Ready to supercharge your AI agents?

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

Get Started Free →

Dev Visual Verdict · evolution-foundation | DecimalAI

testingby evolution-foundation

Dev Visual Verdict

evolution-foundation/dev-visual-verdict

Source evolution-foundation/evo-nexus ↗License NOASSERTION

Visual regression testing — capture before/after screenshots of UI changes and compare.

SkillScore82Maintained

Automatic

QA & Test Engineering pack

Last verified 8/19/2026

What it changes

Passed 16 of 20 test cases with the skill, and 4 of 20 without it.

Without skill18%

With skill82%

Checks it passed that the model alone missed

The final verdict is set to IDENTICAL.
The report includes a final Verdict section.
The workflow ends with issuing a visual verdict.

and 14 more in the full report

14 fixed4 passed either way4 still failing0 broke

Pass-rate lift: +64 pp
Tokens: -32%
Agent turns: 0%
Response time: -59%

Model gemini-3.6-flashMeasured 8/19/2026v118 of 22 cases passed with skill · 20 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/evolution-foundation-dev-visual-verdict/SKILL.md https://app.decimal.ai/s/evolution-foundation-dev-visual-verdict/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add evolution-foundation-dev-visual-verdict, 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/evolution-foundation-dev-visual-verdict/ and pins it in .decimal/skills.lock

decimalai skills add evolution-foundation-dev-visual-verdict

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

curl -fsSL --create-dirs -o .claude/skills/evolution-foundation-dev-visual-verdict/SKILL.md https://app.decimal.ai/s/evolution-foundation-dev-visual-verdict/SKILL.md

Raw file: /s/evolution-foundation-dev-visual-verdict/SKILL.md ↗ · machine-readable summary at /s/evolution-foundation-dev-visual-verdict.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 14

Prompt

We refactored the underlying React render code for our primary modal dialog without changing any CSS styles. Baseline and post-change visual snapshots show 0% pixel difference. Construct the comparison table row and final verdict section for this check.

What was checked, without and with the skill
Checked	Without skill	With skill
The comparison table records 0% diff for unchanged components.	Passed	Passed
The final verdict is set to IDENTICAL.	Missed	Passed

case-16 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md51 linessingle file

Dev Visual Verdict

Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer.

Visual regression testing. Capture before/after screenshots of UI components, compare them, and flag unintended visual impact.

Use When

CSS / styling change that might cascade to other components
Component refactor where the visual output should remain identical
Theme change that needs to be verified across the app

Do Not Use When

Backend-only changes
Intentional redesigns (use @canvas-designer instead)
Single-component changes with obvious visual outcome

Workflow

Identify scope — which components could be affected
Capture baseline — screenshot current state of each affected component
Apply change — let @bolt-executor make the modification
Capture after — screenshot post-change state
Compare — flag any visual differences (pixel-level or layout-level)
Verdict — IDENTICAL / EXPECTED CHANGES / UNEXPECTED REGRESSION

Output

Saved to workspace/development/verifications/[C]visual-{component}-{date}.md:

## Visual Verdict — {component}

### Scope
- Components checked: [list]

### Comparison
| Component | Before | After | Diff | Verdict |
|---|---|---|---|---|
| Header | ![](before-1.png) | ![](after-1.png) | 0% | IDENTICAL |
| Footer | ![](before-2.png) | ![](after-2.png) | 12% | UNEXPECTED |

Track record

Benchmark

16 / 20

test cases passed, vs 4 / 20 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

evolution-foundation / evo-nexus

.claude/skills/dev-visual-verdict/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 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

Dev Visual Verdict

Use When

Do Not Use When

Workflow

Output

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills