend MVC structure and test coverage. If it outputs any issues, show the issue list and stop.

使用此命令基于规格文档生成集成的前端/后端代码。

流程：

读取

/specs/functions/*

、

/specs/details/

、

/specs/models/*.md

、

/specs/background/dependencies.md

，并检测当前的前端/后端技术栈和代码规范。

加载
```
prompts/vspec_impl/implement.md
```
，优先实现后端：在
```
/specs/backend/
```
目录下生成可运行的后端项目（健康检查+核心API/服务），然后在后端API可用后生成前端集成代码。
仅在
```
/specs/
```
目录下写入代码，尽量减少差异并保持可审阅性；后端代码必须写入
```
/specs/backend/
```
，原型前端代码写入
```
/specs/prototypes/
```
。
加载
```
prompts/harness/post_impl_verify.md
```
验证后端MVC结构和测试覆盖率。若输出问题列表，则展示问题并停止操作。

/vspec:upgrade

/vspec:upgrade

Use this command to upgrade/retrofit requirements based on materials stored under

/docs/

(

/docs/legacy

for legacy system,

/docs/current

for new inputs), and regenerate the

/specs/

artifacts in the same structure as

/vspec:new

Language:

Read
```
/scheme.yaml
```
```
selected.language
```
(supports
```
en
```
,
```
zh
```
,
```
ja
```
; default to
```
en
```
if missing/invalid).
All regenerated
```
/specs/**
```
artifacts must use the selected language consistently.

Flow:

Ensure the input entry file exists at
```
/docs/current/file_list.md
```
; if missing, generate it with the expected input list template.
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.
If
```
/specs/background/original.md
```
exists, treat it as the current canonical requirement and use it as baseline for diff (inherit/new/change/deprecate).
Load
```
prompts/vspec_upgrade/upgrade.md
```
and generate/update artifacts under
```
/specs/
```
, reusing
```
/vspec:new
```
output conventions.
Sync extracted technical spec into
```
/scheme.yaml
```
so it can be used by
```
/vspec:verify
```
and
```
/vspec:impl
```
.

使用此命令基于

/docs/

目录下的材料（

/docs/legacy

用于遗留系统，

/docs/current

用于新输入）升级/改造需求，并按照

/vspec:new

的输出结构重新生成

/specs/

下的产物。

语言规则：

读取
```
/scheme.yaml
```
中的
```
selected.language
```
字段（支持
```
en
```
、
```
zh
```
、
```
ja
```
；若缺失或无效则默认使用
```
en
```
）。
重新生成的所有
```
/specs/**
```
产物必须统一使用所选语言。

流程：

确保输入入口文件
```
/docs/current/file_list.md
```
存在；若缺失，使用预期输入列表模板生成该文件。
读取
```
/docs/current/file_list.md
```
，然后按顺序读取
```
/docs/
```
下列出的源文件（通常为
```
/docs/legacy/*
```
、
```
/docs/current/*
```
，可选
```
/docs/templates/*
```
、
```
/docs/texts/*
```
、
```
/docs/assets/*
```
）并提取结构化信息（功能、依赖、UI风格、角色/权限、技术规格）。此外，必须递归扫描
```
/docs/legacy/
```
及其所有子目录，将这些文档视为原始输入材料（即使尚未明确列在
```
file_list.md
```
中）；若发现
```
file_list.md
```
中未列出的遗留文件，将其追加到
```
/docs/current/file_list.md
```
后再读取。
若
```
/specs/background/original.md
```
存在，则将其视为当前标准需求，作为差异对比的基线（继承/新增/修改/废弃）。
加载
```
prompts/vspec_upgrade/upgrade.md
```
生成/更新
```
/specs/
```
下的产物，复用
```
/vspec:new
```
的输出规范。
将提取的技术规格同步到
```
/scheme.yaml
```
，供
```
/vspec:verify
```
和
```
/vspec:impl
```
使用。

/vspec:plan

/vspec:plan

Use this command to break down requirements, estimate efforts, and schedule via a user story map.

