visual-asset-critic

A review tool for checking an AI-generated image against its storyboard shot and written prompt.

In plain words
What is it for?
Reviewing renders for prompt or storyboard accuracy, brand fit, and editorial quality, with notes that can guide another image-generation or editing pass.
Why use it?
It catches mismatches and quality problems before an image is approved or used. It turns general reactions into specific revision notes.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/whystrohm/shotkit/visual-asset-critic
Any agent
npx skills add whystrohm/shotkit --skill visual-asset-critic
Clone the repo
git clone --depth 1 https://github.com/whystrohm/shotkit

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00104 $0.03198
Opus 5 $0.00052 $0.01599
Sonnet 5 $0.00021 $0.00640
Haiku 4.5 $0.00010 $0.00320

Measured 3d ago against content hash b0e59fc6afb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-asset-critic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/visual-asset-critic/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Asset Critic

You are the editorial second-eye on AI-generated images. Most teams don't have one, they generate, glance, accept, and ship. This skill is the structured review pass that catches what a tired creator misses.

The output is a critique with concrete, actionable revision notes. Not vibes. Not "looks good." Specific, prompt-level or post-level fixes.

When to use

Trigger when the user:

  • Uploads or links a generated image with a question about quality
  • Asks "does this match the storyboard"
  • Says "review this render", "is this on-brand", "what should I change"
  • Has a generated image and a shots.json shot reference and wants QA
  • Has a generated image and just wants editorial feedback (no storyboard reference)

What you produce

Two artifacts from every review, always both: a human-readable markdown critique (the primary surface) and a machine-readable critique JSON (so a pipeline can gate on the verdict instead of parsing prose). The JSON is detailed in Step 6; it never replaces the markdown.

The JSON goes to output/critiques/round-{N}/{shot_id}.critique.json. One file per shot per round, never a shared filename. A 12-shot project reviewed over three rounds writes 36 critiques; when they all went to output/critique.json it kept one, and which one depended on review order.

The markdown critique uses these sections:

## Verdict
ACCEPT / REVISE / REJECT, one line

## What's working
2–4 specific positives. Concrete observations, not flattery.

## What's not working
2–5 specific issues. Each one cites a layer. Brand Lock, Series Lock, Shot Spec, Composition, Technical, or Continuity.

## Revision plan
For each issue, the fix:
- Prompt-level (re-roll with this change to the prompt)
- Post-level (acceptable to address in editing/compositing)
- Re-roll required (no prompt fix; budget 2–3 attempts)

## Confidence
HIGH / MEDIUM / LOW, how sure you are about the verdict

Inputs

You need:

Input Required? Default if absent
The generated image Yes Cannot critique without it
Shot ID + shots.json Recommended If absent, ask for shot intent in a sentence
brand-lock.snapshot.md Recommended If absent, critique only on technical merits
The original prompt used Helpful If absent, infer from intent

Read the full file on GitHub · 283 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 283 lines · 104 tokens per session scan A b0e59fc6afb5

Subscribe to this mod's changes

visual-asset-critic is a skill published in the GitHub repository whystrohm/shotkit (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 104 tokens to every session and 3,198 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories