jpskill.com
💼 ビジネス コミュニティ

daily-meeting-update

日々の朝会や進捗報告で、GitHubやJiraなどの情報をもとに、昨日やったこと、今日やること、課題、相談事項を質問形式で聞き出し、Markdown形式でまとまった報告文を自動作成するSkill。

📜 元の英語説明(参考)

Interactive daily standup/meeting update generator. Use when user says 'daily', 'standup', 'scrum update', 'status update', 'what did I do yesterday', 'prepare for meeting', 'morning update', or 'team sync'. Pulls activity from GitHub, Jira, and Claude Code session history. Conducts 4-question interview (yesterday, today, blockers, discussion topics) and generates formatted Markdown update.

🇯🇵 日本人クリエイター向け解説

一言でいうと

日々の朝会や進捗報告で、GitHubやJiraなどの情報をもとに、昨日やったこと、今日やること、課題、相談事項を質問形式で聞き出し、Markdown形式でまとまった報告文を自動作成するSkill。

※ jpskill.com 編集部が日本のビジネス現場向けに補足した解説です。Skill本体の挙動とは独立した参考情報です。

⚡ おすすめ: コマンド1行でインストール(60秒)

下記のコマンドをコピーしてターミナル(Mac/Linux)または PowerShell(Windows)に貼り付けてください。 ダウンロード → 解凍 → 配置まで全自動。

🍎 Mac / 🐧 Linux
mkdir -p ~/.claude/skills && cd ~/.claude/skills && curl -L -o daily-meeting-update.zip https://jpskill.com/download/20846.zip && unzip -o daily-meeting-update.zip && rm daily-meeting-update.zip
🪟 Windows (PowerShell)
$d = "$env:USERPROFILE\.claude\skills"; ni -Force -ItemType Directory $d | Out-Null; iwr https://jpskill.com/download/20846.zip -OutFile "$d\daily-meeting-update.zip"; Expand-Archive "$d\daily-meeting-update.zip" -DestinationPath $d -Force; ri "$d\daily-meeting-update.zip"

完了後、Claude Code を再起動 → 普通に「動画プロンプト作って」のように話しかけるだけで自動発動します。

💾 手動でダウンロードしたい(コマンドが難しい人向け)
  1. 1. 下の青いボタンを押して daily-meeting-update.zip をダウンロード
  2. 2. ZIPファイルをダブルクリックで解凍 → daily-meeting-update フォルダができる
  3. 3. そのフォルダを C:\Users\あなたの名前\.claude\skills\(Win)または ~/.claude/skills/(Mac)へ移動
  4. 4. Claude Code を再起動

⚠️ ダウンロード・利用は自己責任でお願いします。当サイトは内容・動作・安全性について責任を負いません。

🎯 このSkillでできること

下記の説明文を読むと、このSkillがあなたに何をしてくれるかが分かります。Claudeにこの分野の依頼をすると、自動で発動します。

📦 インストール方法 (3ステップ)

  1. 1. 上の「ダウンロード」ボタンを押して .skill ファイルを取得
  2. 2. ファイル名の拡張子を .skill から .zip に変えて展開(macは自動展開可)
  3. 3. 展開してできたフォルダを、ホームフォルダの .claude/skills/ に置く
    • · macOS / Linux: ~/.claude/skills/
    • · Windows: %USERPROFILE%\.claude\skills\

Claude Code を再起動すれば完了。「このSkillを使って…」と話しかけなくても、関連する依頼で自動的に呼び出されます。

詳しい使い方ガイドを見る →
最終更新
2026-05-18
取得日時
2026-05-18
同梱ファイル
3

📖 Skill本文(日本語訳)

※ 原文(英語/中国語)を Gemini で日本語化したものです。Claude 自身は原文を読みます。誤訳がある場合は原文をご確認ください。

[スキル名] daily-meeting-update

デイリーミーティング更新

対話形式のインタビューを通じて、デイリースタンドアップ/ミーティングの更新を生成します。ツールが設定されていると決して仮定せず、まず尋ねてください。


ワークフロー

START
  │
  ▼
┌─────────────────────────────────────────────────────┐
│ フェーズ1: 統合の検出と提案                      │
│ • 確認: Claude Code履歴? gh CLI? jira CLI?          │
│ • Claude Code → 昨日のセッションダイジェストをプル│
│   → ユーザーがマルチセレクトで関連アイテムを選択    │
│ • GitHub/Jira → ユーザーに尋ね、承認されればプル    │
│ • データは今すぐプルする (インタビュー前)           │
├─────────────────────────────────────────────────────┤
│ フェーズ2: インタビュー (洞察を伴う)                │
│ • プルしたデータをコンテキストとして表示            │
│ • 昨日: 「PR #123をマージしましたね、他に何か?」   │
│ • 今日: 何に取り組みますか?                        │
│ • ブロッカー: 何か妨げになっていることはありますか?│
│ • トピック: ミーティングの最後に議論したいことは?  │
├─────────────────────────────────────────────────────┤
│ フェーズ3: 更新の生成                              │
│ • インタビューの回答 + ツールデータを結合           │
│ • 整然としたMarkdown形式でフォーマット              │
│ • ユーザーに提示                                    │
└─────────────────────────────────────────────────────┘

