Back to Details

daily-meeting-update

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Daily Meeting Update

每日会议更新

Generate a daily standup/meeting update through an interactive interview. Never assume tools are configured—ask first.
通过交互式访谈生成每日站会/会议更新内容。切勿假设工具已配置完成——务必先询问用户。

Workflow

工作流程

START
  │
  ▼
┌─────────────────────────────────────────────────────┐
│ Phase 1: DETECT & OFFER INTEGRATIONS                │
│ • Check: Claude Code history? gh CLI? jira CLI?     │
│ • Claude Code → Pull yesterday's session digest     │
│   → User selects relevant items via multiSelect     │
│ • GitHub/Jira → Ask user, pull if approved          │
│ • Pull data NOW (before interview)                  │
├─────────────────────────────────────────────────────┤
│ Phase 2: INTERVIEW (with insights)                  │
│ • Show pulled data as context                       │
│ • Yesterday: "I see you merged PR #123, what else?" │
│ • Today: What will you work on?                     │
│ • Blockers: Anything blocking you?                  │
│ • Topics: Anything to discuss at end of meeting?    │
├─────────────────────────────────────────────────────┤
│ Phase 3: GENERATE UPDATE                            │
│ • Combine interview answers + tool data             │
│ • Format as clean Markdown                          │
│ • Present to user                                   │
└─────────────────────────────────────────────────────┘
START
  │
  ▼
┌─────────────────────────────────────────────────────┐
│ 阶段1：检测并提供集成选项                          │
│ • 检查：Claude Code历史记录？gh CLI？jira CLI？     │
│ • Claude Code → 提取昨日会话摘要                   │
│   → 用户通过多选功能选择相关项                     │
│ • GitHub/Jira → 询问用户，获许后提取数据            │
│ • 立即提取数据（访谈前完成）                        │
├─────────────────────────────────────────────────────┤
│ 阶段2：带上下文的访谈                              │
│ • 展示提取的数据作为上下文                         │
│ • 昨日工作：“我看到你合并了PR #123，还有其他工作吗？”│
│ • 今日计划：你今天将开展哪些工作？                  │
│ • 遇到的阻碍：有没有什么问题阻碍你推进工作？          │
│ • 讨论议题：会议末尾有什么需要讨论的内容吗？          │
├─────────────────────────────────────────────────────┤
│ 阶段3：生成更新内容                                │
│ • 结合访谈回答与工具提取的数据                      │
│ • 格式化为简洁的Markdown                           │
│ • 呈现给用户                                      │
└─────────────────────────────────────────────────────┘

Phase 1: Detect & Offer Integrations

阶段1：检测并提供集成选项

Step 1: Silent Detection

步骤1：静默检测

Check for available integrations silently (suppress errors, don't show to user):
IntegrationDetection
Claude Code History
~/.claude/projects
directory exists with 
.jsonl
files
GitHub CLI
gh auth status
succeeds
Jira CLI
jira
command exists
Atlassian MCP
mcp__atlassian__*
tools available
GitInside a git repository
静默检查可用的集成（抑制错误，不向用户展示）：
集成工具检测方式
Claude Code历史记录存在
~/.claude/projects
目录及
.jsonl
文件
GitHub CLI
gh auth status
执行成功
Jira CLI
jira
命令可执行
Atlassian MCP存在
mcp__atlassian__*
工具
Git当前处于git仓库目录内

Step 2: Offer GitHub/Jira Integrations (if available)

步骤2：提供GitHub/Jira集成选项（如果可用）

Claude Code users: Use 
AskUserQuestionTool
tool for all questions in this phase.
GitHub/Git:
If 
HAS_GH
or 
HAS_GIT
:
"I detected you have GitHub/Git configured. Want me to pull your recent activity (commits, PRs, reviews)?"

Options:
- "Yes, pull the info"
- "No, I'll provide everything manually"
If yes:
"Which repositories/projects should I check?"

Options:
- "Just the current directory" (if in a git repo)
- "I'll list the repos" → user provides list
Jira:
If 
HAS_JIRA_CLI
or 
HAS_ATLASSIAN_MCP
:
"I detected you have Jira configured. Want me to pull your tickets?"

