HeyEddi-comHeyEddi-com/heyeddi-skills/skills/visual-auditor/SKILL.md

visual-auditor

Skill0 starsChanged 3 months agoMITView on GitHub

ALWAYS use after design/implement for screenshot QA: capture, contrast, fix, document. Mandatory after handoff. Fast widths 375/768/1440; before flagship done use --preset done (375/430/768/1024/1440/1920). Auto-fix — never report-only unless user says audit-only. Edges must read on the plane.

In this repository51 other files it gives its agents.
- .cursor/rules/skill-authoring.mdcCursor rule
- backend-type-bridgerSkill
- composable-patternsSkill
- dart-type-bridgerSkill
- design-handoff-flutterSkill
- design-system-generalizerSkill
- engineering-excellenceSkill
- flutter-engineeringSkill
- flutter-patternsSkill
- heyeddi-designSkill
- heyeddi-handoffSkill
- heyeddi-intakeSkill
- heyeddi-orchestratorSkill
- heyeddi-productSkill
- heyeddi-pr-respondSkill
- heyeddi-pr-reviewSkill
- no-duplicate-uiSkill
- pre-merge-gateSkill
- primevue-openprops-architectSkill
- project-engineeringSkill
- ux-flow-auditorSkill
- verify-buildSkill
- visual-auditorSkill
- backend-type-bridgerSkill
- composable-patternsSkill
- dart-type-bridgerSkill
- design-handoff-flutterSkill
- design-system-generalizerSkill
- engineering-excellenceSkill
- flutter-engineeringSkill
- flutter-patternsSkill
- heyeddi-ci-configSkill
- heyeddi-ci-failsSkill
- heyeddi-ci-guideSkill
- heyeddi-ci-runnersSkill
- heyeddi-designSkill
- heyeddi-handoffSkill
- heyeddi-intakeSkill
- heyeddi-orchestratorSkill
- heyeddi-productSkill
- heyeddi-pr-respondSkill
- heyeddi-pr-reviewSkill
- heyeddi-setupSkill
- heyeddiSkill
- no-duplicate-uiSkill
- pre-merge-gateSkill
- primevue-openprops-architectSkill
- project-engineeringSkill
- taste-penpotSkill
- ux-flow-auditorSkill
- verify-buildSkill

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Run automatically after every @heyeddi-handoff, @design-handoff-flutter, and stack implement pass
line 21
Very specific:
After @heyeddi-design craft or @heyeddi-handoff on a route
line 38
Very specific:
Read reference/visual-review.md and reference/fix-loop.md.
line 45
Distinctive:
When you have finished the user's request for this skill (not after every tool call or subagent phase), suggest what to run next:
line 103
Very specific:
Add --route /path if you worked a specific route.
line 111

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Visual Auditor

See the UI. Compare to spec. Fix. Document. Re-verify.

You are a visual QA implementer: not a screenshot-only subagent. You read captures against product (persona, route intent, purpose) and design (tokens, mockup-brief, hierarchy), fix issues in Vue/CSS in the same turn, and log every change.

On marketing and app flagships, also apply the calm-wow lens in reference/visual-review.md (thesis hero, living atmosphere, brand-only status craft, reduced-motion) and the done gate (6 widths + logo-off brand test).

Default behavior (no confirmation)

Always fix actionable visual issues in code in the same turn
Never deliver a bullet list of problems without fixing (exception: user explicitly said audit-only, no code)
Run automatically after every @heyeddi-handoff, @design-handoff-flutter, and stack implement pass

Width presets

Preset	Widths	When
fast (default capture)	`375, 768, 1440`	Iteration during craft/polish
done / flagship	`375, 430, 768, 1024, 1440, 1920`	Before calling marketing/flagship done; `finalize_visual_review` defaults here

capture_screenshots --route / --preset fast
capture_screenshots --route / --preset done
finalize_visual_review --route / --check   # defaults to done

When to use

After @heyeddi-design craft or @heyeddi-handoff on a route
Green-on-green, illegible text, layout drift vs brief
Pre-merge visual gate with fixes, not a issue list alone
@heyeddi-product delegated legibility research: you fix, they synthesize

Mandatory pipeline

Read reference/visual-review.md and reference/fix-loop.md.

load_visual_context --route /path --write-review
capture_screenshots --route /path
audit_contrast --route /path
→ READ PNGs + product.md + design.md + mockup-brief + contrast report
→ FIX each error/actionable warn in code
→ append_fix_log (per fix)
finalize_visual_review --route /path --check

Never deliver only a bullet list of problems without fixing them. Report-only is allowed only when the user explicitly said audit-only / no code changes.

Review against specification

Lens	Source
Product	`route_intent`, page purpose, persona `success_feeling`
Design	`design.md` tokens, `mockup-brief.md` regions, wireframe if no PNG
Legibility	`audit_contrast` automated + your eyes on captures

Tools

Tool	Role
`load_visual_context`	Spec paths, captures, contrast summary; `--write-review` scaffolds review doc
`capture_screenshots`	PNGs → `.heyeddi/audits/visual/screenshots/` (`--preset fast\|done`)
`audit_contrast`	WCAG + motion-over-text
`append_fix_log`	Document each fix with spec reference + files
`finalize_visual_review`	Re-capture at done widths, contrast `--check`, close review

Subagents

Shell scripts for capture/contrast; you (main agent) read images, edit code, call append_fix_log. See reference/subagents.md.

Artifacts (`.heyeddi/audits/visual/`)

Path	Purpose
`screenshots/`	Responsive captures
`reviews/<feature>-review-<date>.md`	Review vs product + design
`fix-log.md` / `fix-log.jsonl`	Every fix documented
`<feature>-contrast-<date>.md`	Automated contrast

Env

DEV_SERVER_URL: Vue (default http://localhost:5173)
FLUTTER_WEB_URL: Flutter web

Chain

@primevue-openprops-architect: run after token/CSS fixes
@heyeddi-design polish: if IA problems remain after visual pass
@pre-merge-gate: after finalize_visual_review --check passes

When the task is complete: suggest next skills

When you have finished the user's request for this skill (not after every tool call or subagent phase), suggest what to run next:

Run:

python .agents/skills/heyeddi/scripts/suggest_next_skill.py --current-skill visual-auditor --project-root .

Add --route /path if you worked a specific route.

Include the script's ### Next step block in your final reply. The user copies the Prompt line into chat (e.g. @heyeddi-design craft /settings).

Pass --mode shape (or craft, audit, etc.) when you know which sub-command just finished.

See @heyeddi → reference/next-skill-handoff.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free