create-meta-prompts

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

<objective> Create prompts optimized for Claude-to-Claude communication in multi-stage workflows. Outputs are structured with XML and metadata for efficient parsing by subsequent prompts.

Every execution produces a

SUMMARY.md

for quick human scanning without reading full outputs.

Each prompt gets its own folder in

.prompts/

with its output artifacts, enabling clear provenance and chain detection. </objective>

<quick_start> <workflow>

Intake: Determine purpose (Do/Plan/Research/Refine), gather requirements
Chain detection: Check for existing research/plan files to reference
Generate: Create prompt using purpose-specific patterns
Save: Create folder in
```
.prompts/{number}-{topic}-{purpose}/
```
Present: Show decision tree for running
Execute: Run prompt(s) with dependency-aware execution engine
Summarize: Create SUMMARY.md for human scanning </workflow>

<folder_structure>

.prompts/
├── 001-auth-research/
│   ├── completed/
│   │   └── 001-auth-research.md    # Prompt (archived after run)
│   ├── auth-research.md            # Full output (XML for Claude)
│   └── SUMMARY.md                  # Executive summary (markdown for human)
├── 002-auth-plan/
│   ├── completed/
│   │   └── 002-auth-plan.md
│   ├── auth-plan.md
│   └── SUMMARY.md
├── 003-auth-implement/
│   ├── completed/
│   │   └── 003-auth-implement.md
│   └── SUMMARY.md                  # Do prompts create code elsewhere
├── 004-auth-research-refine/
│   ├── completed/
│   │   └── 004-auth-research-refine.md
│   ├── archive/
│   │   └── auth-research-v1.md     # Previous version
│   └── SUMMARY.md

</folder_structure> </quick_start>

<context> Prompts directory: !`[ -d ./.prompts ] && echo "exists" || echo "missing"` Existing research/plans: !`find ./.prompts -name "*-research.md" -o -name "*-plan.md" 2>/dev/null | head -10` Next prompt number: !`ls -d ./.prompts/*/ 2>/dev/null | wc -l | xargs -I {} expr {} + 1` </context>

<automated_workflow>

<step_0_intake_gate>

<title>Adaptive Requirements Gathering</title>

<critical_first_action> BEFORE analyzing anything, check if context was provided.

IF no context provided (skill invoked without description): → IMMEDIATELY use AskUserQuestion with:

header: "Purpose"
question: "What is the purpose of this prompt?"
options:
- "Do" - Execute a task, produce an artifact
- "Plan" - Create an approach, roadmap, or strategy
- "Research" - Gather information or understand something
- "Refine" - Improve an existing research or plan output

After selection, ask: "Describe what you want to accomplish" (they select "Other" to provide free text).

IF context was provided: → Check if purpose is inferable from keywords:

```
implement
```
,
```
build
```
,
```
create
```
,
```
fix
```
,
```
add
```
,
```
refactor
```
→ Do
```
plan
```
,
```
roadmap
```
,
```
approach
```
,
```
strategy
```
,
```
decide
```
,
```
phases
```
→ Plan

research

understand

learn

gather

analyze

explore

→ Research

```
refine
```
,
```
improve
```
,
```
deepen
```
,
```
expand
```
,
```
iterate
```
,
```
update
```
→ Refine

→ If unclear, ask the Purpose question above as first contextual question → If clear, proceed to adaptive_analysis with inferred purpose </critical_first_action>

<adaptive_analysis> Extract and infer:

Purpose: Do, Plan, Research, or Refine
Topic identifier: Kebab-case identifier for file naming (e.g.,
```
auth
```
,
```
stripe-payments
```
)
Complexity: Simple vs complex (affects prompt depth)
Prompt structure: Single vs multiple prompts
Target (Refine only): Which existing output to improve

If topic identifier not obvious, ask:

header: "Topic"
question: "What topic/feature is this for? (used for file naming)"
Let user provide via "Other" option
Enforce kebab-case (convert spaces/underscores to hyphens)

For Refine purpose, also identify target output from

.prompts/*/

to improve. </adaptive_analysis>

<chain_detection> Scan

.prompts/*/

for existing

*-research.md

and

*-plan.md

files.

If found:

List them: "Found existing files: auth-research.md (in 001-auth-research/), stripe-plan.md (in 005-stripe-plan/)"
Use AskUserQuestion:
- header: "Reference"
- question: "Should this prompt reference any existing research or plans?"
- options: List found files + "None"
- multiSelect: true

Match by topic keyword when possible (e.g., "auth plan" → suggest auth-research.md). </chain_detection>

<contextual_questioning> Generate 2-4 questions using AskUserQuestion based on purpose and gaps.

