Menu
Gather context for an upcoming meeting from Jira, Confluence, and Slack. Produces a brief with background, open questions, and talking points.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | meeting-prep |
| description | Gather context for an upcoming meeting from Jira, Confluence, and Slack. Produces a brief with background, open questions, and talking points. |
| metadata | {"workbench.argument-hint":"<meeting topic>"} |
Gather all relevant context for an upcoming meeting so you walk in informed and prepared.
Jira projects are defined in config.yaml under jira.projects. Confluence spaces are defined in config.yaml under confluence.spaces.
The user will provide:
Based on the meeting topic, search across all available sources:
Jira: Use mcp__claude_ai_Atlassian__searchJiraIssuesUsingJql to find related tickets across all configured Jira projects.
Confluence: Use mcp__claude_ai_Atlassian__searchConfluenceUsingCql to find related docs across all configured Confluence spaces.
Slack: Use mcp__claude_ai_Slack_MCP__slack_search_public_and_private to find recent discussions. Focus on the last 2 weeks.
Pull together everything found into a coherent brief. Connect the dots between Jira tickets, design docs, and Slack discussions.
If the brief is saved, shared, or longer than a quick chat answer, read context/standards/html-plan-standard.md and create meeting-brief.md as the primary artifact (text-heavy briefs are Markdown-first per the standard). Generate a meeting-brief.html companion only when the brief carries genuine visual content — an agenda diagram, a decision matrix with semantic colors, side-by-side mockups for design reviews.
## Meeting Brief: [Topic]
### Background
(2-4 sentences: what this meeting is about and the current state of things)
### Key Jira Tickets
- [TICKET-ID] Title — Status: X, Assignee: Y
(1-line summary)
### Relevant Documents
- "Doc Title" (Confluence) — (1-line summary)
### Recent Slack Discussion
- Key points from #channel discussions
- Decisions already made
- Open disagreements or questions
### Current State / Open Questions
1. Question that's likely to come up
2. Decision that needs to be made
3. Risk or blocker to surface
### Your Talking Points
(2-4 opinionated points a principal engineer should contribute)
Config-driven visible plan-to-PR workflow for Workbench engineering work. Use for agent-flow, full lifecycle, visible agents, Helix-style implementation, cross-repo context, HTML plans, PR breakdowns, small or stacked PRs, reviewer packets, review from packet, Claude/Codex pairing, worktrees, Jira/PR handoffs, continuation handoffs, or approved bypass of detailed PR slicing.
Freeform ideation and structured shortlisting. Generates 8-10 approaches including wild cards, then converges on 2-4 viable options with tradeoffs. Use before /forge or standalone for any creative exploration.
Read Outlook Web calendar via Chrome and extract meeting data for capacity planning. Writes to context/active/calendar.md so other skills use real numbers.
Show remaining capacity today and this week by reading daily and weekly plans. Flags overcommitment. Use when checking if there's room for more work.
Read and critically summarize a Confluence document. Surfaces key decisions, gaps, open questions, and suggests review questions.
Create a release branch and managed _release worktree in a Workbench repo using canonical Python worktree tooling. Use when the user wants to cut a release, create a release branch, start a release process, preview the next release branch name, or keep release work out of main/develop.