Options:
- "Yes, pull my tickets"
- "No, I'll provide everything manually"
Claude Code用户注意：此阶段的所有问题请使用
AskUserQuestionTool
工具。
GitHub/Git：
如果检测到
HAS_GH
或
HAS_GIT
：
“我检测到你已配置GitHub/Git。是否需要我提取你近期的活动记录（提交、PR、评审）？”

选项：
- “是，提取相关信息”
- “否，我将手动提供所有内容”
如果用户选择是：
“我需要检查哪些仓库/项目？”

选项：
- “仅当前目录”（如果处于git仓库内）
- “我会列出仓库” → 用户提供仓库列表
Jira：
如果检测到
HAS_JIRA_CLI
或
HAS_ATLASSIAN_MCP
：
“我检测到你已配置Jira。是否需要我提取你的工单信息？”

选项：
- “是，提取我的工单”
- “否，我将手动提供所有内容”

Step 3: Pull GitHub/Jira Data (if approved)

步骤3：提取GitHub/Jira数据（如果获许）

GitHub/Git — For each approved repo:
  • Commits by user since yesterday
  • PRs opened/merged by user
  • Reviews done by user
Jira — Tickets assigned to user, updated in last 24h
Key insight: Store results to use as context in Phase 2 interview.
GitHub/Git — 针对每个获许的仓库：
  • 用户昨日以来的提交记录
  • 用户打开/合并的PR
  • 用户完成的评审
Jira — 过去24小时内更新的、分配给用户的工单
关键提示：保存提取结果，作为阶段2访谈的上下文。

Step 4: Offer Claude Code History

步骤4：提供Claude Code历史记录选项

This integration captures everything you worked on with Claude Code — useful for recalling work that isn't in git or Jira.
Detection:
bash
ls ~/.claude/projects/*/*.jsonl 2>/dev/null | head -1
If Claude Code history exists, ask:
"I can also pull your Claude Code session history from yesterday. This can help recall work that isn't in git/Jira (research, debugging, planning). Want me to check?"

Options:
- "Yes, pull my Claude Code sessions"
- "No, I have everything I need"
If yes, run the digest script:
bash
python3 ~/.claude/skills/daily-meeting-update/scripts/claude_digest.py --format json
Then present sessions with multiSelect:
Use 
AskUserQuestionTool
with 
multiSelect: true
to let user pick relevant items:
"Here are your Claude Code sessions from yesterday. Select the ones relevant to your standup:"

Options (multiSelect):
- "Fix authentication bug (backend-api)"
- "Implement OAuth flow (backend-api)"
- "Update homepage styles (frontend-app)"
- "Research payment providers (docs)"
Key insight: User selects which sessions are work-related. Personal projects or experiments can be excluded.
Do NOT run digest script when:
  • User explicitly says "No" to Claude Code history
  • User says they'll provide everything manually
  • ~/.claude/projects
    directory doesn't exist
If digest script fails:
  • Fallback: Skip Claude Code integration silently, proceed with interview
  • Common issues: Python not installed, no sessions from yesterday, permission errors
  • Do NOT block the standup flow — the script is supplemental, not required
此集成可捕获你在Claude Code上的所有工作内容——有助于回忆未记录在git或Jira中的工作。
检测方式：
bash
ls ~/.claude/projects/*/*.jsonl 2>/dev/null | head -1
如果存在Claude Code历史记录，询问用户：
“我还可以提取你昨日的Claude Code会话历史，这有助于回忆未记录在git/Jira中的工作（研究、调试、规划）。是否需要我提取？”

选项：
- “是，提取我的Claude Code会话记录”
- “否，我已有所需的全部内容”
如果用户选择是，执行摘要脚本：
bash
python3 ~/.claude/skills/daily-meeting-update/scripts/claude_digest.py --format json
然后通过多选功能展示会话记录：
使用
AskUserQuestionTool
工具并开启
multiSelect: true
，让用户选择相关项：
“以下是你昨日的Claude Code会话记录。请选择与站会相关的内容：”

选项（可多选）：
- “修复认证bug（backend-api）”
- “实现OAuth流程（backend-api）”
- “更新首页样式（frontend-app）”
- “研究支付提供商（docs）”
关键提示：用户可选择哪些会话与工作相关，个人项目或实验可排除在外。
以下情况请勿执行摘要脚本：
  • 用户明确拒绝提取Claude Code历史记录
  • 用户表示将手动提供所有内容
  • ~/.claude/projects
    目录不存在
如果摘要脚本执行失败：
  • 备选方案：静默跳过Claude Code集成，继续访谈流程
  • 常见问题：未安装Python、昨日无会话记录、权限错误
  • 请勿中断站会流程——该脚本仅作为补充，非必需项

Phase 2: Interview (with insights)

