Install
$ agentstack add skill-giang6283623-minimal-vibe-coding-kit-visual-design-loop ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Visual Design Loop
Use this skill to improve a visible UI through controlled render-review-fix loops. Keep the brief and existing project conventions as the source of truth; do not add new product requirements just because a screen could be enhanced.
Gate
Do not start loops by default. Score the need first, 0-2 per question:
- Did the change alter a user-visible surface?
- Does the outcome depend on subjective visual judgment (layout, typography, color)?
- Could a visual regression reach end users unnoticed by existing tests?
- Score 0-2: skip the loop; rely on the repo validation command.
- Score 3-4: one screenshot check with at most one targeted fix; no loop.
- Score 5-6: propose the loop with its budget and estimated cost, then wait for explicit user approval before the first loop.
Report the score and decision in one line, for example: "visual gate 5/6: proposing a 3-loop run, awaiting approval".
Contract
Before editing, resolve and state:
- Goal.
- Target surface: route, page, component, flow, or supplied screenshot.
- Source of truth: current brief plus repo instructions, design system, nearby UI, and
backbone.ymlwhen present. - Render method: local URL, app command, Storybook story, preview command, static file, or supplied screenshot.
- Screenshot method: browser screenshot, Playwright, in-app browser, provided image, or equivalent.
- Editable paths.
- Protected paths.
- Budget: default 3 loops.
- Timeout: default 10 minutes per loop.
- Log path:
/tmp/design-{project_slug}.md.
If render or screenshot capture is missing and cannot be inferred safely, ask for the missing command, URL, or image before editing.
Baseline
- Render the target surface.
- Capture or inspect the baseline screenshot.
- Review visible issues only; do not invent findings.
- Create or update
/tmp/design-{project_slug}.md. - Log the baseline screenshot, visual score, main issues, and any render constraints.
Derive project_slug from backbone.yml project.name when available; otherwise use the repository directory name.
Visual rubric
Score screenshots from 1 to 5 using:
- Visual hierarchy: primary content and action are obvious.
- Layout and spacing: alignment, rhythm, density, whitespace.
- Typography: scale, contrast, readability, consistency.
- Color and contrast: accessible, intentional, not noisy.
- Component consistency: matches nearby UI and design system.
- Responsiveness: works at relevant viewport sizes.
- Interaction states: hover, focus, disabled, empty, loading, and error states when relevant.
- Product fit: improves the brief without adding unnecessary features.
Loop
For each loop:
- Review the latest screenshot.
- Identify the highest-impact visual issue.
- Form one small hypothesis.
- Apply one targeted fix inside editable paths only.
- Render again.
- Capture the after screenshot.
- Compare before and after.
- Keep the change only if quality improves, or if quality is equal with simpler and safer implementation.
- Revert only your own loop changes if the result is worse.
- Run the repo validation command when code changed.
- Append the loop result to
/tmp/design-{project_slug}.md.
Each loop entry must include:
- Loop number.
- Screenshot reviewed.
- Issue found.
- Hypothesis.
- Fix applied.
- Before/after judgment.
- Rubric score before.
- Rubric score after.
- Validation result.
- Remaining concerns.
- Stop/continue decision.
Stop criteria
Stop when:
- The design is polished enough for the brief.
- The latest loop gives no meaningful improvement.
- Further changes would be subjective or overworked.
- Budget is reached.
- Validation fails for a non-trivial reason.
- A product or design decision is required from the user.
- Render or screenshot tooling is unavailable.
Final report
Report:
- Baseline score.
- Final score.
- Screenshots reviewed.
- Changes kept.
- Changes discarded, if any.
- Validation result.
- Remaining risks or design decisions.
- Log path.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: giang6283623
- Source: giang6283623/minimal-vibe-coding-kit
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.