build-feature

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

LIBRARY-FIRST PROTOCOL (MANDATORY)

库优先协议（强制性）

Before writing ANY code, you MUST check:

在编写任何代码之前，你必须检查：

Step 1: Library Catalog

步骤1：库目录

Location:
```
.claude/library/catalog.json
```
If match >70%: REUSE or ADAPT

位置：
```
.claude/library/catalog.json
```
如果匹配度>70%：复用或适配

Step 2: Patterns Guide

步骤2：模式指南

Location:

.claude/docs/inventories/LIBRARY-PATTERNS-GUIDE.md

If pattern exists: FOLLOW documented approach

位置：

.claude/docs/inventories/LIBRARY-PATTERNS-GUIDE.md

如果模式已存在：遵循文档记录的方法

Step 3: Existing Projects

步骤3：现有项目

Location:
```
D:\Projects\*
```
If found: EXTRACT and adapt

位置：
```
D:\Projects\*
```
如果找到：提取并适配

Decision Matrix

决策矩阵

Match	Action
Library >90%	REUSE directly
Library 70-90%	ADAPT minimally
Pattern exists	FOLLOW pattern
In project	EXTRACT
No match	BUILD (add to library after)

匹配度	操作
库匹配>90%	直接复用
库匹配70-90%	最小化适配
模式已存在	遵循模式
存在于项目中	提取
无匹配	构建（之后添加到库中）

STANDARD OPERATING PROCEDURE

标准操作流程

Purpose

目的

Primary action: Build feature command

主要操作：构建功能命令

Trigger Conditions

触发条件

Command syntax: /build-feature [args]
Ensure prerequisites are met before execution.

命令语法：/build-feature [参数]
执行前确保满足先决条件。

Inputs and Options

输入和选项

Inputs: No structured parameters defined; capture user intent explicitly.

输入：未定义结构化参数；需明确捕获用户意图。

Execution Phases

执行阶段

Review the request and confirm scope.
Execute the command flow.
Summarize outcomes and next actions.

审查请求并确认范围。
执行命令流程。
总结结果和后续操作。

Success Criteria and Outputs

成功标准和输出

Document artifacts, decisions, and follow-up actions clearly.

清晰记录工件、决策和后续操作。

Error Handling and Recovery

错误处理与恢复

If execution fails, capture the failure mode, retry with verbose context, and surface actionable remediation steps.

如果执行失败，捕获失败模式，结合详细上下文重试，并提供可操作的补救步骤。

Chaining and Coordination

链式调用与协调

Memory and Tagging

记忆与标记

Tag session outputs with who/when/why for traceability.

为会话输出标记执行人/时间/原因，以便追溯。

LEARNED PATTERNS (Session: 2026-01-07)

已学习模式（会话：2026-01-07）

Asset Selection Protocol

资产选择协议

When multiple similar assets exist (e.g., headshot.jpg vs headshot.png):

List all candidates with visual inspection or metadata check
Confirm correct asset with user before implementation
Document reasoning for selection

当存在多个相似资产时（例如：headshot.jpg vs headshot.png）：

通过视觉检查或元数据检查列出所有候选资产
实施前与用户确认正确的资产
记录选择理由

Feature Restoration vs New Feature

功能恢复 vs 新功能

For "restore", "add back", or "bring back" requests:

FIRST: Research git history to find original implementation

bash

git log --all --oneline -- <file>
git show <commit>:<file>

Extract working implementation patterns from historical commits
Apply proven patterns to current codebase
AVOID: Reinventing solutions that previously worked

For NEW features:

Check if similar patterns exist in codebase
Follow established conventions (grid layouts, component structure)
Iterate with user feedback

对于“恢复”、“添加回去”或“带回”请求：

首先：研究git历史以找到原始实现

bash

git log --all --oneline -- <file>
git show <commit>:<file>

从历史提交中提取可行的实现模式
将经过验证的模式应用到当前代码库
避免：重新发明之前已可行的解决方案

对于新功能：

检查代码库中是否存在类似模式
遵循已确立的约定（网格布局、组件结构）
结合用户反馈迭代

Layout Implementation Strategy

布局实施策略

Hero sections with text + image -> Grid-based layout (lg:grid-cols-12)
Card layouts -> Consistent spacing and responsive breakpoints
If >3 positioning iterations needed -> STOP and research existing patterns or ask for design reference

包含文本+图片的Hero区域 -> 基于网格的布局（lg:grid-cols-12）
卡片布局 -> 一致的间距和响应式断点
如果需要超过3次定位迭代 -> 停止并研究现有模式或请求设计参考

User Frustration Signals

用户沮丧信号

Phrases like "this is getting sad", "stop", "reverse all changes" indicate:

Trigger: Immediate rollback + strategy pivot required
Response: Research historical solutions or ask for design reference
Never continue iterating after frustration signals

类似“这太糟糕了”、“停止”、“撤销所有更改”的表述表明：

触发：需要立即回滚+策略调整
响应：研究历史解决方案或请求设计参考
收到沮丧信号后绝不能继续迭代

Example Invocation

示例调用

/build-feature example

/build-feature example

Output Format

输出格式

Provide a concise summary, actions taken, artifacts generated, and recommended next steps.
Always include an explicit confidence line: "Confidence: X.XX (ceiling: TYPE Y.YY)".
Use ceilings — inference/report: 0.70, research: 0.85, observation: 0.95, definition: 0.95.
Keep user-facing output in plain English; reserve VCL markers for the appendix only.

Confidence: 0.86 (ceiling: observation 0.95) - SOP rewritten to Prompt-Architect pattern based on legacy command content.

提供简洁的总结、已执行的操作、生成的工件以及推荐的后续步骤。
始终包含明确的置信度行：“Confidence: X.XX (ceiling: TYPE Y.YY)”。
使用置信度上限——推理/报告：0.70，研究：0.85，观察：0.95，定义：0.95。
用户可见输出使用简洁英语；仅在附录中保留VCL标记。

Confidence: 0.86 (ceiling: observation 0.95) - SOP已基于旧版命令内容重写为Prompt-Architect模式。

VCL COMPLIANCE APPENDIX (Internal Reference)

VCL合规附录（内部参考）

[[HON:teineigo]] [[MOR:root:PA]] [[COM:PromptArchitect]] [[CLS:ge_command]] [[EVD:-DI<gozlem>]] [[ASP:nesov.]] [[SPC:path:/commands]] [define|neutral] CONFIDENCE_CEILINGS := {inference:0.70, report:0.70, research:0.85, observation:0.95, definition:0.95} [conf:0.9] [state:confirmed] [direct|emphatic] L2_LANGUAGE := English; user-facing outputs exclude VCL markers. [conf:0.99] [state:confirmed] [commit|confident] <promise>BUILD_FEATURE_VERILINGUA_VERIX_COMPLIANT</promise> [conf:0.88] [state:confirmed]