blueprint-prp-execute

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/blueprint:prp-execute

Execute a PRP (Product Requirement Prompt) with systematic implementation, validation gates, TDD workflow, and quality assurance.

Usage:

/blueprint:prp-execute [prp-name]

Prerequisites:

PRP exists in
```
docs/prps/[prp-name].md
```
Confidence score >= 7 (if lower, suggest
```
/blueprint:prp-create
```
refinement)

For detailed report templates, deferred items workflow, feature tracker sync, and error handling patterns, see REFERENCE.md.

执行PRP（Product Requirement Prompt，产品需求提示），包含系统化实现、验证关卡、TDD工作流和质量保证。

用法：

/blueprint:prp-execute [prp-name]

前提条件：

PRP已存在于
```
docs/prps/[prp-name].md
```
置信度评分 >=7（若低于该值，建议使用
```
/blueprint:prp-create
```
进行优化）

关于详细的报告模板、延期项工作流、功能跟踪器同步和错误处理模式，请查看REFERENCE.md。

When to Use This Skill

何时使用该技能

Use this skill when...	Use alternative when...
Ready to implement a planned feature from a PRP	PRP is not yet ready (confidence < 7)
Want to execute with full validation and TDD workflow	Implementing ad-hoc features without documentation
Need feature tracker and GitHub issue tracking	Working on isolated bug fixes
Want automatic progress reporting and deferred items tracking	Quick prototyping without formal tracking

适合使用本技能的场景...	适合使用替代方案的场景...
准备从PRP实现已规划的功能	PRP尚未就绪（置信度 <7）
希望通过完整的验证和TDD工作流执行	实现无文档记录的临时功能
需要功能跟踪器和GitHub问题跟踪	处理孤立的Bug修复
希望自动跟踪进度和延期项	无需正式跟踪的快速原型开发

Context

上下文

PRP file path: !

find . -maxdepth 1 -name \'docs/prps/${1:-unknown}.md\' 2>/dev/null

PRP confidence score: !

grep -m1 "^confidence:" docs/prps/${1:-unknown}.md 2>/dev/null

Feature tracker enabled: !

test -f docs/blueprint/feature-tracker.json 2>/dev/null

Current branch: !

git rev-parse --abbrev-ref HEAD 2>/dev/null

Uncommitted changes: !
```
git status --porcelain 2>/dev/null
```

PRP文件路径：!

find . -maxdepth 1 -name \'docs/prps/${1:-unknown}.md\' 2>/dev/null

PRP置信度评分：!

grep -m1 "^confidence:" docs/prps/${1:-unknown}.md 2>/dev/null

功能跟踪器已启用：!

test -f docs/blueprint/feature-tracker.json 2>/dev/null

当前分支：!

git rev-parse --abbrev-ref HEAD 2>/dev/null

未提交的更改：!
```
git status --porcelain 2>/dev/null
```

Parameters

参数解析

Parse

$ARGUMENTS

```
prp-name
```
(required): Name of PRP file in
```
docs/prps/
```
(without .md extension)
- Example:
```
feature-auth-oauth2
```
  → loads
```
docs/prps/feature-auth-oauth2.md
```

解析

$ARGUMENTS

：

```
prp-name
```
（必填）：
```
docs/prps/
```
目录下PRP文件的名称（不含.md扩展名）
- 示例：
```
feature-auth-oauth2
```
  → 加载
```
docs/prps/feature-auth-oauth2.md
```

Execution

执行流程

Execute the complete PRP implementation workflow:

执行完整的PRP实现工作流：

Step 1: Load and validate PRP

步骤1：加载并验证PRP

Read PRP file:
```
docs/prps/{prp-name}.md
```
Extract confidence score from frontmatter
If confidence < 7 → Error: "PRP confidence too low. Run
```
/blueprint:prp-create {prp-name}
```
to refine"
If confidence >= 9 → Offer delegation: "This PRP has high confidence. Execute now (current session) or create work-order for delegation?"
- If work-order chosen → Run
```
/blueprint:work-order --from-prp {prp-name}
```
  and exit
- If delegation to multiple subagents chosen → Create focused work-orders per module from Implementation Blueprint and exit
Continue to Step 2 if executing now OR confidence 7-8
Load all referenced ai_docs entries for context
Parse Implementation Blueprint and create TodoWrite entries ordered by dependencies