Language:

Read
```
/scheme.yaml
```
```
selected.language
```
(supports
```
en
```
,
```
zh
```
,
```
ja
```
; default to
```
en
```
if missing/invalid).

Both

/specs/plan/plan_estimate.md

and

/specs/plan/plan_schedule.html

must use the selected language consistently.

Flow:

Read

/specs/functions/*

/specs/background/roles.md

/specs/background/scenarios.md

/specs/details/

/specs/background/dependencies.md

Load
```
prompts/vspec_plan/estimate.md
```
to generate estimates aligned to the function list.
Write estimates to
```
/specs/plan/plan_estimate.md
```
.
Load
```
prompts/vspec_plan/schedule.md
```
to generate the schedule and delivery map.
Write schedule HTML to
```
/specs/plan/plan_schedule.html
```
.

使用此命令拆解需求、估算工作量，并通过用户故事地图制定进度计划。

语言规则：

读取
```
/scheme.yaml
```
中的
```
selected.language
```
字段（支持
```
en
```
、
```
zh
```
、
```
ja
```
；若缺失或无效则默认使用
```
en
```
）。

/specs/plan/plan_estimate.md

和

/specs/plan/plan_schedule.html

必须统一使用所选语言。

流程：

读取

/specs/functions/*

、

/specs/background/roles.md

、

/specs/background/scenarios.md

、

/specs/details/

、

/specs/background/dependencies.md

。

加载
```
prompts/vspec_plan/estimate.md
```
生成与功能列表对齐的工作量估算。
将估算结果写入
```
/specs/plan/plan_estimate.md
```
。
加载
```
prompts/vspec_plan/schedule.md
```
生成进度计划和交付地图。
将进度计划HTML写入
```
/specs/plan/plan_schedule.html
```
。

/vspec:mrd

/vspec:mrd

Use this command to generate a market research and product positioning pack (MRD): market landscape, competitor analysis, user positioning, and product design notes.

Flow:

Ensure
```
/docs/market/
```
exists.

Read baseline artifacts when available:

/specs/background/original.md

/specs/background/roles.md

/specs/background/terms.md

/specs/background/scenarios.md

/specs/flows/*.puml

/specs/background/dependencies.md

, and

/specs/functions/*

(if any).

Load
```
prompts/vspec_mrd/mrd.md
```
.

Write outputs to:

```
/docs/market/market.md
```
```
/docs/market/competitors.md
```
```
/docs/market/users.md
```
```
/docs/market/product_design.md
```

使用此命令生成市场研究与产品定位包（MRD）：市场格局、竞品分析、用户定位、产品设计说明。

流程：

确保
```
/docs/market/
```
目录存在。

读取可用的基线产物：

/specs/background/original.md

、

/specs/background/roles.md

、

/specs/background/terms.md

、

/specs/background/scenarios.md

、

/specs/flows/*.puml

、

/specs/background/dependencies.md

，以及

/specs/functions/*

（若存在）。

加载
```
prompts/vspec_mrd/mrd.md
```
。

将输出写入以下文件：

```
/docs/market/market.md
```
```
/docs/market/competitors.md
```
```
/docs/market/users.md
```
```
/docs/market/product_design.md
```

Prompt Files

提示词文件

```
prompts/vspec_new/background.md
```
: the prompt used right after
```
/vspec:new
```
receives the raw requirement.

prompts/vspec_interview/interview.md

: the prompt used by

/vspec:interview

to generate

/docs/current/interview_questionnaire.md

prompts/vspec_interview/interview_word.md

: the prompt used by

/vspec:i-word

to generate

/docs/current/interview_questionnaire.docx

(Word-openable single-file HTML).

prompts/vspec_new/stakeholders.md

: the prompt used after the user answers

待确认问题

to generate

/specs/background/stakeholder.md

```
prompts/vspec_new/roles.md
```
: the prompt used after stakeholder analysis to generate
```
/specs/background/roles.md
```
.

