prompt-regression-gate SKILL.md skillA

prompt-regression-gate from alivirgo/major-ai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add alivirgo/major-ai-skills/prompt-regression-gate@git:20261005.2bc0998

Pins git:20261005.2bc0998 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
alivirgo/major-ai-skills
Path
plugins/mas-ai-workflows/skills/prompt-regression-gate/SKILL.md
Versions recorded
2
Latest version
git:20261005.2bc0998, committed Oct 5, 2026
First version recorded
Sep 11, 2026
Size
14,967 bytes
Repository stars
2
License
MIT

Gate prompt, model, tool-schema, or packer changes with paired runs on a frozen eval set, slice-level regression checks, relative baselines, and explicit go/no-go thresholds. Use before merging prompt PRs or swapping models.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Prompt Regression Gate AI Skill Guide (Claude)

## Overview & Engine Architecture

A prompt is production code. Unit tests do not catch “fluent but worse.” A **regression gate** answers only: *is this change worse than the pinned baseline on the same frozen cases?* Absolute “looks good” review and candidate self-confidence are not gates.

Claude operates as a Principal LLM Release Engineer, specializing in **paired baseline vs candidate runs**, **relative delta thresholds**, **slice/P0 hard fails**, **stochastic control**, and **hash-bound provenance** (prompt, dataset, system, judge).

```
┌─────────────────────────────────────────────────────────────┐
│                 Prompt Regression Gate                      │
│                                                             │
│  Inputs (frozen before compare)                             │
│  ├── dataset_version + dataset_hash (@ai-evaluation-dataset)│
│  ├── baseline: prompt_hash + model + tools + retriever      │
│  ├── candidate: same knobs except the intentional delta     │
│  └── thresholds agreed BEFORE seeing scores                 │
│                                                             │
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add alivirgo/major-ai-skills/prompt-regression-gate@sha256:3867e4c86393b3f3

The line at the top of this page pins the label git:20261005.2bc0998, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_koqintnfyk2qocbq.svg)](https://markdownregistry.com/a/art_koqintnfyk2qocbq)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 11, 2026 and Oct 5, 2026, about one every 24 days.

versioncommittedcommitsizeaudit
git:20261005.2bc0998 latest2026-10-05 2bc0998 14,967 BA view · diff
git:20260911.25436b52026-09-11 25436b5 1,608 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14967 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

alivirgo/major-ai-skills · 2 stars · license MIT · pushed 2026-10-21 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_koqintnfyk2qocbq
GET https://markdownregistry.com/api/v1/resolve?ref=alivirgo/major-ai-skills/prompt-regression-gate
GET https://markdownregistry.com/api/v1/blob/3867e4c86393b3f32d58766352a9bd858945b4bb700866401dbb49a1f5b18f32

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from alivirgo/major-ai-skills

AGENTS.md AGENTS.md file
alivirgo/major-ai-skills · AGENTS.md
git:20260826.04755d9 · audit A · 2 stars
llms-full.txt llms.txt file
alivirgo/major-ai-skills · llms-full.txt
git:20260913.a32aaac · audit A · 2 stars
llms.txt llms.txt file
alivirgo/major-ai-skills · llms.txt
git:20260913.a32aaac · audit A · 2 stars
blender SKILL.md skill
alivirgo/major-ai-skills · plugins/mas-3d-games/skills/blender/SKILL.md · Automate Blender scenes with the bpy Python API, build Geometry Nodes workflows, configure Cycles or EEVEE renders, and…
git:20261005.2bc0998 · audit A · 2 stars
cinema-4d SKILL.md skill
alivirgo/major-ai-skills · plugins/mas-3d-games/skills/cinema-4d/SKILL.md · Script Cinema 4D scene workflows, configure MoGraph systems, and troubleshoot Redshift rendering.
git:20260911.25436b5 · audit A · 2 stars
godot SKILL.md skill
alivirgo/major-ai-skills · plugins/mas-3d-games/skills/godot/SKILL.md · Build Godot 4 scenes and GDScript workflows, inspect physics behavior, and configure headless project exports.
git:20261005.2bc0998 · audit A · 2 stars
houdini SKILL.md skill
alivirgo/major-ai-skills · plugins/mas-3d-games/skills/houdini/SKILL.md · Automate Houdini procedural workflows with VEX, the hou Python API, PDG/TOPs, and Solaris/Karma rendering.
git:20260911.25436b5 · audit A · 2 stars
substance-painter SKILL.md skill
alivirgo/major-ai-skills · plugins/mas-3d-games/skills/substance-painter/SKILL.md · Automate Substance 3D Painter texturing and mesh-map baking with Python and batch tools; inspect PBR export workflows.
git:20260911.25436b5 · audit A · 2 stars
unity SKILL.md skill
alivirgo/major-ai-skills · plugins/mas-3d-games/skills/unity/SKILL.md · Automate Unity editor and runtime workflows with C#, Addressables, render pipelines, and batch builds.
git:20261005.2bc0998 · audit A · 2 stars
unreal-engine SKILL.md skill
alivirgo/major-ai-skills · plugins/mas-3d-games/skills/unreal-engine/SKILL.md · Build Unreal Engine workflows with Blueprints, C++, editor Python, and Unreal Automation Tool build or packaging jobs.
git:20261005.2bc0998 · audit A · 2 stars
zbrush SKILL.md skill
alivirgo/major-ai-skills · plugins/mas-3d-games/skills/zbrush/SKILL.md · Automate ZBrush sculpting workflows with ZScript, prepare retopology with ZRemesher, and manage mesh decimation or…
git:20260911.25436b5 · audit A · 2 stars
agent-injection-boundary-test SKILL.md skill
alivirgo/major-ai-skills · plugins/mas-ai-workflows/skills/agent-injection-boundary-test/SKILL.md · Test authorized agents against indirect prompt injection in retrieved docs and tool outputs using paired clean/poison…
git:20261005.2bc0998 · audit A · 2 stars

Every file in alivirgo/major-ai-skills

Browse by kind, by grade A, or by owner.