阶段2：带上下文的访谈

Claude Code users: Use 
AskUserQuestionTool
tool to conduct the interview. This provides a better UX with structured options.
Use pulled data as context to make questions smarter.
Claude Code用户注意：请使用
AskUserQuestionTool
工具开展访谈，这能提供更优的结构化交互体验。
利用提取的数据作为上下文，让问题更贴合实际。

Question 1: Yesterday

问题1：昨日工作

If data was pulled, show it first:
"Here's what I found from your activity:
- Merged PR #123: fix login timeout
- 3 commits in backend-api
- Reviewed PR #456 (approved)

Anything else you worked on yesterday that I missed?"
If no data pulled:
"What did you work on yesterday/since the last standup?"
If user response is vague, ask follow-up:
  • "Can you give more details about X?"
  • "Did you complete anything specific?"
如果已提取数据，先展示数据：
“我从你的活动记录中发现：
- 合并了PR #123：修复登录超时问题
- 在backend-api中有3次提交
- 评审了PR #456（已批准）

还有哪些昨日的工作是我未提取到的？”
如果未提取数据：
“你昨日/上次站会以来做了哪些工作？”
如果用户回答模糊，可追问：
  • “你能详细说说X相关的工作吗？”
  • “你有没有完成什么具体的任务？”

Question 2: Today

问题2：今日计划

"What will you work on today?"

Options:
- [Text input - user types freely]
If Jira data was pulled, you can suggest:
"I see you have these tickets assigned:
- PROJ-123: Implement OAuth flow (In Progress)
- PROJ-456: Fix payment bug (To Do)

Will you work on any of these today?"
“你今天将开展哪些工作？”

选项：
- [文本输入 - 用户自由填写]
如果已提取Jira数据，可给出建议：
“我看到你有以下工单待处理：
- PROJ-123：实现OAuth流程（进行中）
- PROJ-456：修复支付bug（待处理）

你今天会处理这些工单吗？”

Question 3: Blockers

问题3：遇到的阻碍

"Do you have any blockers or impediments?"

Options:
- "No blockers"
- "Yes, I have blockers" → follow-up for details
“你有没有遇到任何阻碍或障碍？”

选项：
- “没有阻碍”
- “有，我遇到了阻碍” → 追问细节

Question 4: Topics for Discussion

问题4：讨论议题

"Any topic you want to bring up at the end of the daily?"

Options:
- "No, nothing to discuss"
- "Yes" → follow-up for details

Examples of topics:
- Technical decision that needs input
- Alignment with another team
- Question about prioritization
- Announcement or info for the team
“站会末尾有什么需要讨论的议题吗？”

选项：
- “没有，无讨论内容”
- “有” → 追问细节

议题示例：
- 需要团队输入的技术决策
- 与其他团队的协作对齐
- 关于优先级的问题
- 团队公告或信息同步

Phase 3: Generate Update

阶段3：生成更新内容

Combine all information into clean Markdown:
markdown
undefined
将所有信息整合成简洁的Markdown格式：
markdown
undefined

Daily Update - [DATE]

每日更新 - [日期]

Yesterday

昨日工作

  • [Items from interview]
  • [Items from GitHub/Jira if pulled]
  • [访谈获取的内容]
  • [如果提取了数据，补充GitHub/Jira相关项]

Today

今日计划

  • [Items from interview]
  • [访谈获取的内容]

Blockers

遇到的阻碍

  • [Blockers or "No blockers"]
  • [阻碍内容或“无阻碍”]

PRs & Reviews (if pulled from GitHub)

PR与评审（如果从GitHub提取了数据）

  • [PRs opened]
  • [PRs merged]
  • [Reviews done]
  • [已打开的PR]
  • [已合并的PR]
  • [已完成的评审]

Jira (if pulled from Jira)

Jira工单（如果从Jira提取了数据）

  • [Tickets updated]
  • [已更新的工单]

Topics for Discussion

讨论议题

  • [Topics or "None"]
Links:
  • [PR links]
  • [Ticket links]

---
  • [议题内容或“无”]
链接：
  • [PR链接]
  • [工单链接]

---

Core Principles

核心原则

  1. Interview is primary — Tools supplement, they don't replace human context
  2. Consent before access — Always ask before pulling from any integration
  3. Context-aware questions — Show pulled data during interview to trigger memory ("I see you merged PR #123...")
  1. 访谈优先 —— 工具仅作为补充，不能替代人工提供的上下文
  2. 获取许可后再访问 —— 提取任何集成工具的数据前务必先询问用户
  3. 问题贴合上下文 —— 访谈时展示提取的数据，帮助用户回忆（“我看到你合并了PR #123...”）

