design-media-quality-evaluation
Generated media quality evaluation for original visual media, controlled revisions and reusable campaign production.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- design-media-quality-evaluation
- description
- Generated media quality evaluation for original visual media, controlled revisions and reusable campaign production.
03 SKILL.md 正文
Generated media quality evaluation
Inputs and workflow
Read the media workflow and reuse accepted upstream inputs. Use the production packet for concrete inputs and outputs. Missing evidence stays explicit; tool availability is not production acceptance.
Use the shared rubric to inspect actual candidates. First reject factual product changes, incorrect required text, unusable crops, broken rights or missing required output specifications. Do not average these failures into a flattering score. Then score composition, brand fit, craft, readability and campaign coherence with visible evidence and exact frame/region references.
Review native-size output, contextual viewing scale and a candidate contact sheet with comparable crops. Video requires complete playback plus frame inspection around cuts, motion peaks and loop join; selected attractive frames alone are insufficient. Separate aesthetic preference from defects and user validation. Recommend accept-as-candidate, repair, reject or held for evidence, with a concrete repair order. Record independent review separately. Do not claim sales uplift, readability at a real distance or hardware compatibility from a desktop preview.
Handoff and acceptance
Return artifact locations, exact baseline, candidate status, observed checks, remaining defects and next owner through the existing handoff. Apply the rubric. Preserve original assets and follow the media execution contract. Stop at the agreed revision/budget limit and report an unresolved result rather than silently changing the brief.
Campaign-wide final review
Review a version-bound manifest of every still, loop, interactive screen, format and fallback. Compare contact sheets for product identity, type hierarchy, palette, light, message and disclosure consistency; also play all motion assets and walk the interactive sequence. Static thumbnails cannot reveal timing or interaction failures. Confirm alternate formats remain distinct compositions with the same brand logic. Check promotion validity and source version across primary/fallback variants. Record per-asset defects and campaign-level conflicts separately. A failure in one asset holds that asset and dependent variants; do not mark the whole campaign approved by averaging scores. Return the manifest, findings, repair owners and exact scope approved for the next stage.
For physical-screen work, use the display production detail checklist and preserve actual test evidence.
Photographic rejection gate
For photographic briefs, reject schematic products, implausible geometry, material response inconsistent with the specified material (real plastic is not a defect), inconsistent reflections or shadows, floating objects, malformed packaging, and visibly artificial compositing before scoring. Inspect the complete image, native-resolution material/edge/label crops and intended viewing size. Cite the failing region and required repair. Do not confuse deliberate photographic shadow or stylization approved in the brief with a defect.
Return separate decisions for photographic appearance, factual product fidelity, brand/art-direction fit, technical delivery and human acceptance. Unknown required evidence holds its dependent stage. Technical passes never override visual rejection. Freeze the accepted still version before motion; review temporal identity, texture stability, transitions and the whole loop separately. The same gate applies to fallback and adapted assets.
Apply the scope, evidence and decision-combination rules in the shared rubric.
Version-Timestamp: 2026-09-16T18:27:08.062526-04:00
Rendered calibration
Version-Timestamp: 2026-09-16T18:06:33.096655-04:00
Use the shared fictional collection for comparative quality, rendered typography, precise revision and motion evidence. Inspect its recorded limits; do not inherit its fonts, style or agent review as approval for another brand.
04 同仓库更多 Skills
web-design
Load before planning, designing, auditing or launching any website, landing page, cinematic hero, microsite or above-the-fold layout, or a prompt for Lovable, Bolt or v0 to build one, including regulated (prescription drug, health, finance), multilingual or market-specific launches. Covers page types (home, product, pricing, about, blog), conversion and ethical persuasion, responsive and fluid layouts, Core Web Vitals, SEO and structured data, localization and language-law requirements, stack and CMS choice (Astro, Next.js, WordPress, Webflow, Framer) and launch QA.
ux-design
Load before designing or reviewing any flow, form, onboarding, navigation or content for real users, especially low-literacy, older, neurodivergent, child or other specific audiences. Covers research and usability tests, heuristic reviews, personas and jobs to be done, journeys and service blueprints, information architecture, UX laws, SUS, SEQ and HEART metrics, plain language and reading level, and microcopy and error messages.
ui-design
Load before designing or specifying any interface screen or component, even a quick one: forms, tables, navigation, dashboards, onboarding, auth and passkeys, pricing, checkout, search and filters, settings, empty, loading and error states, notifications, consent and age-appropriate flows, and AI chat and agent interfaces, all to WCAG 2.2 AA. Also picks React UI libraries (toasts, drawers, command menus). Gives component specs, state matrices, sizes, density and keyboard and accessibility behavior.
typography
Choose, pair, size and set type for brand, web, app, print, slides, signage and motion: modular scales, fluid clamp() type, measure, leading, tracking, OpenType features, font licensing and web font loading, and multiscript setting for CJK, Arabic, Hebrew, Devanagari and Thai. Use when selecting or pairing fonts, building a type scale or type tokens, fixing weak hierarchy or bad line breaks, setting long-form text or numbers, loading web fonts, or localizing type for another market.
reference-reconstruction
Reconstructs the observed interface and behavior of a supplied app, site or screenshot set using a screen index, measurements, state and command maps, reusable components and matched-condition comparisons. Use when asked to reverse engineer, clone, reproduce or match a reference product, then adapt it if requested.
print-packaging-social
Load before any print, packaging, label, barcode, social, out-of-home, slide-deck or email design question, even a quick one, and before making finished collateral files. Specs: bleed, safe zones, 300ppi, CMYK, PDF/X preflight, dielines, barcodes, social formats with 9:16 safe areas, billboard letter heights, 16:9 decks, bulletproof email. Renders token-driven brand books, sell sheets, cards, carousels and decks to PDF and PNG with a Canva editable twin.