フェーズ1: 統合の検出と提案

ステップ1: サイレント検出

利用可能な統合をサイレントにチェックします(エラーを抑制し、ユーザーには表示しません)。

統合 検出
Claude Code履歴 ~/.claude/projects ディレクトリに .jsonl ファイルが存在する
GitHub CLI gh auth status が成功する
Jira CLI jira コマンドが存在する
Atlassian MCP mcp__atlassian__* ツールが利用可能
Git Gitリポジトリ内である

ステップ2: GitHub/Jira統合の提案 (利用可能な場合)

Claude Codeユーザーの方へ: このフェーズのすべての質問には AskUserQuestionTool ツールを使用してください。

GitHub/Git:

HAS_GH または HAS_GIT の場合:

"GitHub/Gitが設定されていることを検出しました。最近のアクティビティ(コミット、PR、レビュー)をプルしますか?"

オプション:
- "はい、情報をプルしてください"
- "いいえ、すべて手動で提供します"

「はい」の場合:

"どのリポジトリ/プロジェクトをチェックすればよいですか?"

オプション:
- "現在のディレクトリのみ" (Gitリポジトリ内の場合)
- "リポジトリをリストします" → ユーザーがリストを提供

Jira:

HAS_JIRA_CLI または HAS_ATLASSIAN_MCP の場合:

"Jiraが設定されていることを検出しました。チケットをプルしますか?"

オプション:
- "はい、チケットをプルしてください"
- "いいえ、すべて手動で提供します"

ステップ3: GitHub/Jiraデータのプル (承認された場合)

GitHub/Git — 承認された各リポジトリについて:

  • 昨日以降のユーザーによるコミット
  • ユーザーが開いた/マージしたPR
  • ユーザーが行ったレビュー

Jira — ユーザーに割り当てられ、過去24時間以内に更新されたチケット

重要な洞察: フェーズ2のインタビューでコンテキストとして使用するために結果を保存します。

ステップ4: Claude Code履歴の提案

この統合は、Claude Codeで作業したすべてをキャプチャします。GitやJiraにない作業を思い出すのに役立ちます。

検出:

ls ~/.claude/projects/*/*.jsonl 2>/dev/null | head -1

Claude Code履歴が存在する場合、尋ねます:

"昨日のClaude Codeセッション履歴もプルできます。これは、Git/Jiraにない作業(調査、デバッグ、計画)を思い出すのに役立ちます。確認しますか?"

オプション:
- "はい、Claude Codeセッションをプルしてください"
- "いいえ、必要なものはすべて揃っています"

「はい」の場合、ダイジェストスクリプトを実行します:

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

次に、マルチセレクトでセッションを提示します:

AskUserQuestionToolmultiSelect: true とともに使用して、ユーザーが関連するアイテムを選択できるようにします。

"昨日のClaude Codeセッションです。スタンドアップに関連するものを選択してください:"

オプション (multiSelect):
- "認証バグを修正 (backend-api)"
- "OAuthフローを実装 (backend-api)"
- "ホームページのスタイルを更新 (frontend-app)"
- "決済プロバイダーを調査 (docs)"

重要な洞察: ユーザーはどのセッションが仕事関連であるかを選択します。個人的なプロジェクトや実験は除外できます。

ダイジェストスクリプトを実行しない場合:

  • ユーザーがClaude Code履歴に対して明示的に「いいえ」と言った場合
  • ユーザーがすべて手動で提供すると言った場合
  • ~/.claude/projects ディレクトリが存在しない場合

ダイジェストスクリプトが失敗した場合:

  • フォールバック: Claude Code統合をサイレントにスキップし、インタビューに進みます
  • 一般的な問題: Pythonがインストールされていない、昨日からのセッションがない、権限エラー
  • スタンドアップフローをブロックしないでください — スクリプトは補足的なものであり、必須ではありません

フェーズ2: インタビュー (洞察を伴う)

Claude Codeユーザーの方へ: インタビューを行うには AskUserQuestionTool ツールを使用してください。これにより、構造化されたオプションでより良いUXが提供されます。

プルしたデータをコンテキストとして使用して、質問をよりスマートにします。

質問1: 昨日

データがプルされた場合、まずそれを表示します。

"あなたのアクティビティから見つかったものです:
- PR #123をマージ: ログインタイムアウトを修正
- backend-apiで3つのコミット
- PR #456をレビュー (承認済み)

他に昨日作業したことで、私が見落としていることはありますか?"

データがプルされなかった場合:

"昨日/前回のスタンドアップ以降、何に取り組みましたか?"

