一键导入
confluence-review
Read and critically summarize a Confluence document. Surfaces key decisions, gaps, open questions, and suggests review questions.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Read and critically summarize a Confluence document. Surfaces key decisions, gaps, open questions, and suggests review questions.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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.
Mid-day progress check against the daily plan. Scans for new DMs, checks capacity, and helps reprioritize if needed.
| name | confluence-review |
| description | Read and critically summarize a Confluence document. Surfaces key decisions, gaps, open questions, and suggests review questions. |
| metadata | {"workbench.argument-hint":"<page title or URL>"} |
Read a document and provide a structured, critical summary that enables fast decision-making.
Confluence spaces are defined in config.yaml under confluence.spaces.
The user will provide one of:
mcp__claude_ai_Atlassian__getConfluencePage.mcp__claude_ai_Atlassian__searchConfluenceUsingCql.Fetch the page content. If it references child pages or linked pages essential to understanding, fetch those too (up to 3 additional pages).
Use mcp__claude_ai_Atlassian__getConfluencePageFooterComments and mcp__claude_ai_Atlassian__getConfluencePageInlineComments. Comments often contain objections, clarifications, or decisions not reflected in the doc body.
If saving or sharing the review, read context/standards/html-plan-standard.md and create confluence-review.md as the primary artifact (review summaries are Markdown-first per the standard). Generate a confluence-review.html companion only when the review reproduces structural elements of the source page that lose meaning in MD (deeply nested diagrams, embedded interactive widgets).
## Document: "Title"
**Space**: X | **Author**: Y | **Last Updated**: Z
### TL;DR
(2-3 sentences)
### What It Proposes
(Structured summary of the main content)
### Key Tradeoffs
- Tradeoff 1: chose X over Y because Z
### Open Questions / Gaps
- Things the doc doesn't address
- Missing sections (rollback plan, monitoring, migration path)
### Comments & Discussion
- Notable comments from reviewers
- Unresolved disagreements
### Questions You Should Raise
(2-4 specific questions based on the content and gaps)