prompts/vspec_new/terms.md

: the prompt used after roles analysis to generate

/specs/background/terms.md

```
prompts/vspec_new/flows.md
```
: the prompt used after terms analysis to generate
```
/specs/flows/*.puml
```
.

prompts/vspec_new/scenarios.md

: the prompt used after flows analysis to generate

/specs/background/scenarios.md

prompts/vspec_new/details_pre_post.md

: the prompt used after scenarios analysis to generate per-node

pre_post.md

under

/specs/background/scenario_details/

prompts/vspec_new/details_constraints.md

: the prompt used after Pre/Post to generate per-node

constraints.md

under

/specs/background/scenario_details/

prompts/vspec_new/details_variations.md

: the prompt used after Constraints to generate per-node

variations.md

under

/specs/background/scenario_details/

prompts/vspec_new/details_boundaries.md

: the prompt used after Variations to generate per-node

boundaries.md

under

/specs/background/scenario_details/

prompts/vspec_new/details_symmetry.md

: the prompt used after Boundaries to generate per-node

symmetry.md

under

/specs/background/scenario_details/

prompts/vspec_new/dependencies.md

: the prompt used after details analysis to generate

/specs/background/dependencies.md

```
prompts/vspec_new/functions.md
```
: the prompt used after dependencies analysis to generate
```
/specs/functions/
```
.

prompts/vspec_new/questions.md

: the prompt used after functions analysis to generate

/specs/background/questions.md

prompts/vspec_more_q/more_q.md

: the prompt used by

/vspec:more-q

to append more questions to

/specs/background/questions.md

```
prompts/vspec_mrd/mrd.md
```
: the prompt used by
```
/vspec:mrd
```
to generate market/user/competitor/product docs under
```
/docs/market/
```
.
```
prompts/vspec_refine/refine.md
```
: the prompt used by
```
/vspec:refine
```
to refine the requirement based on
```
refine.md
```
.
```
prompts/vspec_refine/refine_q.md
```
: the prompt used by
```
/vspec:refine-q
```
to refine the requirement based on answered questions.
```
prompts/vspec_doc/doc.md
```
: the prompt used by
```
/vspec:doc
```
to generate a Word-openable
```
.docx
```
(HTML) requirement detail document under
```
/docs/current/
```
.

prompts/vspec_verify/model.md

: the prompt used by

/vspec:verify

to generate

/specs/models/*.md

```
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
```
).
```
prompts/vspec_verify/validation.md
```
: the prompt used by
```
/vspec:verify
```
to generate the validation web page with a
```
scenario.html
```
entry.
```
prompts/vspec_detail/rbac.md
```
: the prompt used by
```
/vspec:detail
```
to generate RBAC detail docs.
```
prompts/vspec_detail/data_permission.md
```
: the prompt used by
```
/vspec:detail
```
to generate data permission detail docs.
```
prompts/vspec_detail/page_load.md
```
: the prompt used by
```
/vspec:detail
```
to generate page loading logic docs.
```
prompts/vspec_detail/interaction.md
```
: the prompt used by
```
/vspec:detail
```
to generate page interaction logic docs.
```
prompts/vspec_detail/index.md
```
: the prompt used by
```
/vspec:detail
```
to generate
```
/specs/details/reader.html
```
as a markdown/PlantUML-rendered viewer.
```
prompts/vspec_detail/index.html
```
: the fixed HTML template used by
```
/vspec:detail
```
to stabilize
```
/specs/details/reader.html
```
generation (directory tree + markdown renderer).
```
prompts/vspec_detail/timeline.md
```
: the prompt used by
```
/vspec:detail
```
to generate time-axis HTML docs.
```
prompts/vspec_detail/formula.md
```
: the prompt used by
```
/vspec:detail
```
to generate formula docs.
```
prompts/vspec_detail/expression_tree.md
```
: the prompt used by
```
/vspec:detail
```
to generate expression tree docs.
```
prompts/vspec_detail/code_rules.md
```
: the prompt used by
```
/vspec:detail
```
to generate numbering/code rules docs.

