Starlight-IntelligenceStarlight-Intelligence/starlight-agent-skills/skills/coding/starlight-design-review/SKILL.mdstarlight-design-review
Skill1 starsChanged 4 months agoMITView on GitHub
Audit a digital experience against its own design language, information hierarchy, accessibility, responsive behavior, interaction states, content truth, and visual craft. Use for websites, applications, dashboards, generated media, or frontend changes before release.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- frankxai/starlight-agent-skillsword for word, first seen Jul 27, 2026
Other versions1 project uses a version of this.
Word for word · 1
- frankxai/starlight-agent-skills★ 1100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository43 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adapters/claude.mdCLAUDE.md
- arcanea-mythic-overlaySkill
- frankx-authority-postSkill
- starlight-voiceSkill
- cosmic-code-labSkill
- starlight-autoplanSkill
- starlight-ceo-reviewSkill
- starlight-devex-reviewSkill
- starlight-eng-reviewSkill
- starlight-investigateSkill
- starlight-qaSkill
- starlight-shipSkill
- starlight-specSkill
- apod-to-shortSkill
- arxiv-space-paper-to-briefSkill
- cosmic-mythic-overlaySkill
- nasa-image-to-atlas-pageSkill
- rights-check-nasa-esaSkill
- rocket-launch-to-reelSkill
- space-social-repurposerSkill
- coding-challenge-generatorSkill
- explain-like-cosmic-professorSkill
- simulation-lab-builderSkill
- caption-and-hashtagSkill
- nasa-image-to-shortSkill
- rocket-launch-to-youtubeSkill
- social-repurposerSkill
- thumbnail-conceptSkill
- arxiv-paper-to-briefSkill
- claim-verificationSkill
- mission-page-to-summarySkill
- media-studioSkill
- publishing-studioSkill
- software-studioSkill
- template-studioSkill
- world-experience-studioSkill
- affiliate-auditSkill
- agentic-incomeSkill
- capability-foundrySkill
- notion-operating-systemSkill
- payments-mandateSkill
- swarm-queen-coordinationSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
Verify the primary task and content hierarchy before judging decoration.
- Distinctive: line 42
Use the host-approved browser or design connector and an existing preview when possible.
- Distinctive: line 46
No universal font, gradient, glass, grain, or spacing prescription.
≈ “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.
Files
Starlight Design Review
Purpose
Judge whether the experience communicates the right thing, in the right order, with a coherent visual system and usable states across real viewports and input modes.
When it fires
- A user-facing surface is new or materially changed.
- A visual system, motion pattern, or generated asset is introduced.
- The user asks for design, taste, accessibility, or anti-slop review.
Inputs
- Product intent, audience, and primary task.
- Existing design system or taste kernel.
- Live preview or runnable surface and supported breakpoints.
- Content, asset provenance, accessibility, and performance constraints.
Workflow
- Verify the primary task and content hierarchy before judging decoration.
- Compare the implementation to its declared design language; do not impose a generic aesthetic.
- Inspect typography, spacing, contrast, alignment, density, and sentence-case labels.
- Exercise keyboard, focus, pointer, loading, empty, error, success, and reduced-motion states.
- Review mobile, tablet, and desktop for overflow, occlusion, and reading order.
- Inspect generated media for provenance, legibility, identity drift, and appropriate placement.
- Report defects by user impact with visual evidence and a precise correction.
Output contract
Return verdict, task/hierarchy assessment, system-coherence findings, accessibility findings, responsive findings, interaction-state findings, media/provenance findings, prioritized corrections, and verification receipts.
Tools & MCP
Use the host-approved browser or design connector and an existing preview when possible. Do not start arbitrary browser binaries or publish assets without authorization.
Quality bar
- No universal font, gradient, glass, grain, or spacing prescription.
- Sentence case is preserved unless official product casing requires otherwise.
- Accessibility and reduced motion are release criteria, not polish.
- Screenshots support findings but do not replace semantic or interaction checks.
Example
Input: “Review the new marketplace on desktop and phone.”
Good output: validate the purchase journey, heading order, focus names, state truth, line length, tracking, overflow, and primary CTA at both viewports, then list only evidence-backed corrections.
Built on SIP — Starlight Intelligence Protocol Vertical: starlight-agent-skills · portable capability layer
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
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.