frank-luongt/skills/codex/daily-meeting-update

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->

---

name: daily-meeting-update description: Interactive daily standup/meeting update generator. Use when preparing for daily standup, scrum meetings, or team syncs. Pulls activity from GitHub, Jira, and session history, conducts a 4-question interview (yesterday, today, blockers, discussion topics), and generates formatted Markdown update.

Daily Meeting Update

Generate daily standup updates through an interactive interview with optional GitHub/Jira integration.

When to Use

• "daily", "standup", "scrum update"
• "status update", "what did I do yesterday"
• "prepare for meeting", "morning update", "team sync"

Workflow

Phase 1: DETECT & OFFER INTEGRATIONS
  Check: git history? gh CLI? jira CLI?
  Ask user before pulling from any source
  Pull approved data BEFORE interview
    |
Phase 2: INTERVIEW (with insights)
  Show pulled data as context
  Q1: Yesterday (with insights from pulled data)
  Q2: Today (with Jira ticket suggestions if available)
  Q3: Blockers
  Q4: Topics for discussion
    |
Phase 3: GENERATE UPDATE
  Combine interview + tool data
  Format as clean Markdown
  Present to user

Phase 1: Detect & Offer Integrations

Silent Detection

Check these without showing output to the user:

| Integration | How to Detect | |---|---| | Git | Inside a git repository | | GitHub CLI | gh auth status succeeds | | Jira CLI | jira command exists | | Atlassian MCP | mcp__atlassian__* tools available |

Ask Before Pulling

Never pull data without explicit user consent:

"I detected you have GitHub configured. Want me to pull your recent activity?"
- "Yes, pull the info"
- "No, I'll provide everything manually"

If yes, ask which repos to check.

Pull Data

Git/GitHub (for each approved repo):

• Commits by user since yesterday
• PRs opened/merged by user
• Reviews done by user

Jira (if approved):

• Tickets assigned to user, updated in last 24h

Store results for use as context in Phase 2.

Phase 2: Interview

Use pulled data to make questions smarter.

Q1: Yesterday

With data: Show what was found, ask what's missing:

"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 that I missed?"

Without data: "What did you work on yesterday?"

Q2: Today

"What will you work on today?"

With Jira data, suggest tickets:

"I see these tickets assigned to you:
- PROJ-123: Implement OAuth flow (In Progress)
- PROJ-456: Fix payment bug (To Do)

Will you work on any of these?"

Q3: Blockers

"Do you have any blockers?"

Q4: Discussion Topics

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

Examples: technical decisions needing input, cross-team alignment, prioritization questions.

Phase 3: Generate Update

# Daily Update - {DATE}

## Yesterday
- [Items from interview + tool data]

## Today
- [Items from interview]

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

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

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

---
*Links:*
- [PR/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
4. Keep it short -- Max 15 bullets total; standup should be <2 minutes to read

Anti-Patterns

| Avoid | Why | Instead | |---|---|---| | Pull data without asking | Users may have personal repos visible | Always ask first, let user choose repos | | Assume one project | Devs often work on 2-5 repos | Ask which projects | | Skip interview with tool data | Tools capture WHAT but miss WHY | Interview is primary, tools supplement | | Generate before all 4 questions | Might miss critical blocker or topic | Complete interview, then generate | | Include raw commit messages | Often cryptic ("fix", "wip") | Summarize into human-readable outcomes | | Ask for data after interview | Misses opportunity for context | Pull data first, interview with insights | | More than 15 bullets | Standup loses the audience | Summarize and consolidate | | Ticket numbers without context | "PROJ-123" means nothing alone | Always include title or summary |

NEVER

• Assume tools are configured -- many devs have gh installed but not authenticated
• Skip the "Topics for Discussion" question -- often the most valuable part
• Pull data from repos the user didn't approve -- respect boundaries
• Include personal/side-project activity unless user explicitly includes it

References

• Based on softaworks/agent-toolkit daily-meeting-update (MIT License)

<!-- Source: .faos/custom/skills/devops/daily-meeting-update/SKILL.md -->