prompts/vspec_detail/judgemental_matrix.md

: the prompt used by

/vspec:detail

to generate decision matrix docs.

```
prompts/vspec_detail/validation_matrix.md
```
: the prompt used by
```
/vspec:detail
```
to generate validation matrix docs.
```
prompts/vspec_detail/post_submit_check.md
```
: the prompt used by
```
/vspec:detail
```
to generate post-submit checks docs.
```
prompts/vspec_detail/post_submit_processing.md
```
: the prompt used by
```
/vspec:detail
```
to generate post-submit processing docs.
```
prompts/vspec_detail/post_submit_navigation.md
```
: the prompt used by
```
/vspec:detail
```
to generate post-submit navigation docs.
```
prompts/vspec_detail/mq.md
```
: the prompt used by
```
/vspec:detail
```
to generate MQ message design docs.
```
prompts/vspec_detail/message_queue.md
```
: the prompt used by
```
/vspec:detail
```
to generate message queue design docs.
```
prompts/vspec_detail/cache.md
```
: the prompt used by
```
/vspec:detail
```
to generate cache design docs.
```
prompts/vspec_detail/service_logic.md
```
: the prompt used by
```
/vspec:detail
```
to generate backend service logic docs for
```
Backend
```
steps.
```
prompts/vspec_detail/job_logic.md
```
: the prompt used by
```
/vspec:detail
```
to generate job logic docs for
```
Job
```
steps.
```
prompts/vspec_detail/logging_matrix.md
```
: the prompt used by
```
/vspec:detail
```
to generate logging matrix docs.
```
prompts/vspec_detail/notification_matrix.md
```
: the prompt used by
```
/vspec:detail
```
to generate notification matrix docs.
```
prompts/vspec_detail/nfp.md
```
: the prompt used by
```
/vspec:detail
```
to generate non-functional requirements docs.
```
prompts/vspec_detail/file_import.md
```
: the prompt used by
```
/vspec:detail
```
to generate file import docs.
```
prompts/vspec_detail/file_export.md
```
: the prompt used by
```
/vspec:detail
```
to generate file export docs.
```
prompts/vspec_detail/cron_job.md
```
: the prompt used by
```
/vspec:detail
```
to generate scheduled job docs.
```
prompts/vspec_accept/accept.md
```
: the prompt used by
```
/vspec:accept
```
to generate acceptance test cases.
```
prompts/vspec_test/test.md
```
: the prompt used by
```
/vspec:append-test
```
to generate automation test code.
```
prompts/vspec_impl/implement.md
```
: the prompt used by
```
/vspec:impl
```
to generate integrated frontend/backend code.
```
prompts/vspec_upgrade/upgrade.md
```
: the prompt used by
```
/vspec:upgrade
```
to generate upgraded specs from
```
/docs/
```
inputs.

prompts/vspec_plan/estimate.md

: the prompt used by

/vspec:plan

to generate

/specs/plan/plan_estimate.md

prompts/vspec_plan/schedule.md

: the prompt used by

/vspec:plan

to generate

/specs/plan/plan_schedule.html

prompts/vspec_qc/qc.md

: the prompt used by

/vspec:qc

to generate

/specs/qc_report.md

prompts/vspec_qc/quality_standard.md

: built-in quality standard used by

/vspec:qc

```
prompts/vspec_new/background.md
```
：
```
/vspec:new
```
收到原始需求后立即使用的提示词文件。