Load questions from: references/question-bank.md

Route by purpose:

Do → artifact type, scope, approach
Plan → plan purpose, format, constraints
Research → depth, sources, output format
Refine → target selection, feedback, preservation </contextual_questioning>

<decision_gate> After receiving answers, present decision gate using AskUserQuestion:

header: "Ready"
question: "Ready to create the prompt?"
options:
- "Proceed" - Create the prompt with current context
- "Ask more questions" - I have more details to clarify
- "Let me add context" - I want to provide additional information

Loop until "Proceed" selected. </decision_gate>

<finalization> After "Proceed" selected, state confirmation:

"Creating a {purpose} prompt for: {topic} Folder: .prompts/{number}-{topic}-{purpose}/ References: {list any chained files}"

Then proceed to generation. </finalization> </step_0_intake_gate>

<step_1_generate>

<title>Generate Prompt</title>

Load purpose-specific patterns:

Do: references/do-patterns.md
Plan: references/plan-patterns.md
Research: references/research-patterns.md
Refine: references/refine-patterns.md

Load intelligence rules: references/intelligence-rules.md

<prompt_structure> All generated prompts include:

Objective: What to accomplish, why it matters
Context: Referenced files (@), dynamic context (!)
Requirements: Specific instructions for the task
Output specification: Where to save, what structure
Metadata requirements: For research/plan outputs, specify XML metadata structure
SUMMARY.md requirement: All prompts must create a SUMMARY.md file
Success criteria: How to know it worked

For Research and Plan prompts, output must include:

```
<confidence>
```
- How confident in findings
```
<dependencies>
```
- What's needed to proceed
```
<open_questions>
```
- What remains uncertain
```
<assumptions>
```
- What was assumed

All prompts must create

SUMMARY.md

with:

One-liner - Substantive description of outcome
Version - v1 or iteration info
Key Findings - Actionable takeaways
Files Created - (Do prompts only)
Decisions Needed - What requires user input
Blockers - External impediments
Next Step - Concrete forward action </prompt_structure>

<file_creation>

Create folder:
```
.prompts/{number}-{topic}-{purpose}/
```
Create
```
completed/
```
subfolder

Write prompt to:

.prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md

Prompt instructs output to:
```
.prompts/{number}-{topic}-{purpose}/{topic}-{purpose}.md
```
</file_creation> </step_1_generate>

<step_2_present>

<title>Present Decision Tree</title>

After saving prompt(s), present inline (not AskUserQuestion):

<single_prompt_presentation>

Prompt created: .prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md

What's next?

1. Run prompt now
2. Review/edit prompt first
3. Save for later
4. Other

Choose (1-4): _

</single_prompt_presentation>

<multi_prompt_presentation>

Prompts created:
- .prompts/001-auth-research/001-auth-research.md
- .prompts/002-auth-plan/002-auth-plan.md
- .prompts/003-auth-implement/003-auth-implement.md

Detected execution order: Sequential (002 references 001 output, 003 references 002 output)

What's next?

1. Run all prompts (sequential)
2. Review/edit prompts first
3. Save for later
4. Other

Choose (1-4): _

</multi_prompt_presentation> </step_2_present>

<step_3_execute>

<title>Execution Engine</title>

<execution_modes> <single_prompt> Straightforward execution of one prompt.

Read prompt file contents
Spawn Task agent with subagent_type="general-purpose"
Include in task prompt:
- The complete prompt contents
- Output location:
```
.prompts/{number}-{topic}-{purpose}/{topic}-{purpose}.md
```
Wait for completion
Validate output (see validation section)
Archive prompt to
```
completed/
```
subfolder
Report results with next-step options </single_prompt>

<sequential_execution> For chained prompts where each depends on previous output.

Build execution queue from dependency order
For each prompt in queue: a. Read prompt file b. Spawn Task agent c. Wait for completion d. Validate output e. If validation fails → stop, report failure, offer recovery options f. If success → archive prompt, continue to next
Report consolidated results

<progress_reporting> Show progress during execution:

Executing 1/3: 001-auth-research... ✓
Executing 2/3: 002-auth-plan... ✓
Executing 3/3: 003-auth-implement... (running)

</progress_reporting> </sequential_execution>

<parallel_execution> For independent prompts with no dependencies.