ユーザーの回答が曖昧な場合は、フォローアップを尋ねます。

  • 「Xについてもっと詳しく教えていただけますか?」
  • 「何か具体的なことを完了しましたか?」

質問2: 今日

"今日、何に取り組みますか?"

オプション:
- [テキスト入力 - ユーザーが自由にタイプ]

Jiraデータがプルされた場合、提案できます。

"以下のチケットが割り当てられているようです:
- PROJ-123: OAuthフローを実装 (進行中)
- PROJ-456: 支払いバグを修正 (未着手)

今日、これらのいずれかに取り組みますか?"

質問3: ブロッカー

"何かブロッカーや障害はありますか?"

オプション:
- "ブロッカーはありません"
- "はい、ブロッカーがあります" → 詳細をフォローアップ

質問4: 議論するトピック

"デイリーの最後に何か議題にしたいことはありますか?"

オプション:
- "いいえ、議論することはありません"
- "はい" → 詳細をフォローアップ

トピックの例:
- 入力が必要な技術的決定
- 他のチームとの連携
- 優先順位に関する質問
- 発表
📜 原文 SKILL.md(Claudeが読む英語/中国語)を展開

Daily Meeting Update

Generate a daily standup/meeting update through an interactive interview. Never assume tools are configured—ask first.


Workflow

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                                   │
└─────────────────────────────────────────────────────┘

Phase 1: Detect & Offer Integrations

Step 1: Silent Detection

Check for available integrations silently (suppress errors, don't show to user):

Integration Detection
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
Git Inside a git repository

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

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"

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

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.

Step 4: Offer Claude Code History

This integration captures everything you worked on with Claude Code — useful for recalling work that isn't in git or Jira.

Detection:

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:

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

Phase 2: Interview (with insights)

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.

Question 1: Yesterday

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?"

Question 2: Today

"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?"

Question 3: Blockers

"Do you have any blockers or impediments?"

Options:
- "No blockers"
- "Yes, I have blockers" → follow-up for details

Question 4: Topics for Discussion

"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

Phase 3: Generate Update

Combine all information into clean Markdown:

# Daily Update - [DATE]

## Yesterday
- [Items from interview]
- [Items from GitHub/Jira if pulled]

## Today
- [Items from interview]

## Blockers
- [Blockers or "No blockers"]

## PRs & Reviews (if pulled from GitHub)
- [PRs opened]
- [PRs merged]
- [Reviews done]

## Jira (if pulled from Jira)
- [Tickets updated]

## Topics for Discussion
- [Topics or "None"]

---
*Links:*
- [PR links]
- [Ticket links]

Core Principles

  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...")

Quick Reference

Phase Action Tool
1. Detect & Offer Check gh/jira/claude history, ask user, pull data Bash (silent), AskUserQuestionTool*
2. Interview Ask 4 questions with insights AskUserQuestionTool*
3. Generate Format Markdown Output text

*Claude Code only: Use AskUserQuestionTool tool for structured questions.

Claude Code Digest Script

# Get yesterday's sessions as JSON
python3 ~/.claude/skills/daily-meeting-update/scripts/claude_digest.py --format json

# Get today's sessions
python3 ~/.claude/skills/daily-meeting-update/scripts/claude_digest.py --date today --format json

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

Example Session

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]

Output Example

# Daily Update - 2026-01-22

## Yesterday
- Worked on authentication feature
- Research on payment providers
- Merged PR #120 (fix: login timeout)
- Opened PR #125 (feat: add OAuth flow)

## Today
- Continue OAuth feature
- Deploy to staging

## Blockers
- No blockers

## PRs & Reviews
- **Opened:** PR #125 - feat: add OAuth flow
- **Merged:** PR #120 - fix: login timeout
- **Reviews:** PR #123 (approved), PR #456 (changes requested)

## Topics for Discussion
- Architecture of the new payments module

---
*Links:*
- https://github.com/org/repo/pull/125
- https://github.com/org/repo/pull/120

Anti-Patterns

Avoid Why (Expert Knowledge) Instead
Run gh/jira without asking Users may have personal repos visible, or be in a sensitive project context they don't want exposed Always ask first, let user choose repos
Assume current directory is the only project Developers often work on 2-5 repos simultaneously (frontend, backend, infra) Ask "Which projects are you working on?"
Skip interview even with tool data Tools capture WHAT happened but miss WHY and context (research, meetings, planning) Interview is primary, tools supplement
Generate update before all 4 questions User might have critical blocker or discussion topic that changes the narrative Complete interview, then generate
Include raw commit messages Commit messages are often cryptic ("fix", "wip") and don't tell the story Summarize into human-readable outcomes
Ask for data after interview Showing insights during interview makes questions smarter ("I see you merged PR #123, anything else?") Pull data first, then interview with context

NEVER

  • 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

同梱ファイル

※ ZIPに含まれるファイル一覧。`SKILL.md` 本体に加え、参考資料・サンプル・スクリプトが入っている場合があります。