prompts/vspec_interview/interview.md

：

/vspec:interview

用于生成

/docs/current/interview_questionnaire.md

的提示词文件。

prompts/vspec_interview/interview_word.md

：

/vspec:i-word

用于生成

/docs/current/interview_questionnaire.docx

（可在Word中打开的单文件HTML）的提示词文件。

```
prompts/vspec_new/stakeholders.md
```
：用户回答“待确认问题”后，用于生成
```
/specs/background/stakeholder.md
```
的提示词文件。
```
prompts/vspec_new/roles.md
```
：利益相关方分析完成后，用于生成
```
/specs/background/roles.md
```
的提示词文件。
```
prompts/vspec_new/terms.md
```
：角色分析完成后，用于生成
```
/specs/background/terms.md
```
的提示词文件。
```
prompts/vspec_new/flows.md
```
：术语分析完成后，用于生成
```
/specs/flows/*.puml
```
的提示词文件。

prompts/vspec_new/scenarios.md

：流程分析完成后，用于生成

/specs/background/scenarios.md

的提示词文件。

prompts/vspec_new/details_pre_post.md

：场景分析完成后，用于在

/specs/background/scenario_details/

下生成每个节点的

pre_post.md

的提示词文件。

```
prompts/vspec_new/details_constraints.md
```
：前置/后置条件分析完成后，用于在
```
/specs/background/scenario_details/
```
下生成每个节点的
```
constraints.md
```
的提示词文件。

prompts/vspec_new/details_variations.md

：约束条件分析完成后，用于在

/specs/background/scenario_details/

下生成每个节点的

variations.md

的提示词文件。

prompts/vspec_new/details_boundaries.md

：变体分析完成后，用于在

/specs/background/scenario_details/

下生成每个节点的

boundaries.md

的提示词文件。

prompts/vspec_new/details_symmetry.md

：边界分析完成后，用于在

/specs/background/scenario_details/

下生成每个节点的

symmetry.md

的提示词文件。

prompts/vspec_new/dependencies.md

：细节分析完成后，用于生成

/specs/background/dependencies.md

的提示词文件。

```
prompts/vspec_new/functions.md
```
：依赖分析完成后，用于生成
```
/specs/functions/
```
下内容的提示词文件。

prompts/vspec_new/questions.md

：功能分析完成后，用于生成

/specs/background/questions.md

的提示词文件。

prompts/vspec_more_q/more_q.md

：

/vspec:more-q

用于向

/specs/background/questions.md

追加更多问题的提示词文件。

```
prompts/vspec_mrd/mrd.md
```
：
```
/vspec:mrd
```
用于在
```
/docs/market/
```
下生成市场/用户/竞品/产品文档的提示词文件。

prompts/vspec_refine/refine.md

：

/vspec:refine

用于基于

refine.md

优化需求的提示词文件。

```
prompts/vspec_refine/refine_q.md
```
：
```
/vspec:refine-q
```
用于基于已回答问题优化需求的提示词文件。
```
prompts/vspec_doc/doc.md
```
：
```
/vspec:doc
```
用于在
```
/docs/current/
```
下生成可在Word中打开的
```
.docx
```
（HTML格式）需求细节文档的提示词文件。

prompts/vspec_verify/model.md

：

/vspec:verify

用于生成

/specs/models/*.md

的提示词文件。

```
prompts/vspec_verify/prototype.md
```
：
```
/vspec:verify
```
用于在
```
/specs/prototypes/
```
下生成符合技术栈要求的可运行原型的提示词文件（必须遵循
```
scheme.yaml
```
）。