Read all prompt files
CRITICAL: Spawn ALL Task agents in a SINGLE message
- This is required for true parallel execution
- Each task includes its output location
Wait for all to complete
Validate all outputs
Archive all prompts
Report consolidated results (successes and failures)

<failure_handling> Unlike sequential, parallel continues even if some fail:

Collect all results
Archive successful prompts
Report failures with details
Offer to retry failed prompts </failure_handling> </parallel_execution>

<mixed_dependencies> For complex DAGs (e.g., two parallel research → one plan).

Analyze dependency graph from @ references
Group into execution layers:
- Layer 1: No dependencies (run parallel)
- Layer 2: Depends only on layer 1 (run after layer 1 completes)
- Layer 3: Depends on layer 2, etc.
Execute each layer:
- Parallel within layer
- Sequential between layers
Stop if any dependency fails (downstream prompts can't run)

<example> ``` Layer 1 (parallel): 001-api-research, 002-db-research Layer 2 (after layer 1): 003-architecture-plan Layer 3 (after layer 2): 004-implement ``` </example> </mixed_dependencies> </execution_modes>

<dependency_detection> <automatic_detection> Scan prompt contents for @ references to determine dependencies:

Parse each prompt for
```
@.prompts/{number}-{topic}/
```
patterns
Build dependency graph
Detect cycles (error if found)
Determine execution order

<inference_rules> If no explicit @ references found, infer from purpose:

Research prompts: No dependencies (can parallel)
Plan prompts: Depend on same-topic research
Do prompts: Depend on same-topic plan

Override with explicit references when present. </inference_rules> </automatic_detection>

<missing_dependencies> If a prompt references output that doesn't exist:

Check if it's another prompt in this session (will be created)
Check if it exists in
```
.prompts/*/
```
(already completed)
If truly missing:
- Warn user: "002-auth-plan references auth-research.md which doesn't exist"
- Offer: Create the missing research prompt first? / Continue anyway? / Cancel? </missing_dependencies> </dependency_detection>

<validation> <output_validation> After each prompt completes, verify success:

File exists: Check output file was created
Not empty: File has content (> 100 chars)
Metadata present (for research/plan): Check for required XML tags
- ```
<confidence>
```
- ```
<dependencies>
```
- ```
<open_questions>
```
- ```
<assumptions>
```
SUMMARY.md exists: Check SUMMARY.md was created
SUMMARY.md complete: Has required sections (Key Findings, Decisions Needed, Blockers, Next Step)
One-liner is substantive: Not generic like "Research completed"

<validation_failure> If validation fails:

Report what's missing
Offer options:
- Retry the prompt
- Continue anyway (for non-critical issues)
- Stop and investigate </validation_failure> </output_validation> </validation>

<failure_handling> <sequential_failure> Stop the chain immediately:

✗ Failed at 2/3: 002-auth-plan

Completed:
- 001-auth-research ✓ (archived)

Failed:
- 002-auth-plan: Output file not created

Not started:
- 003-auth-implement

What's next?
1. Retry 002-auth-plan
2. View error details
3. Stop here (keep completed work)
4. Other

</sequential_failure>

<parallel_failure> Continue others, report all results:

Parallel execution completed with errors:

✓ 001-api-research (archived)
✗ 002-db-research: Validation failed - missing <confidence> tag
✓ 003-ui-research (archived)

What's next?
1. Retry failed prompt (002)
2. View error details
3. Continue without 002
4. Other

</parallel_failure> </failure_handling>

<archiving> <archive_timing> - **Sequential**: Archive each prompt immediately after successful completion - Provides clear state if execution stops mid-chain - **Parallel**: Archive all at end after collecting results - Keeps prompts available for potential retry

<archive_operation> Move prompt file to completed subfolder:

bash

mv .prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md \
   .prompts/{number}-{topic}-{purpose}/completed/

Output file stays in place (not moved). </archive_operation> </archiving>

<result_presentation> <single_result>

✓ Executed: 001-auth-research
✓ Created: .prompts/001-auth-research/SUMMARY.md

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

<objective> 为多阶段工作流中的Claude-to-Claude通信创建优化的提示词。输出采用XML和元数据结构，以便后续提示词高效解析。

每次执行都会生成一个

SUMMARY.md

，方便人类快速浏览，无需查看完整输出。

每个提示词在

.prompts/

目录下都有独立文件夹，存放其输出产物，便于清晰追溯来源和检测调用链。 </objective>

<quick_start> <workflow>

需求收集：确定目标（Do/Plan/Research/Refine），收集需求
调用链检测：检查是否存在可参考的现有研究/规划文件
生成：使用特定目标的模板创建提示词
保存：在
```
.prompts/{number}-{topic}-{purpose}/
```
目录下创建文件夹
展示：呈现运行决策树
执行：使用支持依赖感知的执行引擎运行提示词
总结：创建供人类浏览的SUMMARY.md </workflow>