读取PRP文件：
```
docs/prps/{prp-name}.md
```
从前置元数据中提取置信度评分
若置信度 <7 → 错误提示："PRP置信度过低。请运行
```
/blueprint:prp-create {prp-name}
```
进行优化"
若置信度 >=9 → 提供委托选项："该PRP置信度较高。立即执行（当前会话）还是创建工单进行委托？"
- 若选择工单 → 运行
```
/blueprint:work-order --from-prp {prp-name}
```
  并退出
- 若选择委托给多个子Agent → 根据实现蓝图为每个模块创建针对性工单并退出
若选择立即执行，或置信度为7-8，则继续步骤2
加载所有相关的ai_docs条目以获取上下文
解析实现蓝图并按依赖顺序创建TodoWrite条目

Step 2: Establish baseline with validation gates

步骤2：通过验证关卡建立基线

Run pre-implementation validation gates (see REFERENCE.md) to establish clean starting state:

Linting gate:
```
[command from PRP]
```
- Expected: PASS
Existing tests gate:
```
[command from PRP]
```
- Expected: PASS

If gates fail:

Document existing issues
Decide: fix first or proceed with note
Continue when ready

运行实现前的验证关卡（参见REFERENCE.md）以建立干净的起始状态：

代码检查关卡：
```
[PRP中指定的命令]
```
- 预期结果：通过
现有测试关卡：
```
[PRP中指定的命令]
```
- 预期结果：通过

若关卡未通过：

记录现有问题
决策：先修复问题还是附带说明继续执行
准备就绪后继续

Step 3: Execute TDD implementation cycle

步骤3：执行TDD实现周期

For each task in Implementation Blueprint:

RED phase: Write failing test matching PRP TDD Requirements
- Create test file if needed
- Run tests → Confirm FAILURE (test is meaningful)
GREEN phase: Implement minimal code to pass test
- Follow Codebase Intelligence patterns from PRP
- Apply patterns from ai_docs references
- Watch for Known Gotchas
- Run tests → Confirm SUCCESS
REFACTOR phase: Improve code while keeping tests green
- Extract common patterns
- Improve naming, add type hints
- Follow project conventions
- Run tests → Confirm PASS
- Run validation gates frequently (not just at end)
Mark progress: Update TodoWrite:
```
✅ Task N: [Description]
```

针对实现蓝图中的每个任务：

RED阶段：编写符合PRP中TDD要求的失败测试
- 若需要则创建测试文件
- 运行测试 → 确认失败（确保测试有实际意义）
GREEN阶段：实现最小化代码以通过测试
- 遵循PRP中的代码库智能模式
- 应用ai_docs引用中的模式
- 注意已知陷阱（Known Gotchas）
- 运行测试 → 确认成功
REFACTOR阶段：在保持测试通过的同时优化代码
- 提取通用模式
- 优化命名、添加类型提示
- 遵循项目规范
- 运行测试 → 确认通过
- 频繁运行验证关卡（而非仅在最后执行）
标记进度：更新TodoWrite：
```
✅ 任务N：[描述]
```

Step 4: Run comprehensive final validation

步骤4：运行全面的最终验证

Execute all validation gates from PRP (see REFERENCE.md):

Linting:
```
[cmd]
```
- Expected: PASS
Type checking:
```
[cmd]
```
- Expected: PASS
Unit tests:
```
[cmd]
```
- Expected: PASS (all tests)
Integration tests:
```
[cmd]
```
- Expected: PASS (if applicable)
Coverage check:
```
[cmd]
```
- Expected: Meets threshold
Security scan:
```
[cmd]
```
- Expected: No high/critical issues (if applicable)
Performance tests:
```
[cmd]
```
- Expected: Meets baseline (if defined)

Verify each success criterion from PRP.

执行PRP中所有的验证关卡（参见REFERENCE.md）：

代码检查：
```
[命令]
```
- 预期结果：通过
类型检查：
```
[命令]
```
- 预期结果：通过
单元测试：
```
[命令]
```
- 预期结果：通过（所有测试）
集成测试：
```
[命令]
```
- 预期结果：通过（若适用）
覆盖率检查：
```
[命令]
```
- 预期结果：达到阈值
安全扫描：
```
[命令]
```
- 预期结果：无高/严重问题（若适用）
性能测试：
```
[命令]
```
- 预期结果：符合基线（若已定义）

验证PRP中的所有成功标准。

Step 5: Document deferred items

步骤5：记录延期项

Identify and track any deferred work:

Review Implementation Blueprint - items not completed
Categorize each deferred item:
- Phase 2 (Required): Must have GitHub issues created
- Nice-to-Have: Optional, no issue required
- Blocked: Cannot complete - document blocker, create issue
Create GitHub issues for all Phase 2 and Blocked items (see REFERENCE.md)
Update PRP with deferred items section linking to GitHub issues
Do NOT proceed to Step 6 until all required issues are created