prompts/vspec_verify/validation.md

：

/vspec:verify

用于生成带

scenario.html

入口的验证网页的提示词文件。

```
prompts/vspec_detail/rbac.md
```
：
```
/vspec:detail
```
用于生成RBAC细节文档的提示词文件。
```
prompts/vspec_detail/data_permission.md
```
：
```
/vspec:detail
```
用于生成数据权限细节文档的提示词文件。
```
prompts/vspec_detail/page_load.md
```
：
```
/vspec:detail
```
用于生成页面加载逻辑文档的提示词文件。
```
prompts/vspec_detail/interaction.md
```
：
```
/vspec:detail
```
用于生成页面交互逻辑文档的提示词文件。
```
prompts/vspec_detail/index.md
```
：
```
/vspec:detail
```
用于生成
```
/specs/details/reader.html
```
（markdown/PlantUML渲染查看器）的提示词文件。
```
prompts/vspec_detail/index.html
```
：
```
/vspec:detail
```
用于稳定
```
/specs/details/reader.html
```
生成的固定HTML模板（目录树+markdown渲染器）。
```
prompts/vspec_detail/timeline.md
```
：
```
/vspec:detail
```
用于生成时间轴HTML文档的提示词文件。
```
prompts/vspec_detail/formula.md
```
：
```
/vspec:detail
```
用于生成公式文档的提示词文件。
```
prompts/vspec_detail/expression_tree.md
```
：
```
/vspec:detail
```
用于生成表达式树文档的提示词文件。
```
prompts/vspec_detail/code_rules.md
```
：
```
/vspec:detail
```
用于生成编号/代码规则文档的提示词文件。

prompts/vspec_detail/judgemental_matrix.md

：

/vspec:detail

用于生成决策矩阵文档的提示词文件。

prompts/vspec_detail/validation_matrix.md

：

/vspec:detail

用于生成验证矩阵文档的提示词文件。

```
prompts/vspec_detail/post_submit_check.md
```
：
```
/vspec:detail
```
用于生成提交后检查文档的提示词文件。

prompts/vspec_detail/post_submit_processing.md

：

/vspec:detail

用于生成提交后处理文档的提示词文件。

prompts/vspec_detail/post_submit_navigation.md

：

/vspec:detail

用于生成提交后导航文档的提示词文件。

```
prompts/vspec_detail/mq.md
```
：
```
/vspec:detail
```
用于生成MQ消息设计文档的提示词文件。
```
prompts/vspec_detail/message_queue.md
```
：
```
/vspec:detail
```
用于生成消息队列设计文档的提示词文件。
```
prompts/vspec_detail/cache.md
```
：
```
/vspec:detail
```
用于生成缓存设计文档的提示词文件。
```
prompts/vspec_detail/service_logic.md
```
：
```
/vspec:detail
```
用于为
```
Backend
```
步骤生成后端服务逻辑文档的提示词文件。
```
prompts/vspec_detail/job_logic.md
```
：
```
/vspec:detail
```
用于为
```
Job
```
步骤生成任务逻辑文档的提示词文件。
```
prompts/vspec_detail/logging_matrix.md
```
：
```
/vspec:detail
```
用于生成日志矩阵文档的提示词文件。

prompts/vspec_detail/notification_matrix.md

：

/vspec:detail

用于生成通知矩阵文档的提示词文件。

```
prompts/vspec_detail/nfp.md
```
：
```
/vspec:detail
```
用于生成非功能性需求文档的提示词文件。
```
prompts/vspec_detail/file_import.md
```
：
```
/vspec:detail
```
用于生成文件导入文档的提示词文件。
```
prompts/vspec_detail/file_export.md
```
：
```
/vspec:detail
```
用于生成文件导出文档的提示词文件。
```
prompts/vspec_detail/cron_job.md
```
：
```
/vspec:detail
```
用于生成定时任务文档的提示词文件。
```
prompts/vspec_accept/accept.md
```
：
```
/vspec:accept
```
用于生成验收测试用例的提示词文件。
```
prompts/vspec_test/test.md
```
：
```
/vspec:append-test
```
用于生成自动化测试代码的提示词文件。
```
prompts/vspec_impl/implement.md
```
：
```
/vspec:impl
```
用于生成集成前端/后端代码的提示词文件。
```
prompts/vspec_upgrade/upgrade.md
```
：
```
/vspec:upgrade
```
用于基于
```
/docs/
```
输入生成升级后规格文档的提示词文件。

prompts/vspec_plan/estimate.md

：

/vspec:plan

用于生成

/specs/plan/plan_estimate.md

的提示词文件。

prompts/vspec_plan/schedule.md

：

/vspec:plan

用于生成

/specs/plan/plan_schedule.html

的提示词文件。

prompts/vspec_qc/qc.md

：

/vspec:qc

用于生成

/specs/qc_report.md

的提示词文件。

prompts/vspec_qc/quality_standard.md

：

/vspec:qc

使用的内置质量标准文件。

Suggested Workflow

建议工作流程

Install this skill.
Run
```
/vspec:new
```
.
Ask the user to input the original requirement and wait for Enter.
Load
```
prompts/vspec_new/background.md
```
and start requirement analysis.
Ask the user to answer
```
待确认问题
```
.

