[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AF19Y1J0FDNNX9GXMTYQ7Z":3,"skill-same:01M6AF19Y1J0FDNNX9GXMTYQ7Z":87},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":74},"01M6AF19Y1J0FDNNX9GXMTYQ7Z","daily-meeting-update",null,"Interactive daily standup\u002Fmeeting 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.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fdaily-meeting-update\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"meeting","update","daily meeting update","daily","question","status update","prepare for meeting","when","activity","session history","do","scrum","interview","github","daily standup","markdown","team","code","jira","prepare","status","sync","2026-11-10 10:12:30",false,"---\nname: daily-meeting-update\ndescription: \"Interactive daily standup\u002Fmeeting 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.\"\nuser-invocable: true\n---\n\n# Daily Meeting Update\n\nGenerate a daily standup\u002Fmeeting update through an **interactive interview**. Never assume tools are configured—ask first.\n\n---\n\n## Workflow\n\n```\nSTART\n  │\n  ▼\n┌─────────────────────────────────────────────────────┐\n│ Phase 1: DETECT & OFFER INTEGRATIONS                │\n│ • Check: Claude Code history? gh CLI? jira CLI?     │\n│ • Claude Code → Pull yesterday's session digest     │\n│   → User selects relevant items via multiSelect     │\n│ • GitHub\u002FJira → Ask user, pull if approved          │\n│ • Pull data NOW (before interview)                  │\n├─────────────────────────────────────────────────────┤\n│ Phase 2: INTERVIEW (with insights)                  │\n│ • Show pulled data as context                       │\n│ • Yesterday: \"I see you merged PR #123, what else?\" │\n│ • Today: What will you work on?                     │\n│ • Blockers: Anything blocking you?                  │\n│ • Topics: Anything to discuss at end of meeting?    │\n├─────────────────────────────────────────────────────┤\n│ Phase 3: GENERATE UPDATE                            │\n│ • Combine interview answers + tool data             │\n│ • Format as clean Markdown                          │\n│ • Present to user                                   │\n└─────────────────────────────────────────────────────┘\n```\n\n---\n\n## Phase 1: Detect & Offer Integrations\n\n### Step 1: Silent Detection\n\nCheck for available integrations **silently** (suppress errors, don't show to user):\n\n| Integration | Detection |\n|-------------|-----------|\n| **Claude Code History** | `~\u002F.claude\u002Fprojects` directory exists with `.jsonl` files |\n| GitHub CLI | `gh auth status` succeeds |\n| Jira CLI | `jira` command exists |\n| Atlassian MCP | `mcp__atlassian__*` tools available |\n| Git | Inside a git repository |\n\n### Step 2: Offer GitHub\u002FJira Integrations (if available)\n\n> **Claude Code users:** Use `AskUserQuestionTool` tool for all questions in this phase.\n\n**GitHub\u002FGit:**\n\nIf `HAS_GH` or `HAS_GIT`:\n\n```\n\"I detected you have GitHub\u002FGit configured. Want me to pull your recent activity (commits, PRs, reviews)?\"\n\nOptions:\n- \"Yes, pull the info\"\n- \"No, I'll provide everything manually\"\n```\n\nIf yes:\n\n```\n\"Which repositories\u002Fprojects should I check?\"\n\nOptions:\n- \"Just the current directory\" (if in a git repo)\n- \"I'll list the repos\" → user provides list\n```\n\n**Jira:**\n\nIf `HAS_JIRA_CLI` or `HAS_ATLASSIAN_MCP`:\n\n```\n\"I detected you have Jira configured. Want me to pull your tickets?\"\n\nOptions:\n- \"Yes, pull my tickets\"\n- \"No, I'll provide everything manually\"\n```\n\n### Step 3: Pull GitHub\u002FJira Data (if approved)\n\n**GitHub\u002FGit** — For each approved repo:\n- Commits by user since yesterday\n- PRs opened\u002Fmerged by user\n- Reviews done by user\n\n**Jira** — Tickets assigned to user, updated in last 24h\n\n**Key insight**: Store results to use as context in Phase 2 interview.\n\n### Step 4: Offer Claude Code History\n\nThis integration captures everything you worked on with Claude Code — useful for recalling work that isn't in git or Jira.\n\n**Detection:**\n```bash\nls ~\u002F.claude\u002Fprojects\u002F*\u002F*.jsonl 2>\u002Fdev\u002Fnull | head -1\n```\n\n**If Claude Code history exists, ask:**\n\n```\n\"I can also pull your Claude Code session history from yesterday. This can help recall work that isn't in git\u002FJira (research, debugging, planning). Want me to check?\"\n\nOptions:\n- \"Yes, pull my Claude Code sessions\"\n- \"No, I have everything I need\"\n```\n\n**If yes, run the digest script:**\n\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fdaily-meeting-update\u002Fscripts\u002Fclaude_digest.py --format json\n```\n\n**Then present sessions with multiSelect:**\n\nUse `AskUserQuestionTool` with `multiSelect: true` to let user pick relevant items:\n\n```\n\"Here are your Claude Code sessions from yesterday. Select the ones relevant to your standup:\"\n\nOptions (multiSelect):\n- \"Fix authentication bug (backend-api)\"\n- \"Implement OAuth flow (backend-api)\"\n- \"Update homepage styles (frontend-app)\"\n- \"Research payment providers (docs)\"\n```\n\n**Key insight:** User selects which sessions are work-related. Personal projects or experiments can be excluded.\n\n**Do NOT run digest script when:**\n- User explicitly says \"No\" to Claude Code history\n- User says they'll provide everything manually\n- `~\u002F.claude\u002Fprojects` directory doesn't exist\n\n**If digest script fails:**\n- Fallback: Skip Claude Code integration silently, proceed with interview\n- Common issues: Python not installed, no sessions from yesterday, permission errors\n- Do NOT block the standup flow — the script is supplemental, not required\n\n---\n\n## Phase 2: Interview (with insights)\n\n> **Claude Code users:** Use `AskUserQuestionTool` tool to conduct the interview. This provides a better UX with structured options.\n\n**Use pulled data as context** to make questions smarter.\n\n### Question 1: Yesterday\n\n**If data was pulled**, show it first:\n\n```\n\"Here's what I found from your activity:\n- Merged PR #123: fix login timeout\n- 3 commits in backend-api\n- Reviewed PR #456 (approved)\n\nAnything else you worked on yesterday that I missed?\"\n```\n\n**If no data pulled:**\n\n```\n\"What did you work on yesterday\u002Fsince the last standup?\"\n```\n\nIf user response is vague, ask follow-up:\n- \"Can you give more details about X?\"\n- \"Did you complete anything specific?\"\n\n### Question 2: Today\n\n```\n\"What will you work on today?\"\n\nOptions:\n- [Text input - user types freely]\n```\n\n**If Jira data was pulled**, you can suggest:\n\n```\n\"I see you have these tickets assigned:\n- PROJ-123: Implement OAuth flow (In Progress)\n- PROJ-456: Fix payment bug (To Do)\n\nWill you work on any of these today?\"\n```\n\n### Question 3: Blockers\n\n```\n\"Do you have any blockers or impediments?\"\n\nOptions:\n- \"No blockers\"\n- \"Yes, I have blockers\" → follow-up for details\n```\n\n### Question 4: Topics for Discussion\n\n```\n\"Any topic you want to bring up at the end of the daily?\"\n\nOptions:\n- \"No, nothing to discuss\"\n- \"Yes\" → follow-up for details\n\nExamples of topics:\n- Technical decision that needs input\n- Alignment with another team\n- Question about prioritization\n- Announcement or info for the team\n```\n\n---\n\n## Phase 3: Generate Update\n\nCombine all information into clean Markdown:\n\n```markdown\n# Daily Update - [DATE]\n\n## Yesterday\n- [Items from interview]\n- [Items from GitHub\u002FJira if pulled]\n\n## Today\n- [Items from interview]\n\n## Blockers\n- [Blockers or \"No blockers\"]\n\n## PRs & Reviews (if pulled from GitHub)\n- [PRs opened]\n- [PRs merged]\n- [Reviews done]\n\n## Jira (if pulled from Jira)\n- [Tickets updated]\n\n## Topics for Discussion\n- [Topics or \"None\"]\n\n---\n*Links:*\n- [PR links]\n- [Ticket links]\n```\n\n---\n\n## Core Principles\n\n1. **Interview is primary** — Tools supplement, they don't replace human context\n2. **Consent before access** — Always ask before pulling from any integration\n3. **Context-aware questions** — Show pulled data during interview to trigger memory (\"I see you merged PR #123...\")\n\n---\n\n## Quick Reference\n\n| Phase | Action | Tool |\n|-------|--------|------|\n| 1. Detect & Offer | Check gh\u002Fjira\u002Fclaude history, ask user, pull data | Bash (silent), AskUserQuestionTool* |\n| 2. Interview | Ask 4 questions with insights | AskUserQuestionTool* |\n| 3. Generate | Format Markdown | Output text |\n\n*Claude Code only: Use `AskUserQuestionTool` tool for structured questions.\n\n### Claude Code Digest Script\n\n```bash\n# Get yesterday's sessions as JSON\npython3 ~\u002F.claude\u002Fskills\u002Fdaily-meeting-update\u002Fscripts\u002Fclaude_digest.py --format json\n\n# Get today's sessions\npython3 ~\u002F.claude\u002Fskills\u002Fdaily-meeting-update\u002Fscripts\u002Fclaude_digest.py --date today --format json\n\n# Filter to specific project\npython3 ~\u002F.claude\u002Fskills\u002Fdaily-meeting-update\u002Fscripts\u002Fclaude_digest.py --project ~\u002Fmy-app --format json\n```\n\n---\n\n## Example Session\n\n```\nClaude: \"Let's prepare your daily! I detected GitHub configured. Want me to pull your recent activity?\"\nUser: \"Yes\"\n\nClaude: \"Which repos should I check?\"\nUser: \"backend-api and frontend-app\"\n\n[Claude pulls GitHub data silently]\n\nClaude: \"I can also pull your Claude Code session history from yesterday. Want me to check?\"\nUser: \"Yes\"\n\n[Claude runs digest script, gets 5 sessions]\n\nClaude: \"Here are your Claude Code sessions from yesterday. Select the ones relevant to your standup:\"\n  ☑ Fix authentication timeout bug (backend-api)\n  ☑ Implement OAuth flow (backend-api)\n  ☐ Update personal blog (blog) - [user unchecks personal project]\n  ☑ Research payment providers (docs)\n  ☐ Debugging test failures (experiments)\n\nUser: [selects 3 relevant items]\n\nClaude: \"Here's what I found from your activity:\n- Merged PR #120: fix login timeout\n- Opened PR #125: feat: add OAuth flow\n- Reviewed PR #123 (approved), PR #456 (changes requested)\n- 5 commits in backend-api\n- [From Claude Code] Fix authentication timeout bug\n- [From Claude Code] Implement OAuth flow\n- [From Claude Code] Research payment providers\n\nAnything else you worked on yesterday that I missed?\"\nUser: \"No, that covers it\"\n\nClaude: \"What will you work on today?\"\nUser: \"Continue the OAuth feature and deploy to staging\"\n\nClaude: \"Any blockers?\"\nUser: \"No\"\n\nClaude: \"Any topic to bring up at the end of the daily?\"\nUser: \"Yes, I want to discuss the architecture of the new payments module\"\n\n[Claude generates update]\n```\n\n---\n\n## Output Example\n\n```markdown\n# Daily Update - 2026-01-22\n\n## Yesterday\n- Worked on authentication feature\n- Research on payment providers\n- Merged PR #120 (fix: login timeout)\n- Opened PR #125 (feat: add OAuth flow)\n\n## Today\n- Continue OAuth feature\n- Deploy to staging\n\n## Blockers\n- No blockers\n\n## PRs & Reviews\n- **Opened:** PR #125 - feat: add OAuth flow\n- **Merged:** PR #120 - fix: login timeout\n- **Reviews:** PR #123 (approved), PR #456 (changes requested)\n\n## Topics for Discussion\n- Architecture of the new payments module\n\n---\n*Links:*\n- https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fpull\u002F125\n- https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fpull\u002F120\n```\n\n---\n\n## Anti-Patterns\n\n| Avoid | Why (Expert Knowledge) | Instead |\n|-------|------------------------|---------|\n| Run gh\u002Fjira 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 |\n| 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?\" |\n| Skip interview even with tool data | Tools capture WHAT happened but miss WHY and context (research, meetings, planning) | Interview is primary, tools supplement |\n| Generate update before all 4 questions | User might have critical blocker or discussion topic that changes the narrative | Complete interview, then generate |\n| Include raw commit messages | Commit messages are often cryptic (\"fix\", \"wip\") and don't tell the story | Summarize into human-readable outcomes |\n| 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 |\n\n---\n\n## NEVER\n\n- **NEVER assume tools are configured** — Many devs have gh installed but not authenticated, or jira CLI pointing to wrong instance\n- **NEVER skip the \"Topics for Discussion\" question** — This is often the most valuable part of standup that tools can't capture\n- **NEVER generate more than 15 bullets** — Standup should be \u003C2 minutes to read; long updates lose the audience\n- **NEVER include ticket\u002FPR numbers without context** — \"PROJ-123\" means nothing; always include title or summary\n- **NEVER pull data from repos user didn't explicitly approve** — Even if you can see other repos, respect boundaries\n","# Daily Meeting Update\n\nGenerate a daily standup\u002Fmeeting update through an **interactive interview**. Never assume tools are configured—ask first.\n\n---\n\n## Workflow\n\n```\nSTART\n  │\n  ▼\n┌─────────────────────────────────────────────────────┐\n│ Phase 1: DETECT & OFFER INTEGRATIONS                │\n│ • Check: Claude Code history? gh CLI? jira CLI?     │\n│ • Claude Code → Pull yesterday's session digest     │\n│   → User selects relevant items via multiSelect     │\n│ • GitHub\u002FJira → Ask user, pull if approved          │\n│ • Pull data NOW (before interview)                  │\n├─────────────────────────────────────────────────────┤\n│ Phase 2: INTERVIEW (with insights)                  │\n│ • Show pulled data as context                       │\n│ • Yesterday: \"I see you merged PR #123, what else?\" │\n│ • Today: What will you work on?                     │\n│ • Blockers: Anything blocking you?                  │\n│ • Topics: Anything to discuss at end of meeting?    │\n├─────────────────────────────────────────────────────┤\n│ Phase 3: GENERATE UPDATE                            │\n│ • Combine interview answers + tool data             │\n│ • Format as clean Markdown                          │\n│ • Present to user                                   │\n└─────────────────────────────────────────────────────┘\n```\n\n---\n\n## Phase 1: Detect & Offer Integrations\n\n### Step 1: Silent Detection\n\nCheck for available integrations **silently** (suppress errors, don't show to user):\n\n| Integration | Detection |\n|-------------|-----------|\n| **Claude Code History** | `~\u002F.claude\u002Fprojects` directory exists with `.jsonl` files |\n| GitHub CLI | `gh auth status` succeeds |\n| Jira CLI | `jira` command exists |\n| Atlassian MCP | `mcp__atlassian__*` tools available |\n| Git | Inside a git repository |\n\n### Step 2: Offer GitHub\u002FJira Integrations (if available)\n\n> **Claude Code users:** Use `AskUserQuestionTool` tool for all questions in this phase.\n\n**GitHub\u002FGit:**\n\nIf `HAS_GH` or `HAS_GIT`:\n\n```\n\"I detected you have GitHub\u002FGit configured. Want me to pull your recent activity (commits, PRs, reviews)?\"\n\nOptions:\n- \"Yes, pull the info\"\n- \"No, I'll provide everything manually\"\n```\n\nIf yes:\n\n```\n\"Which repositories\u002Fprojects should I check?\"\n\nOptions:\n- \"Just the current directory\" (if in a git repo)\n- \"I'll list the repos\" → user provides list\n```\n\n**Jira:**\n\nIf `HAS_JIRA_CLI` or `HAS_ATLASSIAN_MCP`:\n\n```\n\"I detected you have Jira configured. Want me to pull your tickets?\"\n\nOptions:\n- \"Yes, pull my tickets\"\n- \"No, I'll provide everything manually\"\n```\n\n### Step 3: Pull GitHub\u002FJira Data (if approved)\n\n**GitHub\u002FGit** — For each approved repo:\n- Commits by user since yesterday\n- PRs opened\u002Fmerged by user\n- Reviews done by user\n\n**Jira** — Tickets assigned to user, updated in last 24h\n\n**Key insight**: Store results to use as context in Phase 2 interview.\n\n### Step 4: Offer Claude Code History\n\nThis integration captures everything you worked on with Claude Code — useful for recalling work that isn't in git or Jira.\n\n**Detection:**\n```bash\nls ~\u002F.claude\u002Fprojects\u002F*\u002F*.jsonl 2>\u002Fdev\u002Fnull | head -1\n```\n\n**If Claude Code history exists, ask:**\n\n```\n\"I can also pull your Claude Code session history from yesterday. This can help recall work that isn't in git\u002FJira (research, debugging, planning). Want me to check?\"\n\nOptions:\n- \"Yes, pull my Claude Code sessions\"\n- \"No, I have everything I need\"\n```\n\n**If yes, run the digest script:**\n\n```bash\npython3 ~\u002F.claude\u002Fskills\u002Fdaily-meeting-update\u002Fscripts\u002Fclaude_digest.py --format json\n```\n\n**Then present sessions with multiSelect:**\n\nUse `AskUserQuestionTool` with `multiSelect: true` to let user pick relevant items:\n\n```\n\"Here are your Claude Code sessions from yesterday. Select the ones relevant to your standup:\"\n\nOptions (multiSelect):\n- \"Fix authentication bug (backend-api)\"\n- \"Implement OAuth flow (backend-api)\"\n- \"Update homepage styles (frontend-app)\"\n- \"Research payment providers (docs)\"\n```\n\n**Key insight:** User selects which sessions are work-related. Personal projects or experiments can be excluded.\n\n**Do NOT run digest script when:**\n- User explicitly says \"No\" to Claude Code history\n- User says they'll provide everything manually\n- `~\u002F.claude\u002Fprojects` directory doesn't exist\n\n**If digest script fails:**\n- Fallback: Skip Claude Code integration silently, proceed with interview\n- Common issues: Python not installed, no sessions from yesterday, permission errors\n- Do NOT block the standup flow — the script is supplemental, not required\n\n---\n\n## Phase 2: Interview (with insights)\n\n> **Claude Code users:** Use `AskUserQuestionTool` tool to conduct the interview. This provides a better UX with structured options.\n\n**Use pulled data as context** to make questions smarter.\n\n### Question 1: Yesterday\n\n**If data was pulled**, show it first:\n\n```\n\"Here's what I found from your activity:\n- Merged PR #123: fix login timeout\n- 3 commits in backend-api\n- Reviewed PR #456 (approved)\n\nAnything else you worked on yesterday that I missed?\"\n```\n\n**If no data pulled:**\n\n```\n\"What did you work on yesterday\u002Fsince the last standup?\"\n```\n\nIf user response is vague, ask follow-up:\n- \"Can you give more details about X?\"\n- \"Did you complete anything specific?\"\n\n### Question 2: Today\n\n```\n\"What will you work on today?\"\n\nOptions:\n- [Text input - user types freely]\n```\n\n**If Jira data was pulled**, you can suggest:\n\n```\n\"I see you have these tickets assigned:\n- PROJ-123: Implement OAuth flow (In Progress)\n- PROJ-456: Fix payment bug (To Do)\n\nWill you work on any of these today?\"\n```\n\n### Question 3: Blockers\n\n```\n\"Do you have any blockers or impediments?\"\n\nOptions:\n- \"No blockers\"\n- \"Yes, I have blockers\" → follow-up for details\n```\n\n### Question 4: Topics for Discussion\n\n```\n\"Any topic you want to bring up at the end of the daily?\"\n\nOptions:\n- \"No, nothing to discuss\"\n- \"Yes\" → follow-up for details\n\nExamples of topics:\n- Technical decision that needs input\n- Alignment with another team\n- Question about prioritization\n- Announcement or info for the team\n```\n\n---\n\n## Phase 3: Generate Update\n\nCombine all information into clean Markdown:\n\n```markdown\n# Daily Update - [DATE]\n\n## Yesterday\n- [Items from interview]\n- [Items from GitHub\u002FJira if pulled]\n\n## Today\n- [Items from interview]\n\n## Blockers\n- [Blockers or \"No blockers\"]\n\n## PRs & Reviews (if pulled from GitHub)\n- [PRs opened]\n- [PRs merged]\n- [Reviews done]\n\n## Jira (if pulled from Jira)\n- [Tickets updated]\n\n## Topics for Discussion\n- [Topics or \"None\"]\n\n---\n*Links:*\n- [PR links]\n- [Ticket links]\n```\n\n---\n\n## Core Principles\n\n1. **Interview is primary** — Tools supplement, they don't replace human context\n2. **Consent before access** — Always ask before pulling from any integration\n3. **Context-aware questions** — Show pulled data during interview to trigger memory (\"I see you merged PR #123...