<folder_structure>

.prompts/
├── 001-auth-research/
│   ├── completed/
│   │   └── 001-auth-research.md    # Prompt (archived after run)
│   ├── auth-research.md            # Full output (XML for Claude)
│   └── SUMMARY.md                  # Executive summary (markdown for human)
├── 002-auth-plan/
│   ├── completed/
│   │   └── 002-auth-plan.md
│   ├── auth-plan.md
│   └── SUMMARY.md
├── 003-auth-implement/
│   ├── completed/
│   │   └── 003-auth-implement.md
│   └── SUMMARY.md                  # Do prompts create code elsewhere
├── 004-auth-research-refine/
│   ├── completed/
│   │   └── 004-auth-research-refine.md
│   ├── archive/
│   │   └── auth-research-v1.md     # Previous version
│   └── SUMMARY.md

</folder_structure> </quick_start>

<context> 提示词目录：!`[ -d ./.prompts ] && echo "exists" || echo "missing"` 现有研究/规划文件：!`find ./.prompts -name "*-research.md" -o -name "*-plan.md" 2>/dev/null | head -10` 下一个提示词编号：!`ls -d ./.prompts/*/ 2>/dev/null | wc -l | xargs -I {} expr {} + 1` </context>

<automated_workflow>

<step_0_intake_gate>

<title>自适应需求收集</title>

<critical_first_action> 在分析任何内容之前，检查是否提供了上下文信息。

如果未提供上下文（调用技能时未附带描述）： → 立即使用AskUserQuestion，内容如下：

header: "目标"
question: "此提示词的目标是什么？"
options:
- "Do" - 执行任务，生成产物
- "Plan" - 创建方案、路线图或策略
- "Research" - 收集信息或了解相关内容
- "Refine" - 优化现有的研究或规划输出

用户选择后，询问："描述你想要完成的内容"（用户可选择“Other”来提供自由文本）。

如果已提供上下文： → 检查是否可通过关键词推断目标：

```
implement
```
,
```
build
```
,
```
create
```
,
```
fix
```
,
```
add
```
,
```
refactor
```
→ Do
```
plan
```
,
```
roadmap
```
,
```
approach
```
,
```
strategy
```
,
```
decide
```
,
```
phases
```
→ Plan

research

understand

learn

gather

analyze

explore

→ Research

```
refine
```
,
```
improve
```
,
```
deepen
```
,
```
expand
```
,
```
iterate
```
,
```
update
```
→ Refine

→ 如果目标不明确，先询问上述的目标问题 → 如果目标明确，带着推断出的目标进入自适应分析阶段 </critical_first_action>

<adaptive_analysis> 提取并推断：

目标：Do、Plan、Research或Refine
主题标识符：用于文件命名的短横线分隔式标识符（例如：
```
auth
```
,
```
stripe-payments
```
）
复杂度：简单或复杂（影响提示词的深度）
提示词结构：单提示词或多提示词
目标对象（仅Refine场景）：要优化的现有输出

如果主题标识符不明确，询问：

header: "主题"
question: "此提示词针对哪个主题/功能？（用于文件命名）"
允许用户通过“Other”选项提供
强制使用短横线分隔式（将空格/下划线转换为短横线）

对于Refine目标，还需从

.prompts/*/

中识别要优化的目标输出。 </adaptive_analysis>

<chain_detection> 扫描

.prompts/*/

目录下的现有

*-research.md

和

*-plan.md

文件。

如果找到：

列出文件："找到现有文件：auth-research.md（位于001-auth-research/），stripe-plan.md（位于005-stripe-plan/）"
使用AskUserQuestion：
- header: "参考文件"
- question: "此提示词是否需要参考任何现有的研究或规划文件？"
- options: 列出找到的文件 + "无"
- multiSelect: true

尽可能按主题关键词匹配（例如：“auth plan” → 推荐auth-research.md）。 </chain_detection>

<contextual_questioning> 根据目标和信息缺口，使用AskUserQuestion生成2-4个问题。

从references/question-bank.md加载问题。

按目标分类提问：

Do → 产物类型、范围、实现方式
Plan → 规划目的、格式、约束条件
Research → 研究深度、来源、输出格式
Refine → 目标选择、反馈意见、保留内容 </contextual_questioning>

