session-wrap

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Session Wrap Skill

Comprehensive session wrap-up workflow with multi-agent analysis.

这是一套包含多Agent分析的全面会话收尾工作流。

Execution Flow

执行流程

┌─────────────────────────────────────────────────────┐
│  1. Check Git Status                                │
├─────────────────────────────────────────────────────┤
│  2. Phase 1: 4 Analysis Agents (Parallel)           │
│     ┌─────────────────┬─────────────────┐           │
│     │  doc-updater    │  automation-    │           │
│     │  (docs update)  │  scout          │           │
│     ├─────────────────┼─────────────────┤           │
│     │  learning-      │  followup-      │           │
│     │  extractor      │  suggester      │           │
│     └─────────────────┴─────────────────┘           │
├─────────────────────────────────────────────────────┤
│  3. Phase 2: Validation Agent (Sequential)          │
│     ┌───────────────────────────────────┐           │
│     │       duplicate-checker           │           │
│     │  (Validate Phase 1 proposals)     │           │
│     └───────────────────────────────────┘           │
├─────────────────────────────────────────────────────┤
│  4. Integrate Results & AskUserQuestion             │
├─────────────────────────────────────────────────────┤
│  5. Execute Selected Actions                        │
└─────────────────────────────────────────────────────┘

┌─────────────────────────────────────────────────────┐
│  1. Check Git Status                                │
├─────────────────────────────────────────────────────┤
│  2. Phase 1: 4 Analysis Agents (Parallel)           │
│     ┌─────────────────┬─────────────────┐           │
│     │  doc-updater    │  automation-    │           │
│     │  (docs update)  │  scout          │           │
│     ├─────────────────┼─────────────────┤           │
│     │  learning-      │  followup-      │           │
│     │  extractor      │  suggester      │           │
│     └─────────────────┴─────────────────┘           │
├─────────────────────────────────────────────────────┤
│  3. Phase 2: Validation Agent (Sequential)          │
│     ┌───────────────────────────────────┐           │
│     │       duplicate-checker           │           │
│     │  (Validate Phase 1 proposals)     │           │
│     └───────────────────────────────────┘           │
├─────────────────────────────────────────────────────┤
│  4. Integrate Results & AskUserQuestion             │
├─────────────────────────────────────────────────────┤
│  5. Execute Selected Actions                        │
└─────────────────────────────────────────────────────┘

Step 1: Check Git Status

步骤1：检查Git状态

bash

git status --short
git diff --stat HEAD~3 2>/dev/null || git diff --stat

bash

git status --short
git diff --stat HEAD~3 2>/dev/null || git diff --stat

Step 2: Phase 1 - Analysis Agents (Parallel)

步骤2：第一阶段 - 分析Agent（并行执行）

Execute 4 agents in parallel (single message with 4 Task calls).

并行执行4个Agent（通过单条消息发起4个Task调用）。

Session Summary (Provide to all agents)

会话摘要（提供给所有Agent）

Session Summary:
- Work: [Main tasks performed in session]
- Files: [Created/modified files]
- Decisions: [Key decisions made]

Session Summary:
- Work: [Main tasks performed in session]
- Files: [Created/modified files]
- Decisions: [Key decisions made]

Parallel Execution

并行执行

Task(
    subagent_type="doc-updater",
    description="Document update analysis",
    prompt="[Session Summary]\n\nAnalyze if CLAUDE.md, context.md need updates."
)

Task(
    subagent_type="automation-scout",
    description="Automation pattern analysis",
    prompt="[Session Summary]\n\nAnalyze repetitive patterns or automation opportunities."
)

Task(
    subagent_type="learning-extractor",
    description="Learning points extraction",
    prompt="[Session Summary]\n\nExtract learnings, mistakes, and new discoveries."
)

Task(
    subagent_type="followup-suggester",
    description="Follow-up task suggestions",
    prompt="[Session Summary]\n\nSuggest incomplete tasks and next session priorities."
)

Task(
    subagent_type="doc-updater",
    description="Document update analysis",
    prompt="[Session Summary]\n\nAnalyze if CLAUDE.md, context.md need updates."
)

Task(
    subagent_type="automation-scout",
    description="Automation pattern analysis",
    prompt="[Session Summary]\n\nAnalyze repetitive patterns or automation opportunities."
)

Task(
    subagent_type="learning-extractor",
    description="Learning points extraction",
    prompt="[Session Summary]\n\nExtract learnings, mistakes, and new discoveries."
)

Task(
    subagent_type="followup-suggester",
    description="Follow-up task suggestions",
    prompt="[Session Summary]\n\nSuggest incomplete tasks and next session priorities."
)

Agent Roles

Agent角色

Agent	Role	Output
doc-updater	Analyze CLAUDE.md/context.md updates	Specific content to add
automation-scout	Detect automation patterns	skill/command/agent suggestions
learning-extractor	Extract learning points	TIL format summary
followup-suggester	Suggest follow-up tasks	Prioritized task list

Agent	角色	输出内容
doc-updater	分析CLAUDE.md/context.md是否需要更新	需添加的具体内容
automation-scout	检测可自动化的模式	Skill/命令/Agent建议
learning-extractor	提取学习要点	TIL格式的总结
followup-suggester	建议后续任务	优先级排序的任务列表

Step 3: Phase 2 - Validation Agent (Sequential)

步骤3：第二阶段 - 验证Agent（顺序执行）

Run after Phase 1 completes (dependency on Phase 1 results).

Task(
    subagent_type="duplicate-checker",
    description="Phase 1 proposal validation",
    prompt="""
Validate Phase 1 analysis results.

需在第一阶段完成后运行（依赖第一阶段的结果）。

Task(
    subagent_type="duplicate-checker",
    description="Phase 1 proposal validation",
    prompt="""
Validate Phase 1 analysis results.

doc-updater proposals:

[doc-updater results]

automation-scout proposals:

[automation-scout results]

Check if proposals duplicate existing docs/automation:

Complete duplicate: Recommend skip
Partial duplicate: Suggest merge approach
No duplicate: Approve for addition """ )

undefined

[automation-scout results]

Check if proposals duplicate existing docs/automation:

Complete duplicate: Recommend skip
Partial duplicate: Suggest merge approach
No duplicate: Approve for addition """ )

undefined

Step 4: Integrate Results

步骤4：整合结果

markdown

undefined

markdown

undefined

Wrap Analysis Results

会话收尾分析结果

Documentation Updates

文档更新

[doc-updater summary]

Duplicate check: [duplicate-checker feedback]

[doc-updater摘要]

重复项检查：[duplicate-checker反馈]

Automation Suggestions

自动化建议

[automation-scout summary]

Duplicate check: [duplicate-checker feedback]

[automation-scout摘要]

重复项检查：[duplicate-checker反馈]

Learning Points

学习要点

[learning-extractor summary]

[learning-extractor摘要]

Follow-up Tasks

后续任务

[followup-suggester summary]

undefined

[followup-suggester摘要]

undefined

Step 5: Action Selection

步骤5：选择操作

AskUserQuestion(
    questions=[{
        "question": "Which actions would you like to perform?",
        "header": "Wrap Options",
        "multiSelect": true,
        "options": [
            {"label": "Create commit (Recommended)", "description": "Commit changes"},
            {"label": "Update CLAUDE.md", "description": "Document new knowledge/workflows"},
            {"label": "Create automation", "description": "Generate skill/command/agent"},
            {"label": "Skip", "description": "End without action"}
        ]
    }]
)

AskUserQuestion(
    questions=[{
        "question": "Which actions would you like to perform?",
        "header": "Wrap Options",
        "multiSelect": true,
        "options": [
            {"label": "Create commit (Recommended)", "description": "Commit changes"},
            {"label": "Update CLAUDE.md", "description": "Document new knowledge/workflows"},
            {"label": "Create automation", "description": "Generate skill/command/agent"},
            {"label": "Skip", "description": "End without action"}
        ]
    }]
)

Step 6: Execute Selected Actions

步骤6：执行选中的操作

Execute only the actions selected by user.

仅执行用户选中的操作。

Quick Reference

快速参考

When to Use

使用场景

End of significant work session
Before switching to different project
After completing a feature or fixing a bug

重要工作会话结束时
切换到其他项目之前
完成功能开发或修复Bug之后

When to Skip

无需使用的场景

Very short session with trivial changes
Only reading/exploring code
Quick one-off question answered

仅包含微小改动的极短会话
仅进行代码阅读/探索的会话
快速解答单个问题的会话

Arguments

参数说明

Empty: Proceed interactively (full workflow)
Message provided: Use as commit message and commit directly

无参数：以交互模式执行完整工作流
传入消息：将消息作为提交信息直接执行提交操作

Additional Resources

额外资源

See

references/multi-agent-patterns.md

for detailed orchestration patterns.

如需详细的编排模式，请参阅

references/multi-agent-patterns.md

。