name	safeguarding-ai-generated-code
description	Use when AI-generated or AI-modified changes need a Code Health gate before commit, handoff, or pull request.

Safeguarding AI-Generated Code

Overview

Use Code Health safeguards before declaring AI-touched code ready. The goal is to catch maintainability regressions early and prevent agents from normalizing technical debt.

When to Use

The agent changed code and is about to suggest a commit.
The user asks whether a branch or staged changes are safe to merge.
The workflow needs a quality gate for AI-generated code.

Do not use this skill for broad refactoring discovery or project-level prioritization.

Quick Reference

code_health_review: Review each AI-modified file immediately after the change.
pre_commit_code_health_safeguard: Check staged or modified files before commit.
analyze_change_set: Check a branch or PR-style change set against a base ref.

Implementation

After each AI modification to a file, run code_health_review on that file.
If the review reports maintainability problems or regression risk, refactor the file in small steps and review it again.
Run pre_commit_code_health_safeguard before commit-oriented recommendations as a broader gate across staged or modified files.
Run analyze_change_set before PR-oriented recommendations as a final branch-level gate.
If either later gate reports a regression, inspect the affected files with code_health_review and keep iterating until the issue is removed or the user explicitly accepts the risk.

Common Mistakes

Waiting until commit time to run the first Code Health check.
Treating safeguard output as optional guidance instead of a release gate.
Declaring work done after a failing safeguard.
Jumping straight to broad rewrites instead of inspecting the flagged files first.
Treating an accepted risk as invisible; call it out explicitly.

Más de este repositorio

mismo repositorio

explaining-code-health

DavidVujic/my-eca-config

Use when a user asks what Code Health means, how to interpret scores, or why Code Health matters in daily development.

2026-05-2111

guiding-refactoring-with-code-health

DavidVujic/my-eca-config

Use when refactoring unhealthy code and needing Code Health findings to choose small safe steps and verify improvement.

2026-05-2111

making-the-business-case-for-code-health

DavidVujic/my-eca-config

Use when a user asks for ROI, stakeholder justification, delivery impact, or defect-risk reduction from improving Code Health in a file.

2026-05-2111

qa-check

DavidVujic/my-eca-config

Run linting and unit tests against the current repository, auto-discovering the correct commands from Justfile, Makefile, pyproject.toml, or package.json.

2026-03-2511

commit

DavidVujic/my-eca-config

Create a conventional commit from staged changes, with a diff-derived description body.

2026-03-2511

git-changes-context

DavidVujic/my-eca-config

Reliably obtain a non-empty unified git diff for the current branch using safe fallbacks (origin/HEAD...HEAD, origin/main...HEAD, origin/master...HEAD) and return structured JSON containing the diff and the command used.

2026-03-0311

name	safeguarding-ai-generated-code
description	Use when AI-generated or AI-modified changes need a Code Health gate before commit, handoff, or pull request.

Safeguarding AI-Generated Code

Overview

Use Code Health safeguards before declaring AI-touched code ready. The goal is to catch maintainability regressions early and prevent agents from normalizing technical debt.

When to Use

The agent changed code and is about to suggest a commit.
The user asks whether a branch or staged changes are safe to merge.
The workflow needs a quality gate for AI-generated code.

Do not use this skill for broad refactoring discovery or project-level prioritization.

Quick Reference

code_health_review: Review each AI-modified file immediately after the change.
pre_commit_code_health_safeguard: Check staged or modified files before commit.
analyze_change_set: Check a branch or PR-style change set against a base ref.

Implementation

After each AI modification to a file, run code_health_review on that file.
If the review reports maintainability problems or regression risk, refactor the file in small steps and review it again.
Run pre_commit_code_health_safeguard before commit-oriented recommendations as a broader gate across staged or modified files.
Run analyze_change_set before PR-oriented recommendations as a final branch-level gate.
If either later gate reports a regression, inspect the affected files with code_health_review and keep iterating until the issue is removed or the user explicitly accepts the risk.

Common Mistakes

Waiting until commit time to run the first Code Health check.
Treating safeguard output as optional guidance instead of a release gate.
Declaring work done after a failing safeguard.
Jumping straight to broad rewrites instead of inspecting the flagged files first.
Treating an accepted risk as invisible; call it out explicitly.