<decision_gate> 收到所有答案后，使用AskUserQuestion呈现决策门：

header: "准备就绪"
question: "是否准备好创建提示词？"
options:
- "继续" - 使用当前上下文创建提示词
- "补充问题" - 我有更多细节需要澄清
- "添加上下文" - 我想提供额外的信息

循环直到用户选择“继续”。 </decision_gate>

<finalization> 用户选择“继续”后，确认信息：

"正在为以下内容创建{purpose}类型的提示词：{topic} 文件夹：.prompts/{number}-{topic}-{purpose}/ 参考文件：{列出所有关联文件}"

然后进入生成阶段。 </finalization> </step_0_intake_gate>

<step_1_generate>

<title>生成提示词</title>

加载特定目标的模板：

Do: references/do-patterns.md
Plan: references/plan-patterns.md
Research: references/research-patterns.md
Refine: references/refine-patterns.md

加载智能规则：references/intelligence-rules.md

<prompt_structure> 所有生成的提示词都包含以下部分：

目标：要完成的任务及其重要性
上下文：参考文件（@）、动态上下文（!）
需求：任务的具体说明
输出规范：保存位置、结构要求
元数据要求：对于研究/规划输出，指定XML元数据结构
SUMMARY.md要求：所有提示词必须创建SUMMARY.md文件
成功标准：如何判断任务完成

对于Research和Plan类型的提示词，输出必须包含：

```
<confidence>
```
- 对研究结果的置信度
```
<dependencies>
```
- 后续执行所需的条件
```
<open_questions>
```
- 尚未确定的问题
```
<assumptions>
```
- 做出的假设

所有提示词必须创建包含以下内容的

SUMMARY.md

：

一句话总结 - 对结果的实质性描述
版本 - v1或迭代信息
关键发现 - 可执行的结论
创建的文件 - （仅Do类型提示词）
待决策事项 - 需要用户输入的内容
阻塞点 - 外部障碍
下一步行动 - 具体的后续步骤 </prompt_structure>

<file_creation>

创建文件夹：
```
.prompts/{number}-{topic}-{purpose}/
```
创建
```
completed/
```
子文件夹

将提示词写入：

.prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md

提示词指定输出位置为：
```
.prompts/{number}-{topic}-{purpose}/{topic}-{purpose}.md
```
</file_creation> </step_1_generate>

<step_2_present>

<title>呈现决策树</title>

保存提示词后，直接内联呈现（不使用AskUserQuestion）：

<single_prompt_presentation>

已创建提示词：.prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md

下一步操作？

1. 立即运行提示词
2. 先查看/编辑提示词
3. 保存供以后使用
4. 其他

请选择（1-4）：_

</single_prompt_presentation>

<multi_prompt_presentation>

已创建提示词：
- .prompts/001-auth-research/001-auth-research.md
- .prompts/002-auth-plan/002-auth-plan.md
- .prompts/003-auth-implement/003-auth-implement.md

检测到执行顺序：顺序执行（002参考001的输出，003参考002的输出）

下一步操作？

1. 运行所有提示词（顺序执行）
2. 先查看/编辑提示词
3. 保存供以后使用
4. 其他

请选择（1-4）：_

</multi_prompt_presentation> </step_2_present>

<step_3_execute>

<execution_modes> <single_prompt> 单个提示词的直接执行流程。

读取提示词文件内容
生成Task agent，设置subagent_type="general-purpose"
在任务提示词中包含：
- 完整的提示词内容
- 输出位置：
```
.prompts/{number}-{topic}-{purpose}/{topic}-{purpose}.md
```
等待执行完成
验证输出（见验证部分）
将提示词归档到
```
completed/
```
子文件夹
报告结果并提供下一步选项 </single_prompt>

<sequential_execution> 适用于存在依赖关系的链式提示词，每个提示词依赖前一个的输出。

根据依赖顺序构建执行队列
对队列中的每个提示词： a. 读取提示词文件 b. 生成Task agent c. 等待执行完成 d. 验证输出 e. 如果验证失败 → 停止执行，报告失败原因，提供恢复选项 f. 如果执行成功 → 归档提示词，继续下一个
报告综合结果

<progress_reporting> 执行过程中显示进度：

正在执行 1/3: 001-auth-research... ✓
正在执行 2/3: 002-auth-plan... ✓
正在执行 3/3: 003-auth-implement... (运行中)

</progress_reporting> </sequential_execution>

<parallel_execution> 适用于无依赖关系的独立提示词。

读取所有提示词文件
关键要求：在单个消息中生成所有Task agent
- 这是实现真正并行执行的必要条件
- 每个任务包含其输出位置
等待所有任务完成
验证所有输出
归档所有提示词
报告综合结果（成功和失败情况）

