Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

AI Visual Accuracy Check Skill · aiskillstore | DecimalAI

testingby aiskillstore

AI Visual Accuracy Check Skill

aiskillstore/ai-visual-accuracy-check

Source aiskillstore/marketplace ↗License Not recorded

Use AI to compare rendered HTML to original PDF page. AI makes contextual judgment about visual accuracy with explainable reasoning. BLOCKING quality gate - stops pipeline if score below 85%.

SkillScore82Maintained

Automatic

QA & Test Engineering pack

Last verified 8/22/2026

What it changes

Passed 16 of 19 test cases with the skill, and 9 of 19 without it.

Without skill45%

With skill82%

Checks it passed that the model alone missed

Layout match is assigned a weight of 40%.
Visual hierarchy is assigned a weight of 30%.
The workflow proceeds to deployment approval.

and 10 more in the full report

8 fixed10 passed either way4 still failing0 broke

Pass-rate lift: +36 pp
Tokens: +117%
Agent turns: 0%
Response time: -55%

Model gemini-3.6-flashMeasured 8/22/2026v118 of 22 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/aiskillstore-ai-visual-accuracy-check/SKILL.md https://app.decimal.ai/s/aiskillstore-ai-visual-accuracy-check/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add aiskillstore-ai-visual-accuracy-check, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/aiskillstore-ai-visual-accuracy-check/ and pins it in .decimal/skills.lock

decimalai skills add aiskillstore-ai-visual-accuracy-check

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/aiskillstore-ai-visual-accuracy-check/SKILL.md https://app.decimal.ai/s/aiskillstore-ai-visual-accuracy-check/SKILL.md

Raw file: /s/aiskillstore-ai-visual-accuracy-check/SKILL.md ↗ · machine-readable summary at /s/aiskillstore-ai-visual-accuracy-check.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

In our visual quality inspection protocol for book chapters, we weight four visual criteria to compute the final similarity score. What exact weight percentages are assigned to layout match, visual hierarchy, and content positioning?

What was checked, without and with the skill
Checked	Without skill	With skill
Layout match is assigned a weight of 40%.	Missed	Passed
Visual hierarchy is assigned a weight of 30%.	Missed	Passed
Content positioning is assigned a weight of 20%.	Missed	Passed

case-06 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md379 linessingle file

AI Visual Accuracy Check Skill

Purpose

This is a BLOCKING quality gate that uses AI to validate visual accuracy of generated HTML against the original PDF page. Unlike pixel-perfect comparison, AI understands:

Visual hierarchy and layout intent
Contextual differences (web rendering vs PDF)
Whether readers would have similar experience
Trade-offs between CSS limitations and HTML accuracy

The AI provides:

Objective similarity score (0-100%)
Breakdown by evaluation criteria
Specific differences noted
Clear pass/fail recommendation
Explanation for decisions

This combines AI's contextual understanding with deterministic gating (must pass 85+ to continue).

What to Do

Load input files
- Read chapter_XX.html (generated consolidated HTML)
- Read 02_page_XX.png (original PDF page image)
Render HTML to image
- Use headless browser (Playwright/Selenium) to render HTML as PNG
- Capture full page screenshot
- Save rendered image for comparison
Invoke Claude with visual comparison
- Attach original PDF PNG as image 1
- Attach rendered HTML screenshot as image 2
- Request detailed visual comparison
- Ask AI to score on multiple criteria
Parse AI response
- Extract overall similarity score
- Extract criterion-specific scores

Track record

Benchmark

16 / 19

test cases passed, vs 9 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

aiskillstore / marketplace

skills/abejitsu/ai-visual-accuracy-check/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

AI Visual Accuracy Check Skill

Purpose

What to Do

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills