Skills surgical-patch

📦

surgical-patch

Name: surgical-patch
Author: juliusbrussee

Content revision r1 Safe

Fix Bugs with Focused, Verified Changes

Broad fixes can introduce unrelated regressions and overwrite existing work. This skill traces each bug to its responsible layer and verifies a focused correction.

Supports: Claude Codex Code(CC)

🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "surgical-patch" from https://skillstore.io/skills/juliusbrussee-surgical-patch.md and its manifest at https://skillstore.io/api/skills/juliusbrussee-surgical-patch/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/juliusbrussee-surgical-patch.md Signed manifest GET /api/skills/juliusbrussee-surgical-patch/manifest Signed lockfile GET /api/skills/juliusbrussee-surgical-patch/lockfile

Test it

Using "surgical-patch". The profile form clears the display name when only the avatar is updated.

Expected outcome:

The update path now preserves an existing display name when that field is omitted. A focused regression test covers avatar-only updates.

Using "surgical-patch". A parser accepts empty identifiers after the latest validation change.

Expected outcome:

Located the regression in identifier validation.
Restored rejection of empty identifiers without changing other parsing rules.
Ran the focused parser test and the nearest validation suite.

Security Audit

Safe

v1 • 8/12/2026 Open versioned report

The single static finding is a false positive. The cited line limits unrelated code changes and does not request system reconnaissance or any dangerous action.

Files scanned

Lines analyzed

Review items

False positives ignored

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: codex

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/juliusbrussee-surgical-patch/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/juliusbrussee-surgical-patch/security.svg)](https://skillstore.io/skills/juliusbrussee-surgical-patch?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/juliusbrussee-surgical-patch?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/juliusbrussee-surgical-patch/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/juliusbrussee-surgical-patch.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

juliusbrussee. (2026). surgical-patch security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/juliusbrussee-surgical-patch/audits/1

BibTeX citation

@techreport{juliusbrussee-juliusbrussee-surgical-patch-2026,
  author = {juliusbrussee},
  title = {surgical-patch security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/juliusbrussee-surgical-patch/audits/1},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "surgical-patch security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "juliusbrussee"
date-released: "2026-08-12"
url: "https://skillstore.io/skills/juliusbrussee-surgical-patch/audits/1"
identifiers:
  - type: other
    value: "skillstore:juliusbrussee-surgical-patch:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Repair a Product Regression

Trace a reported regression, correct its owning layer, and add focused proof without changing unrelated behavior.

Review a Narrow Maintenance Fix

Keep a maintenance patch limited to the defect while preserving existing user changes and nearby behavior.

Stabilize a Failing Build

Identify the mechanism behind a focused test failure and verify the smallest responsible correction.

Try These Prompts

Fix a Reproducible Bug

Use surgical-patch to reproduce this bug, fix the narrowest responsible layer, and run the most relevant test: [bug details].

Patch with Limited Evidence

Use surgical-patch for [symptom]. Capture the strongest available evidence, trace the cause, preserve unrelated behavior, and verify the focused fix.

Protect Existing Changes

Fix [defect] with surgical-patch. Preserve current user modifications, avoid unrelated cleanup, and add only regression proof relevant to this defect.

Constrain a Cross-Layer Regression

Analyze [regression] across affected layers. Patch only the layer owning the incorrect behavior, then run focused proof and the nearest affected gate.

Best Practices

Provide reproduction steps, expected behavior, and observed behavior whenever available.
Identify existing user changes that the patch must preserve.
Name the focused tests and validation gates relevant to the defect.

Avoid

Do not combine the bug fix with unrelated cleanup or renaming.
Do not request broad architectural changes when a responsible layer is already identifiable.
Do not treat a passing focused test as proof for unrelated system behavior.

Frequently Asked Questions

What types of tasks fit this skill?

It fits bug fixes and small behavior changes where minimal scope and regression proof are important.

Does the skill always reproduce the failure first?

It reproduces the failure when practical. Otherwise, it captures the strongest evidence available before making a change.

Will it refactor nearby code?

No. It avoids unrelated cleanup, renaming, and abstraction unless they are required to correct the behavior.

How does it protect existing work?

It preserves unrelated behavior and user changes while limiting edits to the layer responsible for the defect.

What validation does it perform?

It runs focused regression proof and the nearest affected test or validation gate available in the project.

Can it handle large redesigns?

It is not intended for broad redesigns. Use it when the requested correction can remain narrow and independently verified.

Developer Details

Author

juliusbrussee

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/juliusbrussee/caveman/tree/a0109974ea3258a14aadaef1ed1f8ff2837d30d5/skills/surgical-patch

Ref

bcfdf876e95298ed287f7ee770346a19d41ade01

Maintenance freshness

8/13/2026

Usage

0 downloads · 0 views

File structure

📁 agents/

📄 openai.yaml

📄 SKILL.md