work-summary
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseWork Summary Skill
工作总结技能
Create factual working journal entries that document completed analysis work without interpretation or recommendations.
创建真实准确的工作日志条目,记录已完成的分析工作,不包含解读或建议内容。
When to Use
适用场景
Activate when user requests:
- "Summarize the work"
- "Document the results"
- "Create a working journal entry"
- "Write up the analysis"
当用户提出以下请求时激活:
- “总结工作内容”
- “记录分析结果”
- “创建工作日志条目”
- “撰写分析报告”
Instructions
操作步骤
Step 1: Verify Git Commit
步骤1:验证Git提交
Check if code has been committed:
bash
git statusIf uncommitted changes exist:
- Inform user: "I see uncommitted changes. Should I run the code-quality-reviewer agent and commit the code first?"
- Wait for user confirmation
- If confirmed, use Task tool with then assist with git commit
subagent_type="code-quality-reviewer" - Get commit info:
git log -1 --pretty=format:"%H%n%s"
If clean: Get latest commit:
git log -1 --pretty=format:"%H%n%s"检查代码是否已提交:
bash
git status若存在未提交的更改:
- 告知用户:“我发现存在未提交的更改。是否需要先运行code-quality-reviewer agent并提交代码?”
- 等待用户确认
- 若用户确认,使用Task工具并设置,随后协助完成git提交
subagent_type="code-quality-reviewer" - 获取提交信息:
git log -1 --pretty=format:"%H%n%s"
若代码已提交: 获取最新提交信息:
git log -1 --pretty=format:"%H%n%s"Step 2: Confirm Understanding
步骤2:确认工作内容
If you have context from recent work:
- Summarize your understanding of objective, code location, output location
- Use AskUserQuestion tool to confirm with user
If you don't have context:
- Ask user for: objective, code location, output location
Then read code files, output files, and documentation to gather information.
若有近期工作的上下文信息:
- 总结你对工作目标、代码位置、输出文件位置的理解
- 使用AskUserQuestion工具向用户确认
若无上下文信息:
- 向用户询问:工作目标、代码位置、输出文件位置
随后读取代码文件、输出文件及相关文档以收集信息。
Step 3: Handle Figures
步骤3:处理图表
If figures exist in output folder:
bash
mkdir -p Notes/WorkingJournal/attachments
cp Output/[subfolder]/figure.png Notes/WorkingJournal/attachments/YYYY-MM-DD-description.pngIn markdown:
markdown

Source: [Original](../../Output/[subfolder]/figure.png)若输出文件夹中存在图表:
bash
mkdir -p Notes/WorkingJournal/attachments
cp Output/[subfolder]/figure.png Notes/WorkingJournal/attachments/YYYY-MM-DD-description.png在Markdown中引用:
markdown

来源:[原始文件](../../Output/[subfolder]/figure.png)Step 4: Create Working Journal Entry
步骤4:创建工作日志条目
Filename:
Notes/WorkingJournal/YYYY-MM-DD-[Author]-[Description].mdFront Matter:
yaml
---
author: "[[Author]]"
date: YYYY-MM-DD
project: "[[IntermediaryDemand]]"
git_commit: [full hash if available]
git_message: "[message if available]"
permalink: working-journal/YYYY-MM-DD-author-description
---文件名格式:
Notes/WorkingJournal/YYYY-MM-DD-[Author]-[Description].md头部信息:
yaml
---
author: "[[Author]]"
date: YYYY-MM-DD
project: "[[IntermediaryDemand]]"
git_commit: [若有则填写完整哈希值]
git_message: "[若有则填写提交信息]"
permalink: working-journal/YYYY-MM-DD-author-description
---Step 5: Write Summary
步骤5:撰写总结内容
Structure can be flexible, but typically include:
- Objective section
- Summary of what was done
- Data description
- Methodology description
- Results with tables/figures
- Technical implementation details (code and outputs)
Use relative paths from Notes/WorkingJournal/:
- Code:
../../Code/ - Output:
../../Output/ - Data:
../../Data/
结构可灵活调整,但通常需包含:
- 工作目标部分
- 已完成工作的总结
- 数据说明
- 方法说明
- 包含表格/图表的结果展示
- 技术实现细节(代码及输出文件)
使用相对于Notes/WorkingJournal/的路径:
- 代码:
../../Code/ - 输出文件:
../../Output/ - 数据:
../../Data/
Critical Rules - MUST FOLLOW
关键规则 - 必须遵守
1. Be Factual and Objective
1. 保持真实客观
✓ DO:
- State what was done and what was found
- Report numerical results precisely
- Describe methods used
- Link every claim to source (code, output, documentation)
✗ DO NOT:
- Interpret economic meaning without user request
- Speculate on causes or implications
- Make recommendations or suggest next steps
- Use subjective assessments ("excellent", "poor", "successful")
✅ 允许:
- 陈述已完成的工作及发现的结果
- 精确报告数值结果
- 描述所使用的方法
- 为每一项声明添加来源链接(代码、输出文件、文档)
❌ 禁止:
- 在未收到用户请求的情况下解读经济含义
- 推测原因或影响
- 提出建议或下一步计划
- 使用主观评价词汇(如“优秀”、“糟糕”、“成功”)
2. Examples
2. 示例
Good (Factual):
- "Processed 4.7M holdings from 11,857 submissions"
- "Difference of -30% (-$243B)"
- "Front-end tenors within 7% of benchmark"
- "Classification success rate: 70% (3,988 of 5,699)"
Bad (Speculative/Interpretive):
- "This suggests the classification is insufficient"
- "The results indicate strong performance"
- "This likely means we should use BKMS data"
- "The excellent match validates our approach"
正确(客观表述):
- “处理了来自11,857份提交的470万条持有数据”
- “差值为-30%(-2430亿美元)”
- “前端期限与基准值的偏差在7%以内”
- “分类成功率:70%(5699条中的3988条)”
错误(推测/解读性表述):
- “这表明分类效果不足”
- “结果显示性能优异”
- “这可能意味着我们应该使用BKMS数据”
- “高度匹配验证了我们的方法”
3. Cite Everything
3. 内容需全部引用
Every claim must link to supporting evidence:
[descriptive text](../../path/to/file)- Code files for methodology
- Output files for results
- Documentation for data sources
每一项声明都必须链接到支持证据:
[描述性文本](../../path/to/file)- 方法相关的代码文件
- 结果相关的输出文件
- 数据来源相关的文档
4. Figures
4. 图表处理
- Copy to attachments/ with descriptive filename
- Cite original source location
- Use descriptive captions
- 将图表复制到attachments/目录,并使用描述性文件名
- 引用原始文件的位置
- 使用描述性标题
Step 6: Verify Report Quality
步骤6:验证报告质量
After creating the report, use the report-checker agent to verify quality:
Use Task tool with subagent_type="report-checker"
Pass: report path, code location, output location, objectiveThe agent will check:
- All claims are cited and accurate
- No speculation or unsupported interpretation
- Numbers match source files
- No subjective language
If issues found, revise the report before finalizing.
创建报告后,使用report-checker agent验证质量:
使用Task工具,设置subagent_type="report-checker"
传入参数:报告路径、代码位置、输出文件位置、工作目标该agent将检查:
- 所有声明均有引用且准确
- 无推测或无依据的解读内容
- 数值与源文件一致
- 无主观语言
若发现问题,在最终确定前修改报告。
After Creating
创建完成后的操作
- Tell user the file path
- List what was documented
- Report any issues found by report-checker
- Ask: "Would you like me to add any specific information?"
- Do NOT suggest interpretations or next steps unless asked
- 告知用户文件路径
- 列出已记录的内容
- 报告report-checker发现的所有问题
- 询问用户:“是否需要我添加特定信息?”
- 除非用户要求,否则不得提出解读或下一步计划