菜单
Interactive review of auto-generated Ralph artifacts. Use when user asks to "ralph review stories", "ralph review tasks", "ralph review roadmap", or needs to validate planning artifacts against their intent.
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
Walk through a milestone GUIDE.md with agent-browser, testing every step. Fixes code bugs and guide inaccuracies as they're found. Use when user asks to "test the guide", "run guide and fix", "validate guide", or "run-guide-and-fix".
Generate a comprehensive GUIDE.md for a project milestone. Use when user asks to "write guide", "generate guide", "create demo guide", or "write-guide". Analyzes milestone stories, git changes, and project setup to produce a step-by-step demo guide.
Complete reference for using the All Agents CLI (`aaa`). Use this skill whenever the user asks to run an aaa command, wants to plan/build/review with Ralph, needs to know the right CLI invocation, asks about available commands or flags, mentions 'aaa', 'ralph', 'subtasks', 'milestones', 'cascade', or needs help constructing any `aaa` CLI command. Also trigger when user says things like 'plan stories', 'build the queue', 'check status', 'review subtasks', 'run calibration', or any development workflow task that maps to an aaa command.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Create Obsidian .canvas files programmatically with correct format. Use when user asks to "create canvas", "make canvas", "canvas file", "obsidian canvas", or needs to generate a .canvas for Obsidian.
Run Ralph calibration checks to analyze intention drift, technical quality, and self-improvement opportunities. Use when user asks to "ralph calibrate", "check drift", "analyze sessions", or needs to verify work alignment.
| name | ralph-review |
| description | Interactive review of auto-generated Ralph artifacts. Use when user asks to "ralph review stories", "ralph review tasks", "ralph review roadmap", or needs to validate planning artifacts against their intent. |
Interactive review of planning artifacts with fresh eyes.
Check the ARGUMENTS:
gap roadmapLaunch a subagent with fresh context to analyze the roadmap for gaps.
Follow @context/workflows/ralph/review/roadmap-gap-auto.md completely.
gap stories <milestone>Launch a subagent with fresh context to analyze stories for gaps.
If no milestone provided, ask user: "Which milestone should I analyze? (e.g., milestone-1)"
Follow @context/workflows/ralph/review/stories-gap-auto.md completely.
gap tasks --story <path>Launch a subagent with fresh context to analyze task coverage for a story.
If no story provided, ask user: "Which story should I analyze? (e.g., docs/planning/stories/STORY-001.md)"
Follow @context/workflows/ralph/review/tasks-gap-auto.md completely.
stories <milestone>Follow @context/workflows/ralph/review/stories-review.md completely.
roadmapLaunch a subagent with fresh context to review the roadmap for quality and completeness.
Presentation: @context/workflows/ralph/review/chunked-presentation.md
Read and analyze:
Walk through milestone by milestone:
Review dimensions per milestone:
tasks <story-id>Tell user: "Task review coming soon."
helpShow:
/ralph-review stories <milestone> Review stories for a milestone
/ralph-review roadmap Review roadmap milestones
/ralph-review gap roadmap Cold analysis of roadmap gaps
/ralph-review gap stories <milestone> Cold analysis of story gaps
/ralph-review gap tasks --story <path> Task gap analysis for a story
/ralph-review tasks <story-id> (coming) Review tasks for a story