<failure_handling> 与顺序执行不同，并行执行即使部分任务失败也会继续：

收集所有结果
归档成功的提示词
报告失败详情
提供重试失败提示词的选项 </failure_handling> </parallel_execution>

<mixed_dependencies> 适用于复杂的DAG依赖（例如：两个并行的研究提示词 → 一个规划提示词）。

从@引用中分析依赖图
将提示词分组为执行层：
- 第1层：无依赖（并行运行）
- 第2层：仅依赖第1层的提示词（第1层完成后运行）
- 第3层：依赖第2层的提示词，依此类推
执行每个层：
- 层内并行执行
- 层间顺序执行
如果任何依赖任务失败，停止执行（下游提示词无法运行）

<example> ``` 第1层（并行）：001-api-research, 002-db-research 第2层（第1层完成后）：003-architecture-plan 第3层（第2层完成后）：004-implement ``` </example> </mixed_dependencies> </execution_modes>

<dependency_detection> <automatic_detection> 扫描提示词内容中的@引用以确定依赖关系：

解析每个提示词中的
```
@.prompts/{number}-{topic}/
```
模式
构建依赖图
检测循环依赖（如果发现则报错）
确定执行顺序

<inference_rules> 如果未找到明确的@引用，根据目标推断依赖关系：

Research提示词：无依赖（可并行执行）
Plan提示词：依赖同主题的Research提示词
Do提示词：依赖同主题的Plan提示词

如果存在明确引用，则覆盖推断结果。 </inference_rules> </automatic_detection>

<missing_dependencies> 如果提示词引用的输出不存在：

检查是否是本次会话中将要创建的其他提示词
检查是否存在于
```
.prompts/*/
```
目录中（已完成的提示词）
如果确实不存在：
- 警告用户："002-auth-plan引用的auth-research.md不存在"
- 提供选项：先创建缺失的研究提示词？/ 继续执行？/ 取消？ </missing_dependencies> </dependency_detection>

<validation> <output_validation> 每个提示词执行完成后，验证是否成功：

文件存在：检查输出文件是否已创建
非空：文件内容长度大于100字符
元数据存在（仅研究/规划类型）：检查是否包含所需的XML标签
- ```
<confidence>
```
- ```
<dependencies>
```
- ```
<open_questions>
```
- ```
<assumptions>
```
SUMMARY.md存在：检查是否已创建SUMMARY.md
SUMMARY.md内容完整：包含所需部分（关键发现、待决策事项、阻塞点、下一步行动）
一句话总结具有实质性：不是通用描述如“研究完成”

<validation_failure> 如果验证失败：

报告缺失的内容
提供选项：
- 重试提示词
- 继续执行（针对非关键问题）
- 停止执行并调查 </validation_failure> </output_validation> </validation>

<failure_handling> <sequential_failure> 立即停止链式执行：

✗ 执行失败 2/3: 002-auth-plan

已完成：
- 001-auth-research ✓ （已归档）

失败：
- 002-auth-plan：未创建输出文件

未开始：
- 003-auth-implement

下一步操作？
1. 重试002-auth-plan
2. 查看错误详情
3. 在此停止（保留已完成的工作）
4. 其他

</sequential_failure>

<parallel_failure> 继续执行其他任务，报告所有结果：

并行执行完成，存在错误：

✓ 001-api-research（已归档）
✗ 002-db-research：验证失败 - 缺少<confidence>标签
✓ 003-ui-research（已归档）

下一步操作？
1. 重试失败的提示词（002）
2. 查看错误详情
3. 忽略002继续执行
4. 其他

</parallel_failure> </failure_handling>

<archiving> <archive_timing> - **顺序执行**：每个提示词执行成功后立即归档 - 便于在执行中途停止时清晰了解状态 - **并行执行**：收集所有结果后统一归档 - 保留提示词以便后续重试

<archive_operation> 将提示词文件移动到completed子文件夹：

bash

mv .prompts/{number}-{topic}-{purpose}/{number}-{topic}-{purpose}.md \
   .prompts/{number}-{topic}-{purpose}/completed/

输出文件保留在原位置（不移动）。 </archive_operation> </archiving>

<result_presentation> <single_result>

✓ 执行完成：001-auth-research
✓ 已创建：.prompts/001-auth-research/SUMMARY.md

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Auth Research Summary

认证研究总结

JWT with jose library and httpOnly cookies recommended

推荐使用jose库和httpOnly Cookie实现JWT

Key Findings

关键发现

• jose outperforms jsonwebtoken with better TypeScript support • httpOnly cookies required (localStorage is XSS vulnerable) • Refresh rotation is OWASP standard

• jose库比jsonwebtoken性能更好，且TypeScript支持更完善 • 必须使用httpOnly Cookie（localStorage易受XSS攻击） • 刷新令牌轮换是OWASP标准

Decisions Needed

待决策事项

None - ready for planning

无 - 已准备好进入规划阶段

Blockers

阻塞点

None

无

Next Step

下一步行动

Create auth-plan.md ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

What's next?