\")\n\n---\n\n## Quick Reference\n\n| Phase | Action | Tool |\n|-------|--------|------|\n| 1. Detect & Offer | Check gh\u002Fjira\u002Fclaude history, ask user, pull data | Bash (silent), AskUserQuestionTool* |\n| 2. Interview | Ask 4 questions with insights | AskUserQuestionTool* |\n| 3. Generate | Format Markdown | Output text |\n\n*Claude Code only: Use `AskUserQuestionTool` tool for structured questions.\n\n### Claude Code Digest Script\n\n```bash\n# Get yesterday's sessions as JSON\npython3 ~\u002F.claude\u002Fskills\u002Fdaily-meeting-update\u002Fscripts\u002Fclaude_digest.py --format json\n\n# Get today's sessions\npython3 ~\u002F.claude\u002Fskills\u002Fdaily-meeting-update\u002Fscripts\u002Fclaude_digest.py --date today --format json\n\n# Filter to specific project\npython3 ~\u002F.claude\u002Fskills\u002Fdaily-meeting-update\u002Fscripts\u002Fclaude_digest.py --project ~\u002Fmy-app --format json\n```\n\n---\n\n## Example Session\n\n```\nClaude: \"Let's prepare your daily! I detected GitHub configured. Want me to pull your recent activity?\"\nUser: \"Yes\"\n\nClaude: \"Which repos should I check?\"\nUser: \"backend-api and frontend-app\"\n\n[Claude pulls GitHub data silently]\n\nClaude: \"I can also pull your Claude Code session history from yesterday. Want me to check?\"\nUser: \"Yes\"\n\n[Claude runs digest script, gets 5 sessions]\n\nClaude: \"Here are your Claude Code sessions from yesterday. Select the ones relevant to your standup:\"\n  ☑ Fix authentication timeout bug (backend-api)\n  ☑ Implement OAuth flow (backend-api)\n  ☐ Update personal blog (blog) - [user unchecks personal project]\n  ☑ Research payment providers (docs)\n  ☐ Debugging test failures (experiments)\n\nUser: [selects 3 relevant items]\n\nClaude: \"Here's what I found from your activity:\n- Merged PR #120: fix login timeout\n- Opened PR #125: feat: add OAuth flow\n- Reviewed PR #123 (approved), PR #456 (changes requested)\n- 5 commits in backend-api\n- [From Claude Code] Fix authentication timeout bug\n- [From Claude Code] Implement OAuth flow\n- [From Claude Code] Research payment providers\n\nAnything else you worked on yesterday that I missed?\"\nUser: \"No, that covers it\"\n\nClaude: \"What will you work on today?\"\nUser: \"Continue the OAuth feature and deploy to staging\"\n\nClaude: \"Any blockers?\"\nUser: \"No\"\n\nClaude: \"Any topic to bring up at the end of the daily?\"\nUser: \"Yes, I want to discuss the architecture of the new payments module\"\n\n[Claude generates update]\n```\n\n---\n\n## Output Example\n\n```markdown\n# Daily Update - 2026-01-22\n\n## Yesterday\n- Worked on authentication feature\n- Research on payment providers\n- Merged PR #120 (fix: login timeout)\n- Opened PR #125 (feat: add OAuth flow)\n\n## Today\n- Continue OAuth feature\n- Deploy to staging\n\n## Blockers\n- No blockers\n\n## PRs & Reviews\n- **Opened:** PR #125 - feat: add OAuth flow\n- **Merged:** PR #120 - fix: login timeout\n- **Reviews:** PR #123 (approved), PR #456 (changes requested)\n\n## Topics for Discussion\n- Architecture of the new payments module\n\n---\n*Links:*\n- https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fpull\u002F125\n- https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fpull\u002F120\n```\n\n---\n\n## Anti-Patterns\n\n| Avoid | Why (Expert Knowledge) | Instead |\n|-------|------------------------|---------|\n| Run gh\u002Fjira 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 |\n| 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?\" |\n| Skip interview even with tool data | Tools capture WHAT happened but miss WHY and context (research, meetings, planning) | Interview is primary, tools supplement |\n| Generate update before all 4 questions | User might have critical blocker or discussion topic that changes the narrative | Complete interview, then generate |\n| Include raw commit messages | Commit messages are often cryptic (\"fix\", \"wip\") and don't tell the story | Summarize into human-readable outcomes |\n| 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 |\n\n---\n\n## NEVER\n\n- **NEVER assume tools are configured** — Many devs have gh installed but not authenticated, or jira CLI pointing to wrong instance\n- **NEVER skip the \"Topics for Discussion\" question** — This