역방향 호환이 가능한 안전한 전환을 구현합니다. 롤백과 보존 증명이 필요한 스키마, 데이터, API, 프로토콜, 설정 또는 의존성 마이그레이션에 사용합니다.
이 스킬은 스키마, 데이터, API, 프로토콜, 설정, 의존성 등 다양한 영역에서 안전하고 되돌릴 수 있는 마이그레이션을 수행하는 방법을 제공합니다. 핵심 원칙은 기존 데이터를 보존하면서 전환 경로(forward path)와 롤백 경로(rollback path)를 명확히 정의하여, 배포 중 혼합 버전 환경에서도 안전하게 운영할 수 있도록 합니다. 마이그레이션 단계는 확장(expand), 마이그레이션(migrate), 검증(verify), 수축(contract) 순서로 진행되며, 각 단계에서 실패 시 재시도가 멱등(idempotent)하게 동작하고 부분 실패를 관찰 가능하게 합니다. 이 스킬은 Claude Code, Cursor, Codex 등 AI 에이전트 플랫폼에서 활용할 수 있으며, 변경 전에 현재 리더, 라이터, 데이터 구조, 호환성 윈도우, 소유권을 먼저 파악하도록 지시합니다. 요청된 단계까지만 수행하고, 이후의 파괴적인 수축 단계를 암묵적으로 수행하지 않도록 주의합니다.
npx skills add https://github.com/JuliusBrussee/caveman/tree/main/skills/migration변경 전에 현재 리더, 라이터, 데이터 형태, 호환성 윈도우 및 소유권을 파악합니다.
요청된 단계가 통과하면 중단하고, 이후의 파괴적인 수축 단계를 암묵적으로 수행하지 않습니다.
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".