Reimagine It Audit
Kayforkind/reimagine-it
Design Health — runs 19 deterministic quality checks on HTML output.
Design, review, and visually QA web and app interfaces against explicit design laws so shipped screens look intentional instead of generic AI output.
$ npx skills add JasonColapietro/suede-creator-skills --skill frontend-design-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install JasonColapietro/suede-creator-skills frontend-design-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/vendorable/frontend-design-review .claude/skills/frontend-design-review && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "frontend-design-review" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/vendorable/frontend-design-review into .claude/skills/frontend-design-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frontend-design-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/JasonColapietro/suede-creator-skills/tree/main/vendorable/frontend-design-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add JasonColapietro/suede-creator-skills --skill frontend-design-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install JasonColapietro/suede-creator-skills frontend-design-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/vendorable/frontend-design-review .agents/skills/frontend-design-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "frontend-design-review" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/vendorable/frontend-design-review into .agents/skills/frontend-design-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frontend-design-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JasonColapietro/suede-creator-skills --skill frontend-design-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install JasonColapietro/suede-creator-skills frontend-design-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/vendorable/frontend-design-review .cursor/skills/frontend-design-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "frontend-design-review" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/vendorable/frontend-design-review into .cursor/skills/frontend-design-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frontend-design-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/JasonColapietro/suede-creator-skills.git --path vendorable/frontend-design-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add JasonColapietro/suede-creator-skills --skill frontend-design-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install JasonColapietro/suede-creator-skills frontend-design-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/vendorable/frontend-design-review .gemini/skills/frontend-design-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "frontend-design-review" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/vendorable/frontend-design-review into .gemini/skills/frontend-design-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frontend-design-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install JasonColapietro/suede-creator-skills frontend-design-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add JasonColapietro/suede-creator-skills --skill frontend-design-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/vendorable/frontend-design-review .github/skills/frontend-design-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "frontend-design-review" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/vendorable/frontend-design-review into .github/skills/frontend-design-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frontend-design-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JasonColapietro/suede-creator-skills --skill frontend-design-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install JasonColapietro/suede-creator-skills frontend-design-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/vendorable/frontend-design-review .opencode/skills/frontend-design-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "frontend-design-review" agent skill from https://github.com/JasonColapietro/suede-creator-skills/tree/main/vendorable/frontend-design-review into .opencode/skills/frontend-design-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frontend-design-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
frontend-design-reviewDesign, review, and visually QA web and app interfaces against explicit design laws so shipped screens look intentional instead of generic AI output.
Frontend Design Review is an agent skill from JasonColapietro/suede-creator-skills. Design, review, and visually QA web and app interfaces against explicit design laws so shipped screens look intentional instead of generic AI output.
Its SKILL.md is about 5.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/design-laws.md` and `references/scoped-bans.md`).
It sits in Media & Creative, covering Design review and critique. The repository describes itself as: Open-source AI skills for SEO, AI search visibility, conversion copy, marketing strategy, and business operations. Reusable workflows for Claude Code and Codex, plus code review… The licence is MIT.
7 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit e5f94d7. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
npxgitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npx and git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Frontend Design Review loads about 5.5k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 2,551 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from JasonColapietro/suede-creator-skills at commit e5f94d7, republished under its MIT licence (© JasonColapietro). 2,551 words, ~5,455 tokens.
.claude/skills/frontend-design-review/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Most AI-generated interfaces fail the same way: they compile, they look plausible in code, and they render as the average of every landing page in the training data. Dark blue for a developer tool. Purple gradient for a music app. Three icon cards in a row. A tiny uppercase eyebrow above every section.
This skill replaces taste-by-vibes with thresholds. It gives Claude a design contract to lock before writing CSS, numeric laws to satisfy while writing it, a list of banned defaults with the specific replacement for each, and a render-and-compare loop so nothing is called done from reading code. It works on product UI, dashboards, marketing pages, component systems, and app store assets.
Core principle: strip the logo and the surface must still be unmistakably this product, and render the result before claiming it works.
Skip it for backend-only work, or a one-line copy change with no visual consequence.
clamp(), line measure, layout
and z-index rules, component laws for forms, modals, tables, navigation, and
empty states, plus motion curves and durations. See
references/design-laws.md.visual-qa-report.md with findings ordered P0 to P3.ship, ship-with-caveats, or hold, with the
evidence that supports the verdict.Review the design of the dashboard at http://localhost:3000/app and tell me
what is wrong with it. Render it at desktop and mobile before answering.Claude inspects the source, renders the page, checks it against the design laws and the banned-defaults list, and reports findings with file names and specific fixes.
Redesign our pricing page. Before writing code:
1. Write the design contract (audience, page job, primary action, register).
2. Name the aesthetic direction and the one memorable move, and explain why the
obvious choice for this category is the wrong one.
3. Propose two approaches with tradeoffs and let me pick.
Then build it, render at 1280x900 and 390x844, and finish with a ship gate.Compare ./designs/hero-mock.png against the implementation at
http://localhost:5173 and save visual-qa-report.md with P0-P3 findings.Audit our design system in ./src/styles and score it out of 100 across color
consistency, typography hierarchy, spacing rhythm, component consistency,
responsive behavior, dark/light behavior, motion restraint, accessibility,
information density, and polish. Fix the two lowest dimensions.User: "Our analytics dashboard looks like every other analytics dashboard. Fix it."
Output:
DESIGN PREFLIGHT
target=./apps/web surface=/dashboard register=product
context=partial (no DESIGN.md) render=pass (1280x900, 390x844)
DIAGNOSIS
The surface is the category average. Three findings explain most of it.
