회귀 증명, 주변 동작 보존, 작업 관련 테스트에 중점을 두고, 가장 좁은 책임 계층에서 버그와 작은 동작 변경을 수정합니다.
이 스킬은 개발자가 버그나 작은 동작 변경을 수정할 때, 회귀(regression)를 방지하고 주변 동작을 손상시키지 않도록 돕는 방법을 제공합니다. 'Surgical Patch(수술적 패치)'라는 이름처럼 최소한의 변경으로 문제를 정확히 해결하는 것에 초점을 맞춥니다. Claude Code, Cursor, Codex 등 다양한 AI 에이전트 플랫폼에서 활용할 수 있으며, SKILL.md 문서를 기반으로 동작합니다. 이 스킬은 먼저 증상을 재현하거나 강력한 증거를 확보한 후, 증상의 원인을 추적하여 잘못된 동작을 책임지는 가장 좁은 계층(narrowest layer)을 변경합니다. 변경 시 불필요한 정리, 이름 변경, 추상화를 피하고, 관련 없는 동작과 사용자 변경 사항을 보존합니다. 마지막으로 작업과 관련된 회귀 증명(regression proof)만 추가하고, 집중된 증명과 가장 가까운 영향을 받는 게이트(gate)를 실행하여 수정이 완료되고 회귀 증명이 통과했는지 확인합니다.
npx skills add https://github.com/JuliusBrussee/caveman/tree/main/skills/surgical-patchInstalled? Explore more 코딩 & 개발 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
경제적일 때는 먼저 실패를 재현하고, 그렇지 않으면 사용 가능한 가장 강력한 증거를 확보하세요.
집중된 증명과 가장 가까운 영향을 받는 게이트(gate)를 실행하세요. 실패가 수정되고 회귀 증명이 통과할 때까지 중단하지 마세요.
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.
Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
Send and manage iMessages via BlueBubbles, including attachments, tapbacks, edits, replies, and groups.
Control Eight Sleep pods (status, temperature, alarms, schedules).
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Create, search, and manage Bear notes via grizzly CLI.
Capture frames or clips from RTSP/ONVIF cameras.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.