识别并跟踪所有延期工作：

审查实现蓝图 - 未完成的项
对每个延期项进行分类：
- 第二阶段（必填）：必须创建GitHub问题
- 锦上添花项：可选，无需创建问题
- 受阻项：无法完成 - 记录阻塞原因，创建问题
为所有第二阶段和受阻项创建GitHub问题（参见REFERENCE.md）
更新PRP，添加链接到GitHub问题的延期项部分
在所有必填问题创建完成前，不得进入步骤6

Step 6: Sync feature tracker (if enabled)

步骤6：同步功能跟踪器（若已启用）

If feature tracker exists (

docs/blueprint/feature-tracker.json

Identify which feature codes (e.g., FR2.1) were addressed from PRP
Update feature tracker for each code:
- Status:
```
complete
```
  (all criteria met) or
```
partial
```
  (some criteria met) or
```
in_progress
```
- Files: List of modified/created files
- Tests: List of test files
- Commits: Commit hashes
- Notes: Implementation notes
Recalculate statistics: completion percentages, phase status
Update TODO.md: Check boxes for completed features
Report feature tracker changes

若功能跟踪器存在（

docs/blueprint/feature-tracker.json

）：

识别PRP中涉及的功能代码（例如FR2.1）
为每个代码更新功能跟踪器：
- 状态：
```
complete
```
  （所有标准已满足）或
```
partial
```
  （部分标准已满足）或
```
in_progress
```
- 文件：已修改/创建的文件列表
- 测试：测试文件列表
- 提交：提交哈希值
- 备注：实现说明
重新计算统计数据：完成百分比、阶段状态
更新TODO.md：勾选已完成的功能
报告功能跟踪器的变更

Step 7: Report results and next steps

步骤7：报告结果和下一步行动

Generate comprehensive execution summary report:

Tasks completed: X/Y
Tests added: N
Files modified: [list]
Validation results: Table of all gates (PASS/FAIL status)
Success criteria: All verified
Deferred items summary: Count and GitHub issue numbers
Feature tracker updates: Features updated and percentages
New gotchas discovered: [documented for future reference]
Recommendations: Follow-up work or ai_docs updates

Prompt user for next action:

Commit changes (Recommended) → Run
```
/git:commit
```
Create work-order for follow-up → Run
```
/blueprint:work-order
```
Update ai_docs with patterns → Run
```
/blueprint:curate-docs
```
Continue to next PRP → Run
```
/blueprint:prp-execute [next]
```
Done for now → Exit

生成全面的执行总结报告：

已完成任务：X/Y
新增测试：N
已修改文件：[列表]
验证结果：所有关卡的状态表（通过/未通过）
成功标准：全部已验证
延期项摘要：数量及GitHub问题编号
功能跟踪器更新：已更新的功能及百分比
新发现的陷阱：[记录以供未来参考]
建议：后续工作或ai_docs更新

提示用户选择下一步行动：

提交更改（推荐）→ 运行
```
/git:commit
```
创建后续工单 → 运行
```
/blueprint:work-order
```
更新ai_docs中的模式 → 运行
```
/blueprint:curate-docs
```
继续执行下一个PRP → 运行
```
/blueprint:prp-execute [next]
```
暂时结束 → 退出

Agentic Optimizations

Agent优化

Context	Command
Check PRP exists	`test -f docs/prps/${1}.md && echo "EXISTS" \|\| echo "MISSING"`
Extract confidence	`head -50 docs/prps/${1}.md \| grep -m1 "^confidence:" \| sed 's/^[^:]:[[:space:]]//'`
List all PRPs	`ls docs/prps/*.md 2>/dev/null \| xargs basename -s .md`
Check feature tracker	`test -f docs/blueprint/feature-tracker.json && echo "YES" \|\| echo "NO"`
Fast validation	Run validation gates in parallel when possible

For detailed validation gate definitions, deferred items workflow, error handling procedures, and agent team coordination, see REFERENCE.md.

上下文	命令
检查PRP是否存在	`test -f docs/prps/${1}.md && echo "EXISTS" \|\| echo "MISSING"`
提取置信度	`head -50 docs/prps/${1}.md \| grep -m1 "^confidence:" \| sed 's/^[^:]:[[:space:]]//'`
列出所有PRP	`ls docs/prps/*.md 2>/dev/null \| xargs basename -s .md`
检查功能跟踪器	`test -f docs/blueprint/feature-tracker.json && echo "YES" \|\| echo "NO"`
快速验证	尽可能并行运行验证关卡

关于详细的验证关卡定义、延期项工作流、错误处理流程和Agent团队协作，请查看REFERENCE.md。