raydocs

Export RepoPrompt context for external LLM review (ChatGPT, Claude web, etc.). Use when you want to review code or plans with an external model. Triggers on /flow-next:export-context.

John Carmack-level implementation review via RepoPrompt or OpenCode. Use when reviewing code changes, PRs, or implementations. Triggers on /flow-next:impl-review.

Interview user in-depth about an epic, task, or spec file to extract complete implementation details. Use when user wants to flesh out a spec, refine requirements, or clarify a feature before building. Triggers on /flow-next:interview with Flow IDs (fn-1, fn-1.2) or file paths.

Carmack-level plan review via RepoPrompt or OpenCode. Use when reviewing Flow epic specs or design docs. Triggers on /flow-next:plan-review.

Create structured build plans from feature requests or Flow IDs. Use when planning features or designing implementation. Triggers on /flow-next:plan with text descriptions or Flow IDs (fn-1, fn-1.2).

Scaffold repo-local Ralph autonomous harness under scripts/ralph/. Use when user runs /flow-next:ralph-init.

Token-efficient codebase exploration using RepoPrompt CLI. Use when user says "use rp to..." or "use repoprompt to..." followed by explore, find, understand, search, or similar actions.

Local install of flowctl CLI and CLAUDE.md/AGENTS.md instructions. Use when user runs /flow-next:setup.

Token-efficient codebase exploration using RepoPrompt codemaps and slices. Use when you need deep codebase understanding without bloating context, finding all pieces of a feature across many files, or building context for code review. Requires rp-cli on macOS; degrades to repo-scout otherwise.

Identify documentation that may need updates based on planned changes. Use when planning a feature to identify which docs (README, CHANGELOG, API docs) will need updates after implementation.

Find the most relevant framework and library documentation pages for implementing a feature correctly. Use when you need official API references, version-specific guidance, or examples from documentation.

Scan existing epics to find dependencies and relationships for a new plan. Use when planning a new feature to identify if it depends on or conflicts with existing work.

Map user flows, edge cases, and missing requirements from a brief spec. Use when you need to find what is missing or ambiguous in a feature request before implementation starts.

Search GitHub repositories (public and private) for code patterns, implementations, and examples. Use when you need to find how others implement a feature, search for code patterns across repos, or find known issues and solutions.

Search project memory (.flow/memory/) for entries relevant to the current task or request. Use when you need to recall past pitfalls, conventions, or decisions that apply to the work at hand.

Gather modern best practices and pitfalls for a specific implementation task. Use when you need current guidance on how to implement a feature correctly, avoid common mistakes, or find real-world examples from established projects.

28天效果追踪，对比分析皮肤变化，生成改善报告。实现追踪功能时使用此技能。

使用Gemini Vision API分析皮肤照片，返回结构化分析结果。当需要实现AI皮肤分析功能时自动调用此技能。

扫描护肤品成分表，OCR识别并AI解读成分功效与风险。实现成分扫描功能时使用此技能。

标准化拍照流程，确保光线、角度、距离一致，用于效果追踪对比。实现拍照引导功能时使用此技能。

基于用户皮肤档案和社区数据，生成个性化产品推荐。实现产品推荐功能时使用此技能。

皮肤双胞胎匹配算法，找到相似皮肤用户并推荐其有效产品。实现社区匹配功能时使用此技能。