Create planning prompt (auth-plan)
View full research output
Done
Other


Display the actual SUMMARY.md content inline so user sees findings without opening files.
</single_result>

<chain_result>

✓ Chain completed: auth workflow

Results: ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 001-auth-research JWT with jose library and httpOnly cookies recommended Decisions: None • Blockers: None

002-auth-plan 4-phase implementation: types → JWT core → refresh → tests Decisions: Approve 15-min token expiry • Blockers: None

003-auth-implement JWT middleware complete with 6 files created Decisions: Review before Phase 2 • Blockers: None ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

All prompts archived. Full summaries in .prompts/*/SUMMARY.md

What's next?

Review implementation
Run tests
Create new prompt chain
Other


For chains, show condensed one-liner from each SUMMARY.md with decisions/blockers flagged.
</chain_result>
</result_presentation>

<special_cases>
<re_running_completed>
If user wants to re-run an already-completed prompt:

1. Check if prompt is in `completed/` subfolder
2. Move it back to parent folder
3. Optionally backup existing output: `{output}.bak`
4. Execute normally
</re_running_completed>

<output_conflicts>
If output file already exists:

1. For re-runs: Backup existing → `{filename}.bak`
2. For new runs: Should not happen (unique numbering)
3. If conflict detected: Ask user - Overwrite? / Rename? / Cancel?
</output_conflicts>

<commit_handling>
After successful execution:

1. Do NOT auto-commit (user controls git workflow)
2. Mention what files were created/modified
3. User can commit when ready

Exception: If user explicitly requests commit, stage and commit:
- Output files created
- Prompts archived
- Any implementation changes (for Do prompts)
</commit_handling>

<recursive_prompts>
If a prompt's output includes instructions to create more prompts:

1. This is advanced usage - don't auto-detect
2. Present the output to user
3. User can invoke skill again to create follow-up prompts
4. Maintains user control over prompt creation
</recursive_prompts>
</special_cases>
</step_3_execute>

</automated_workflow>

<reference_guides>
**Prompt patterns by purpose:**
- [references/do-patterns.md](references/do-patterns.md) - Execution prompts + output structure
- [references/plan-patterns.md](references/plan-patterns.md) - Planning prompts + plan.md structure
- [references/research-patterns.md](references/research-patterns.md) - Research prompts + research.md structure
- [references/refine-patterns.md](references/refine-patterns.md) - Iteration prompts + versioning

**Shared templates:**
- [references/summary-template.md](references/summary-template.md) - SUMMARY.md structure and field requirements
- [references/metadata-guidelines.md](references/metadata-guidelines.md) - Confidence, dependencies, open questions, assumptions

**Supporting references:**
- [references/question-bank.md](references/question-bank.md) - Intake questions by purpose
- [references/intelligence-rules.md](references/intelligence-rules.md) - Extended thinking, parallel tools, depth decisions
</reference_guides>

<success_criteria>
**Prompt Creation:**
- Intake gate completed with purpose and topic identified
- Chain detection performed, relevant files referenced
- Prompt generated with correct structure for purpose
- Folder created in `.prompts/` with correct naming
- Output file location specified in prompt
- SUMMARY.md requirement included in prompt
- Metadata requirements included for Research/Plan outputs
- Quality controls included for Research outputs (verification checklist, QA, pre-submission)
- Streaming write instructions included for Research outputs
- Decision tree presented

**Execution (if user chooses to run):**
- Dependencies correctly detected and ordered
- Prompts executed in correct order (sequential/parallel/mixed)
- Output validated after each completion
- SUMMARY.md created with all required sections
- One-liner is substantive (not generic)
- Failed prompts handled gracefully with recovery options
- Successful prompts archived to `completed/` subfolder
- SUMMARY.md displayed inline in results
- Results presented with decisions/blockers flagged

**Research Quality (for Research prompts):**
- Verification checklist completed
- Quality report distinguishes verified from assumed claims
- Sources consulted listed with URLs
- Confidence levels assigned to findings
- Critical claims verified with official documentation
</success_criteria>

