media-judge SKILL.md skillA

media-judge from varghq/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add varghq/skills/media-judge@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
varghq/skills
Path
media-judge/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Nov 4, 2026
Size
13,752 bytes
Repository stars
21
License
MIT

Judge a finished AI-made video, image or track by measuring it, then rank takes on the defects found. One command reads every frame and writes facts with timestamps and evidence: broken frames, banding after a simulated X or YouTube upload, numbers that jiggle, spelling, too much on screen, nothing leading the eye, motion with no cause, pinned graphics, sliding labels, a face, outfit or light that changed, sound after the cut, loudness, voice against the script, and distance to references…

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

# Media judge

**Measure, don't grade.** A judgment here is a time, a number and a picture. "Looks great", "8/10" and "feels premium"
are not findings, and neither is any adjective with no measurement behind it.

Code finds the moment and a fresh pair of eyes reads only that moment, in that order, because the other way round fails:
12 vision models scored at most 54.1% on spotting temporal glitches; Claude Opus caught 17.5% of them, Gemini 3 Flash
said "glitch" to about 87% of clean clips ([TempGlitch](https://arxiv.org/abs/2605.21443), gameplay clips). Uniform sampling
at 0.5 fps caught 11.81% of faults under 0.2 s ([SynFlash](https://arxiv.org/abs/2603.17374)), and GPT-4 preferred its own
output 0.705 and 0.912 of the time on tasks where people saw equal quality ([Panickssery et al.](https://arxiv.org/abs/2404.13076)). So:

1. **Facts:** `judge.py` reads every frame and every sample. It does not sample.
2. **Eyes:** a fresh agent opens only the evidence and answers narrow questions.
3. **Verdict:** counted defects. Ranking follows from the counts, never from a feeling.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add varghq/skills/media-judge@sha256:e683d017fddf6248

The line at the top of this page pins the label v1.0.0, 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_tyjiwcu5gvotwvcs.svg)](https://markdownregistry.com/a/art_tyjiwcu5gvotwvcs)

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

Versions

The registry has recorded 1 version of this file, committed on Nov 4, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-11-04 013442f 13,752 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 (13752 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

varghq/skills · 21 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tyjiwcu5gvotwvcs
GET https://markdownregistry.com/api/v1/resolve?ref=varghq/skills/media-judge
GET https://markdownregistry.com/api/v1/blob/e683d017fddf62486948c7d62df669cf9e011b53f2a579da655c83acaf49e045

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 varghq/skills

AGENTS.md AGENTS.md file
varghq/skills · AGENTS.md
git:20261106.f977c6f · audit A · 21 stars
CLAUDE.md CLAUDE.md file
varghq/skills · CLAUDE.md
git:20261106.f977c6f · audit B · 21 stars
ad-creative-testing SKILL.md skill
varghq/skills · ad-creative-testing/SKILL.md · Turn one winning ad into a creative testing plan for TikTok and Meta. Decodes why an ad won (hook, argument, buyer…
v1.0.0 · audit A · 21 stars
ai-ad-compliance-check SKILL.md skill
varghq/skills · ai-ad-compliance-check/SKILL.md · Turns an AI video ad into a compliance report for TikTok Shop, TikTok ads, Meta, YouTube, the FTC, New York's…
v1.0.0 · audit A · 21 stars
ai-ugc-ad-video SKILL.md skill
varghq/skills · ai-ugc-ad-video/SKILL.md · Open-source alternative to Arcads: AI UGC ads with an AI actor holding your real product. Casts a creator whose age…
v1.0.0 · audit A · 21 stars
app-ui-mockups SKILL.md skill
varghq/skills · app-ui-mockups/SKILL.md · Ten animated UI mockups for product, launch and dev-tool videos, rebuilt as HTML instead of screen recordings: phone…
v0.1.0 · audit A · 21 stars
caption-styles SKILL.md skill
varghq/skills · caption-styles/SKILL.md · Seventeen animated caption looks for talking heads, podcasts, ads, lyric and short-form videos (karaoke fill…
v0.1.0 · audit A · 21 stars
character-passport SKILL.md skill
varghq/skills · character-passport/SKILL.md · Cast an AI video before anything moves: for every character and hero prop, a passport (one paragraph, every visible…
v1.0.1 · audit A · 21 stars
code-to-video-previz SKILL.md skill
varghq/skills · code-to-video-previz/SKILL.md · Prototype a video in code with an agent. Decides if a shot needs a 3D prototype at all and which tool fits (Three.js…
v1.0.0 · audit A · 21 stars
ecommerce-video-ads SKILL.md skill
varghq/skills · ecommerce-video-ads/SKILL.md · Ecommerce video ad skills for Claude Code and AI agents: plans and makes short product videos that sell on TikTok…
v1.0.0 · audit A · 21 stars
ecommerce-video-edit SKILL.md skill
varghq/skills · ecommerce-video-edit/SKILL.md · Turn raw product footage into a TikTok ad with FFmpeg. Recuts creator, UGC or product footage into a 9:16 ecommerce ad…
v1.0.0 · audit A · 21 stars
edit-footage-with-code SKILL.md skill
varghq/skills · edit-footage-with-code/SKILL.md · Edit real footage with an agent: turn raw takes of a talking head, podcast, vlog, course or ad into a clean cut, then…
v1.0.1 · audit A · 21 stars

Every file in varghq/skills

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