is often the most valuable part of standup that tools can't capture\n- **NEVER generate more than 15 bullets** — Standup should be \u003C2 minutes to read; long updates lose the audience\n- **NEVER include ticket\u002FPR numbers without context** — \"PROJ-123\" means nothing; always include title or summary\n- **NEVER pull data from repos user didn't explicitly approve** — Even if you can see other repos, respect boundaries\n",{"name":5,"description":7,"user-invocable":51},true,"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fdaily-meeting-update",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":51},[64,67,70],{"tool":65,"command":66},"npx","npx skills add davila7\u002Fclaude-code-templates --skill daily-meeting-update",{"tool":68,"command":69},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill daily-meeting-update",{"tool":71,"command":72},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill daily-meeting-update","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fdaily-meeting-update\u002FSKILL.md",[75,81],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"README.md","REFERENCE","参考文档",7533,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fdaily-meeting-update\u002FREADME.md",{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Fclaude_digest.py","SCRIPT","脚本",10692,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fdaily-meeting-update\u002Fscripts\u002Fclaude_digest.py",[88,119,145,176,211,235],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":99,"publishedAt":46},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[94],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[100,101,102,103,104,105,106,107,108,31,109,110,111,112,113,114,115,116,117,118],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","use","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":126,"publishedAt":46},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[125],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[127,128,129,130,131,132,133,134,135,136,137,31,41,138,139,140,141,142,143,144],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","todo","work","plan","focus","signals","audit","dependency",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":158,"publishedAt":46},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[151,154,155],{"categoryNo":152,"categoryName":153,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},{"categoryNo":156,"categoryName":157,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师",[159,160,161,162,163,164,165,105,166,167,168,169,170,171,172,108,173,174,31,175],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":180,"licenseFileUrl":181,"sourceHtmlUrl":182,"categories":183,"keywords":187,"publishedAt":46},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[184],{"categoryNo":185,"categoryName":186,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000009","前端开发",[188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,105,210],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":180,"licenseFileUrl":215,"sourceHtmlUrl":216,"categories":217,"keywords":222,"publishedAt":46},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[218,221],{"categoryNo":219,"categoryName":220,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":185,"categoryName":186,"taxonomyType":97,"taxonomyTypeDesc":98},[223,224,225,226,227,189,228,198,199,229,230,231,232,105,233,110,234],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":236,"name":237,"nameZh":6,"description":238,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":180,"licenseFileUrl":239,"sourceHtmlUrl":240,"categories":241,"keywords":249,"publishedAt":46},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[242,245,246],{"categoryNo":243,"categoryName":244,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},{"categoryNo":247,"categoryName":248,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000036","内容创作者",[250,251,252,253,254,255,256,257,191,258,201,41,259,260,261,262,263,171,264,31,265,266,267,268,269,116,270],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]