跳到正文
cccskills
免费在 GitHub 公开

design-qa

Check a prototype against its original design direction and requirements before shipping. Compares implementation to the mockup/spec/context, flags drift in layout, spacing, type, color, states, and behavior, and reports a pass/fix list. Use when the user says "design QA", "does it match the design", "check against the spec", "conformance check", or before sharing/handing off a prototype. Part of the Product Design set. Uses a browser tool for visual comparison.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Design — Design QA

Verify the built prototype actually matches the intended design + requirements. Catch drift before it ships. Unlike design-audit (open-ended critique of any UI), QA is a conformance check against a known source of truth — it answers "does this match what we agreed to build?"

When to use

  • A prototype is built and you need to confirm it matches the mockup/spec before review.
  • Final gate before design-share or dev handoff.
  • "Does it match the design?", "conformance check".

When NOT to use

  • No spec/reference to compare against → that's open critique → design-audit.
  • Nothing built yet → build it first.

Inputs

  • The built prototype (local URL or path).
  • The source of truth: reference image/mockup, ./design/context.md, ./design/ideate/*.
  • Acceptance/success criteria (from context).

Workflow

  1. Capture the implementation via a browser-automation tool — screenshots of key screens and states (loading/empty/error/success).
  2. Visual conformance — compare to the reference: layout, type scale, spacing rhythm, palette, radii/shadows, iconography. Note every drift with the expected vs actual value.
  3. Behavioral conformance — walk the flow: do interactions, states, and navigation match the intended UX?
  4. Requirements conformance — does it satisfy the goal + success criteria from context? Any scope item missing?
  5. Accessibility sanity — contrast, focus order, target size, keyboard reachability (flag what needs manual AT testing — automated checks aren't full WCAG).
  6. Write ./design/qa.md: PASS items + prioritized fix list (severity × effort) + a verdict.

Output: ./design/qa.md

prototype: http://localhost:5173   source: ./mocks/onboarding.png + context.md
visual:
 ✓ layout matches  ✗ body type 14px (spec 16px)  ✗ accent #7C3 (spec #6366F1)
behavior:
 ✓ happy path  ✗ no error state on empty name (spec requires inline error)
requirements (vs success criteria):
 ✓ 3-step wizard  ✓ progress saved  ✗ missing "skip" affordance (scope v1)
a11y:
 ✗ CTA contrast 3.1:1 (<4.5)   manual: screen-reader pass still required
verdict: NOT READY — 4 fixes (2 HIGH: error state, contrast). Loop to design-prototype.

Quality bar

  • Compared against the locked source of truth, not personal taste.
  • Every miss cites which source it violates (mock / context / success criteria) + expected vs actual.
  • A11y findings distinguish automated checks from what needs manual AT validation.
  • A clear verdict: READY, or NOT READY with the blocking items named.

Common pitfalls

  • QA by opinion — drifting into "I'd prefer..." instead of "spec says X, build shows Y".
  • Skipping states — only checking the happy path; error/empty/loading are where drift hides.
  • Passing HIGH drift — don't green-light something with blocking visual/behavioral mismatches.
  • Overclaiming a11y — automated contrast/focus ≠ full WCAG conformance; say so.

Handoff

PASS → design-share. FAIL → loop the fix list back to design-prototype (or design-image-to-code for visual drift), then re-QA. Don't share stakeholder-facing prototypes with unresolved HIGH items without explicitly flagging them.

Tooling

Needs a browser-automation tool to capture screens/states for comparison. Without one, do a code-level + manual review and flag that visual conformance is unverified.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Rapidly generate up to 25 distinct ad creative hypotheses for testing. Produces a matrix of angles (pain, benefit, social proof, urgency, curiosity, comparison) x formats (static, carousel hook, UGC-style, bold-text overlay) with headline, visual prompt, and rationale for each, then generates the visuals with any image tool. Use when the user wants "ad variations", "ad concepts", "creative testing batch", "give me 25 ads", or paid-social creative ideation. Part of the Creative Production set.

中文简介正在准备中。当前显示原文说明。

DKeken/codex-skills-alternative152026年6月3日 更新

Pick a visual direction before generating any creative. Produces 3-6 named, distinct visual directions (e.g. premium minimal, bold maximalist, lifestyle/editorial, retro, techno-brutalist) with rationale + sample prompts, then generates one reference image per direction so the user can choose. Use when the user says "explore visual direction", "what style should this be", "give me directions/looks", or before ads/scene/shot work when no style is locked. Part of the Creative Production set.

中文简介正在准备中。当前显示原文说明。

DKeken/codex-skills-alternative152026年6月3日 更新

Build visual territories (mood boards) for team alignment before production. Groups references into 2-4 named territories, each with palette, texture, typography feel, and 4-6 generated sample tiles, so a team can agree on a direction. Use when the user says "moodboard", "visual territories", "align the team on a look", "reference board", or needs stakeholder sign-off on aesthetic before generating final assets. Part of the Creative Production set.

中文简介正在准备中。当前显示原文说明。

DKeken/codex-skills-alternative152026年6月3日 更新

Build visuals that sell a specific offer and value proposition. Translates an offer (price, bundle, guarantee, bonus, deadline) into hero visuals that make the value legible at a glance. Use when the user says "visualize the offer", "promo creative", "make the deal look good", "value prop hero", or has a concrete offer to merchandise. Part of the Creative Production set.

中文简介正在准备中。当前显示原文说明。

DKeken/codex-skills-alternative152026年6月3日 更新

Take a chosen visual to finished, production-ready state. Runs cleanup + refinement passes (fix artifacts, balance composition, color-grade, sharpen text, conform to spec/aspect) using image edit/regenerate. Use when the user says "polish this", "finalize", "clean up the image", "production-ready", "fix the artifacts", or has a selected visual that needs finishing. Final stage of the Creative Production set.

中文简介正在准备中。当前显示原文说明。

DKeken/codex-skills-alternative152026年6月3日 更新

Connect business positioning to a concrete visual language. Maps strategic positioning (category, differentiator, who-it's-for, who-it's-against) onto visual decisions — palette, type, imagery, tone — so the look reinforces the strategy. Use when the user says "positioning into visuals", "what should the brand look like given our strategy", "align visuals with positioning", or is moving from strategy to brand expression. Part of the Creative Production set.

中文简介正在准备中。当前显示原文说明。

DKeken/codex-skills-alternative152026年6月3日 更新

查看 DKeken 的全部技能

报告此技能的问题