surgical-patch

juliusbrussee/caveman/surgical-patch

The surgical-patch skill is designed to fix bugs and small behavior changes at the narrowest responsible layer. It emphasizes reproducing the failure first when economical, or capturing the strongest available evidence, then tracing the symptom to the responsible mechanism and changing only the narrowest layer that owns the incorrect behavior. The skill requires preserving unrelated behavior and user changes, avoiding cleanup, renaming, or abstraction outside the fix, and adding only regression proof relevant to the task. Finally, run focused proof plus the nearest affected gate, and stop when the failure is fixed and regression proof passes.

Installs · 981View source

Installation

npx skills add https://github.com/juliusbrussee/caveman --skill surgical-patch

Skill files

SKILL.md

Last synced · Aug 29, 2026

agents/openai.yaml›

interface:
  display_name: "Surgical Patch"
  short_description: "Fix narrow responsible layer with proof"
  default_prompt: "Use $surgical-patch to fix this bug with a narrow verified change."

SKILL.md›

---
name: surgical-patch
description: Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.
---

# Surgical patch

Reproduce failure first when economical; otherwise capture strongest available evidence.

- Trace symptom to responsible mechanism.
- Change narrowest layer that owns incorrect behavior.
- Preserve unrelated behavior and user changes.
- Avoid cleanup, renaming, and abstraction outside fix.
- Add only regression proof relevant to task.

Run focused proof plus nearest affected gate. Stop when failure is fixed and regression proof passes.