Quick Reference

快速参考

PhaseActionTool
1. Detect & OfferCheck gh/jira/claude history, ask user, pull dataBash (silent), AskUserQuestionTool*
2. InterviewAsk 4 questions with insightsAskUserQuestionTool*
3. GenerateFormat MarkdownOutput text
*Claude Code only: Use 
AskUserQuestionTool
tool for structured questions.
阶段操作工具
1. 检测并提供检查gh/jira/claude历史记录，询问用户，提取数据Bash（静默执行）, AskUserQuestionTool*
2. 访谈结合上下文提出4个问题AskUserQuestionTool*
3. 生成格式化为Markdown输出文本
*仅Claude Code用户：使用
AskUserQuestionTool
工具进行结构化提问。

Claude Code Digest Script

Claude Code摘要脚本

bash
undefined
bash
undefined

Get yesterday's sessions as JSON

获取昨日的会话记录（JSON格式）

python3 ~/.claude/skills/daily-meeting-update/scripts/claude_digest.py --format json
python3 ~/.claude/skills/daily-meeting-update/scripts/claude_digest.py --format json

Get today's sessions

获取今日的会话记录

python3 ~/.claude/skills/daily-meeting-update/scripts/claude_digest.py --date today --format json
python3 ~/.claude/skills/daily-meeting-update/scripts/claude_digest.py --date today --format json

Filter to specific project

筛选特定项目

python3 ~/.claude/skills/daily-meeting-update/scripts/claude_digest.py --project ~/my-app --format json

---
python3 ~/.claude/skills/daily-meeting-update/scripts/claude_digest.py --project ~/my-app --format json

---

Example Session

会话示例

Claude: "Let's prepare your daily! I detected GitHub configured. Want me to pull your recent activity?"
User: "Yes"

Claude: "Which repos should I check?"
User: "backend-api and frontend-app"

[Claude pulls GitHub data silently]

Claude: "I can also pull your Claude Code session history from yesterday. Want me to check?"
User: "Yes"

[Claude runs digest script, gets 5 sessions]

Claude: "Here are your Claude Code sessions from yesterday. Select the ones relevant to your standup:"
  ☑ Fix authentication timeout bug (backend-api)
  ☑ Implement OAuth flow (backend-api)
  ☐ Update personal blog (blog) - [user unchecks personal project]
  ☑ Research payment providers (docs)
  ☐ Debugging test failures (experiments)

User: [selects 3 relevant items]

Claude: "Here's what I found from your activity:
- Merged PR #120: fix login timeout
- Opened PR #125: feat: add OAuth flow
- Reviewed PR #123 (approved), PR #456 (changes requested)
- 5 commits in backend-api
- [From Claude Code] Fix authentication timeout bug
- [From Claude Code] Implement OAuth flow
- [From Claude Code] Research payment providers

Anything else you worked on yesterday that I missed?"
User: "No, that covers it"

Claude: "What will you work on today?"
User: "Continue the OAuth feature and deploy to staging"

Claude: "Any blockers?"
User: "No"

Claude: "Any topic to bring up at the end of the daily?"
User: "Yes, I want to discuss the architecture of the new payments module"

[Claude generates update]
Claude: “让我们准备你的每日站会更新！我检测到你已配置GitHub，是否需要提取你近期的活动记录？”
用户: “是”

Claude: “我需要检查哪些仓库？”
用户: “backend-api和frontend-app”

[Claude静默提取GitHub数据]

Claude: “我还可以提取你昨日的Claude Code会话记录，是否需要提取？”
用户: “是”

[Claude执行摘要脚本，获取5条会话记录]

Claude: “以下是你昨日的Claude Code会话记录。请选择与站会相关的内容：”
  ☑ 修复认证超时bug（backend-api）
  ☑ 实现OAuth流程（backend-api）
  ☐ 更新个人博客（blog） - [用户取消选择个人项目]
  ☑ 研究支付提供商（docs）
  ☐ 调试测试失败问题（experiments）

用户: [选择3条相关内容]

Claude: “我从你的活动记录中发现：
- 合并了PR #120：修复登录超时
- 打开了PR #125：feat: 添加OAuth流程
- 评审了PR #123（已批准）、PR #456（要求修改）
- 在backend-api中有5次提交
- [来自Claude Code] 修复认证超时bug
- [来自Claude Code] 实现OAuth流程
- [来自Claude Code] 研究支付提供商

还有哪些昨日的工作是我未提取到的？”
用户: “没有，这些已经涵盖了”

Claude: “你今天将开展哪些工作？”
用户: “继续开发OAuth功能并部署到预发布环境”

