迁移 是做什么的？
在编辑之前，先映射当前读取器、写入器、数据形状、兼容性窗口和所有权。
- 定义前向路径和回滚路径。
- 保留现有数据；破坏性步骤必须明确说明并单独授权。
- 在发布可能重叠的情况下，确保混合版本操作的安全性。
- 在适用时，按顺序执行扩展、迁移、验证，然后收缩。
- 确保重试操作幂等，并使部分失败可观测。
- 在必要的过渡阶段验证新旧路径。
在请求的阶段通过后停止；不得隐式执行后续的破坏性收缩操作。
实现可逆且兼容性安全的变更。适用于需要回滚及保留证明的架构、数据、API、协议、配置或依赖迁移。
该技能（JuliusBrussee/migration）专为需要安全逆向操作的迁移场景设计。其核心原则是在执行任何变更之前，先映射当前读取器、写入器、数据形状、兼容性窗口以及所有权关系。它要求始终定义前向路径和回滚路径，确保破坏性步骤得到明确说明并单独授权，同时保持混合版本环境下的操作安全。该技能特别强调数据保留，对破坏性操作必须有额外授权，并支持扩展、迁移、验证、收缩的分阶段流程，使重试操作具备幂等性，并使部分失败可被观察。它适用于架构、数据、API、协议、配置或依赖等任何需要兼容性证明和回滚能力的迁移工作。
npx skills add https://github.com/JuliusBrussee/caveman/tree/main/skills/migration在编辑之前，先映射当前读取器、写入器、数据形状、兼容性窗口和所有权。
在请求的阶段通过后停止；不得隐式执行后续的破坏性收缩操作。
This repo contains 12 individual skills — each has its own dedicated page.
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
ElevenLabs text-to-speech with mac-style say UX.
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.
Capture and automate macOS UI with the Peekaboo CLI.
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".