创建auth-plan.md ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

下一步操作？

创建规划提示词（auth-plan）
查看完整研究输出
完成
其他


直接内联显示SUMMARY.md的内容，方便用户无需打开文件即可查看研究结果。
</single_result>

<chain_result>

✓ 链式执行完成：认证工作流

结果： ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 001-auth-research 推荐使用jose库和httpOnly Cookie实现JWT 待决策：无 • 阻塞点：无

002-auth-plan 4阶段实施：类型定义 → JWT核心 → 刷新机制 → 测试 待决策：批准15分钟令牌过期时间 • 阻塞点：无

003-auth-implement JWT中间件已完成，创建了6个文件 待决策：第二阶段前需审核 • 阻塞点：无 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

所有提示词已归档。完整总结位于.prompts/*/SUMMARY.md

下一步操作？

查看实施内容
运行测试
创建新的提示词链
其他


对于链式执行，显示每个SUMMARY.md中的一句话总结，并标记待决策事项和阻塞点。
</chain_result>
</result_presentation>

<special_cases>
<re_running_completed>
如果用户想要重新运行已完成的提示词：

1. 检查提示词是否在`completed/`子文件夹中
2. 将其移回父文件夹
3. 可选：备份现有输出为`{output}.bak`
4. 正常执行
</re_running_completed>

<output_conflicts>
如果输出文件已存在：

1. 对于重新运行的提示词：备份现有文件为`{filename}.bak`
2. 对于新运行的提示词：不应出现此情况（编号唯一）
3. 如果检测到冲突：询问用户 - 覆盖？/ 重命名？/ 取消？
</output_conflicts>

<commit_handling>
执行成功后：

1. **不自动提交**（用户控制git工作流）
2. 说明创建/修改的文件
3. 用户可在准备好后提交

例外情况：如果用户明确要求提交，则暂存并提交以下内容：
- 创建的输出文件
- 已归档的提示词
- （Do类型提示词的）任何实施变更
</commit_handling>

<recursive_prompts>
如果提示词的输出包含创建更多提示词的说明：

1. 这是高级用法 - 不自动检测
2. 将输出呈现给用户
3. 用户可再次调用技能创建后续提示词
4. 保持用户对提示词创建的控制权
</recursive_prompts>
</special_cases>
</step_3_execute>

</automated_workflow>

<reference_guides>
**按目标分类的提示词模板：**
- [references/do-patterns.md](references/do-patterns.md) - 执行类提示词 + 输出结构
- [references/plan-patterns.md](references/plan-patterns.md) - 规划类提示词 + plan.md结构
- [references/research-patterns.md](references/research-patterns.md) - 研究类提示词 + research.md结构
- [references/refine-patterns.md](references/refine-patterns.md) - 优化类提示词 + 版本控制

**共享模板：**
- [references/summary-template.md](references/summary-template.md) - SUMMARY.md结构和字段要求
- [references/metadata-guidelines.md](references/metadata-guidelines.md) - 置信度、依赖关系、未解决问题、假设的规范

**支持性参考：**
- [references/question-bank.md](references/question-bank.md) - 按目标分类的需求收集问题
- [references/intelligence-rules.md](references/intelligence-rules.md) - 扩展思考、并行工具、深度决策规则
</reference_guides>

<success_criteria>
**提示词创建成功标准：**
- 完成需求收集，确定目标和主题
- 执行调用链检测，参考相关文件
- 根据目标生成结构正确的提示词
- 在`.prompts/`目录下创建命名规范的文件夹
- 提示词中指定输出文件位置
- 提示词中包含SUMMARY.md生成要求
- 研究/规划类提示词包含元数据要求
- 研究类提示词包含质量控制要求（验证清单、QA、提交前检查）
- 研究类提示词包含流式写入说明
- 呈现决策树

**执行成功标准（如果用户选择运行）：**
- 正确检测并排序依赖关系
- 按正确顺序执行提示词（顺序/并行/混合）
- 每个提示词执行完成后验证输出
- 创建内容完整的SUMMARY.md
- 一句话总结具有实质性（非通用描述）
- 优雅处理失败的提示词，提供恢复选项
- 成功的提示词归档到`completed/`子文件夹
- 结果中内联显示SUMMARY.md内容
- 结果中标记待决策事项和阻塞点

**研究质量标准（仅研究类提示词）：**
- 完成验证清单
- 质量报告区分已验证和假设的结论
- 列出参考来源及URL
- 为研究结果分配置信度
- 关键结论已通过官方文档验证
</success_criteria>