Claude: “有没有遇到任何阻碍？”
用户: “没有”

Claude: “站会末尾有什么需要讨论的议题吗？”
用户: “有，我想讨论新支付模块的架构”

[Claude生成更新内容]

Output Example

输出示例

markdown
undefined
markdown
undefined

Daily Update - 2026-01-22

每日更新 - 2026-01-22

Yesterday

昨日工作

  • Worked on authentication feature
  • Research on payment providers
  • Merged PR #120 (fix: login timeout)
  • Opened PR #125 (feat: add OAuth flow)
  • 开发认证功能
  • 研究支付提供商
  • 合并了PR #120（修复：登录超时）
  • 打开了PR #125（新增：添加OAuth流程）

Today

今日计划

  • Continue OAuth feature
  • Deploy to staging
  • 继续开发OAuth功能
  • 部署到预发布环境

Blockers

遇到的阻碍

  • No blockers
  • 无阻碍

PRs & Reviews

PR与评审

  • Opened: PR #125 - feat: add OAuth flow
  • Merged: PR #120 - fix: login timeout
  • Reviews: PR #123 (approved), PR #456 (changes requested)
  • 已打开： PR #125 - 新增：添加OAuth流程
  • 已合并： PR #120 - 修复：登录超时
  • 已评审： PR #123（已批准）、PR #456（要求修改）

Topics for Discussion

讨论议题

  • Architecture of the new payments module
Links:

---
  • 新支付模块的架构
链接：

---

Anti-Patterns

反模式

AvoidWhy (Expert Knowledge)Instead
Run gh/jira without askingUsers may have personal repos visible, or be in a sensitive project context they don't want exposedAlways ask first, let user choose repos
Assume current directory is the only projectDevelopers often work on 2-5 repos simultaneously (frontend, backend, infra)Ask "Which projects are you working on?"
Skip interview even with tool dataTools capture WHAT happened but miss WHY and context (research, meetings, planning)Interview is primary, tools supplement
Generate update before all 4 questionsUser might have critical blocker or discussion topic that changes the narrativeComplete interview, then generate
Include raw commit messagesCommit messages are often cryptic ("fix", "wip") and don't tell the storySummarize into human-readable outcomes
Ask for data after interviewShowing insights during interview makes questions smarter ("I see you merged PR #123, anything else?")Pull data first, then interview with context
需避免的做法原因（专业经验）正确做法
未询问就提取gh/jira数据用户可能有个人仓库可见，或处于敏感项目环境中，不希望数据被暴露务必先询问用户，让用户选择要提取的仓库
假设当前目录是唯一的项目开发者通常同时处理2-5个仓库（前端、后端、基础设施）询问“你正在处理哪些项目？”
即使有工具数据也跳过访谈工具只能记录“做了什么”，但无法记录“为什么做”及相关上下文（研究、会议、规划）访谈优先，工具仅作为补充
未完成4个问题就生成更新内容用户可能有重要的阻碍或讨论议题，会改变更新内容的整体叙事完成所有访谈问题后再生成更新
包含原始提交信息提交信息通常晦涩难懂（如“fix”“wip”），无法完整呈现工作内容总结为易于理解的成果
访谈后才提取数据访谈时展示提取的上下文能让问题更贴合实际（“我看到你合并了PR #123，还有其他工作吗？”）先提取数据，再结合上下文开展访谈

NEVER

绝对禁止

  • NEVER assume tools are configured — Many devs have gh installed but not authenticated, or jira CLI pointing to wrong instance
  • NEVER skip the "Topics for Discussion" question — This is often the most valuable part of standup that tools can't capture
  • NEVER generate more than 15 bullets — Standup should be <2 minutes to read; long updates lose the audience
  • NEVER include ticket/PR numbers without context — "PROJ-123" means nothing; always include title or summary
  • NEVER pull data from repos user didn't explicitly approve — Even if you can see other repos, respect boundaries
  • 绝对不要假设工具已配置完成 —— 很多开发者安装了gh但未认证，或jira CLI指向错误的实例
  • 绝对不要跳过“讨论议题”问题 —— 这通常是站会中最有价值的部分，工具无法捕获相关内容
  • 绝对不要生成超过15个项目符号 —— 站会内容应在2分钟内读完；过长的更新会失去受众注意力
  • 绝对不要只包含工单/PR编号而无上下文 —— “PROJ-123”毫无意义；务必附带标题或摘要
  • 绝对不要提取用户未明确批准的仓库数据 —— 即使你能看到其他仓库，也要尊重用户边界