Load

prompts/vspec_new/stakeholders.md

and generate

/specs/background/stakeholder.md

Load

prompts/vspec_new/roles.md

and generate

/specs/background/roles.md

Load

prompts/vspec_new/terms.md

and generate

/specs/background/terms.md

Load

prompts/vspec_new/flows.md

and generate

/specs/flows/*.puml

Load

prompts/vspec_new/scenarios.md

and generate

/specs/background/scenarios.md

Load

prompts/vspec_new/details_pre_post.md

and generate per-node

pre_post.md

under

/specs/background/scenario_details/

Load

prompts/vspec_new/details_constraints.md

and generate per-node

constraints.md

under

/specs/background/scenario_details/

Load

prompts/vspec_new/details_variations.md

and generate per-node

variations.md

under

/specs/background/scenario_details/

Load

prompts/vspec_new/details_boundaries.md

and generate per-node

boundaries.md

under

/specs/background/scenario_details/

Load

prompts/vspec_new/details_symmetry.md

and generate per-node

symmetry.md

under

/specs/background/scenario_details/

Load

prompts/vspec_new/dependencies.md

and generate

/specs/background/dependencies.md

Load

prompts/vspec_new/functions.md

and generate

/specs/functions/

Load

prompts/vspec_new/questions.md

and generate

/specs/background/questions.md

Follow the generated analysis steps to continue the project.

安装此技能。
运行
```
/vspec:new
```
。
请用户输入原始需求并等待回车键。
加载
```
prompts/vspec_new/background.md
```
开始需求分析。
请用户回答“待确认问题”。

加载

prompts/vspec_new/stakeholders.md

生成

/specs/background/stakeholder.md

。

加载

prompts/vspec_new/roles.md

生成

/specs/background/roles.md

。

加载

prompts/vspec_new/terms.md

生成

/specs/background/terms.md

。

加载

prompts/vspec_new/flows.md

生成

/specs/flows/*.puml

。

加载

prompts/vspec_new/scenarios.md

生成

/specs/background/scenarios.md

。

加载

prompts/vspec_new/details_pre_post.md

在

/specs/background/scenario_details/

下生成每个节点的

pre_post.md

。

加载

prompts/vspec_new/details_constraints.md

在

/specs/background/scenario_details/

下生成每个节点的

constraints.md

。

加载

prompts/vspec_new/details_variations.md

在

/specs/background/scenario_details/

下生成每个节点的

variations.md

。

加载

prompts/vspec_new/details_boundaries.md

在

/specs/background/scenario_details/

下生成每个节点的

boundaries.md

。

加载

prompts/vspec_new/details_symmetry.md

在

/specs/background/scenario_details/

下生成每个节点的

symmetry.md

。

加载

prompts/vspec_new/dependencies.md

生成

/specs/background/dependencies.md

。

加载

prompts/vspec_new/functions.md

生成

/specs/functions/

下的内容。

加载

prompts/vspec_new/questions.md

生成

/specs/background/questions.md

。

按照生成的分析步骤继续推进项目。

Output Goal

输出目标

Clarify business objective and core user scenario.
Identify key roles, page modules, and interaction flow.
Extract entities and main data fields.
Produce a visual-spec-oriented requirement draft for the next step.

明确业务目标和核心用户场景。
识别关键角色、页面模块和交互流程。
提取实体和主要数据字段。
生成面向视觉规格的需求草稿，供下一步使用。