skill-change-gate

Classify regressions in proposed skill package changes and return a pass, fail, or warning decision.

Updated Apr 27, 2026
One-click install
npx skills add https://github.com/ginmp8/rhapsodia --skill skill-change-gate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-change-gate
Source: https://github.com/ginmp8/rhapsodia/tree/main/skills/skill-change-gate
Command: npx skills add https://github.com/ginmp8/rhapsodia --skill skill-change-gate

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Identify and classify regressions introduced by a proposed change to an existing skill package, and return a structured decision without mutating the target.

Core Features & Use Cases

  • Structural acceptance gating for skill changes, surfacing only gating results without mutating the target.
  • Evidence classification and regression taxonomy (blocking, material, and warnings) to guide decisions.
  • Supports multiple modes: candidate-gate, preflight-gate, post-validation-gate, and advisory-review.
  • Outputs a standardized decision for downstream pipelines and integration with evaluator/benchmark workflows.
  • Integrates with references and scripts to enable evidence collection and reproducible gating.

Quick Start

Run the gate on a candidate skill change by supplying the target folder and any before/after evidence to obtain a pass, pass-with-warnings, fail, or insufficient-evidence decision.

Frequently Asked Questions about skill-change-gate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect regressions in a skill package before merging changes?

A change gate evaluates candidate diffs or patches against before and after skill packages to identify and classify regressions in activation, scope, safety, or packaging, returning a structured pass or fail decision without mutating the target.

What is skill change gating and how does it work?

Skill change gating is a structural acceptance process that classifies regressions from proposed skill package modifications using candidate evidence like diffs and validator outputs, returning a standardized final decision of pass, pass-with-warnings, fail, or insufficient-evidence.

Can I use a regression gate to evaluate hardening patches and manual edits?

Yes, the gate evaluates hardening patches and manual edits by analyzing the target folder and before or after evidence to identify blocking regressions in local references, validation, and output contracts without modifying the original package.

What evidence do I need to run a preflight gate on a skill package?

Running a preflight gate requires candidate evidence including a diff or patch, before and after packages, and any validator or benchmark outputs to accurately assess output contracts and packaging regressions for a pass or fail decision.

When should I use an advisory review instead of a blocking validation gate?

Use advisory review mode when you need to surface material regressions and warnings from a skill package change without enforcing a strict pass, pass-with-warnings, fail, or insufficient-evidence blocking decision in your downstream pipelines.

Why does my skill change gate return an insufficient-evidence decision?

The gate returns an insufficient-evidence decision when provided candidate evidence like diffs, before and after packages, or validator outputs is inadequate to confidently classify activation, validation, or packaging regressions.