P0 Color is decorative, not semantic. src/styles/tokens.css:14
Six blues, none of which encode meaning. Threshold breaches, healthy
ranges, and stale data all render in the same accent.
Fix: commit to Restrained strategy. Tinted neutrals plus one accent
under 10% of surface area, reserved for threshold breaches only.
P1 Card-in-card nesting. src/components/MetricGrid.tsx:31
Each metric is a card inside a section card. Cards are for items that
are independently scannable or selectable, not section wrappers.
Fix: rows with a shared rule, one card level maximum.
P1 Hero-metric template. src/components/Headline.tsx:8
"$2.4M" at 80px/weight-900 with a 12px label under it. Isolated big
numbers read as marketing, not instrumentation.
Fix: put the number back in the row it belongs to, with its delta and
its comparison window beside it.
DIRECTION
Aesthetic: product-utilitarian. Scene: an on-call engineer scanning for the
one number that moved, at 2am, on a second monitor. That scene forbids hero
type and rewards density plus one loud state color.
Memorable move: a sparkline gutter down the left edge of every row, so the
shape of the week is readable before any number is.
SHIP GATE
Surface: /dashboard
Done signal: desktop + mobile render, contrast pass
Evidence: dashboard-desktop.png, dashboard-mobile.png, contrast 7.1:1 body
Blockers: none
Accepted caveats: empty state still generic, tracked separately
Next action: apply P0 token change, re-render
Status: ship-with-caveatsInspired by: the design workflow from the Suede Creator Skills collection by Jason Colapietro, generalized for any product.
npx playwright screenshot <url> --viewport-size=1280,900 desktop.png
captures the render. One-time setup: npx playwright install chromium.[NEEDS REAL DATA].The sections below are the operating detail. Read them when doing the work, not when deciding whether the skill applies.
Before design work, read the surface context:
PRODUCT.md if present: users, brand, tone, anti-references, principles.DESIGN.md if present: color tokens, type scale, component inventory, spacing.AGENTS.md, CLAUDE.md, AI_HANDOFF.md, or README.md for surface context.If those files are missing on a major surface, note the gap, proceed with what is available, and offer to create them afterward.
State the preflight before starting:
DESIGN PREFLIGHT
target=<repo-or-folder> surface=<route-or-url> register=<brand|product>
context=<pass|partial|none> design_system=<loaded|not_found>
render=<pass|pending|skipped:reason>Choose the smallest path that fits the request.
visual-qa-report.md.Before a new surface, significant redesign, reusable component family, or design-system pass, lock these:
For a narrow one-element fix, document only the relevant items instead of forcing a full spec.
The numeric rules (spacing, type scale, color, contrast, dark mode, density, motion, component behavior) are in references/design-laws.md. Read that file whenever writing or reviewing actual styles. It is not needed to route a request or scope the work.
What is banned, the scope each ban applies to, and the narrow allowed exceptions are in references/scoped-bans.md. Read it when a design choice looks like it needs an exception, or when reviewing whether one was legitimately taken.
Commit to a direction before writing code, and name it explicitly.
Tonal spectrum, pick one and execute it with precision:
Bold maximalism and refined minimalism both work. The failure mode is neither: a design with no committed direction reads as generic.
Unforgettable factor: every major surface should have one move that earns memory, and it should be subject-native, something that only makes sense for this product. A chain-of-title timeline for a rights platform. A live request waterfall for an API tool. A shift-coverage ribbon for a scheduling app. Name it before implementation.
AI slop check: run both reflex tests before committing.
Theme sentence: name the physical scene concretely enough that it forces the design answer. Dark versus light is never a default. Not dark because tools look cool dark, not light to play it safe.
Background and atmosphere: gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows, grain overlays, and decorative borders are legitimate tools when they serve the aesthetic. Do not substitute generic gradient blobs, bokeh orbs, or CSS-only approximations for real art direction.
For any major surface, reusable app shell, or important component family, produce these at the smallest useful fidelity:
DESIGN.md or
design-tokens.json.Extract a design-system issue when a token, component, spacing pattern, color, type treatment, or state pattern repeats at least three times or controls a high-visibility surface. Classify drift root cause as token missing, token ignored, component gap, content pressure, platform convention, or legacy debt.
For broad audits, score:
Color consistency: /10
Typography hierarchy: /10
Spacing rhythm: /10
Component consistency: /10
Responsive behavior: /10
Dark/light behavior: /10
Motion restraint: /10
Accessibility: /10
Information density: /10
Polish: /10
Total: /100Below 70/100 the system is failing: fix the two lowest dimensions before styling new features on that surface. Any dimension at 4/10 or lower is a P1 finding.
npx playwright screenshot <url> --viewport-size=1280,900 desktop.png and
--viewport-size=390,844 mobile.png, or the environment's built-in preview
or screenshot tool. For app store submissions: 1290x2796 (6.7-inch),
1488x2266 (iPad Pro 13-inch).git diff --check when files changed. Verify live URLs before
claiming public behavior.If any of these thoughts appear, stop and run the check being skipped:
[NEEDS REAL DATA] flag.When comparing a source visual target against an implementation, save
visual-qa-report.md with:
final result: passed or final result: blocked.Compare source and implementation in the same visual pass, not from memory. Check typography, spacing and layout, colors and tokens, image and asset fidelity, logos and icons, copy and content, loading/empty/error/hover/focus/ active states, responsiveness, accessibility, and motion where relevant.
Use blocked when a required artifact is missing for the comparison, or when
actionable P0/P1/P2 issues remain. Use passed only when no actionable P0/P1/P2
findings remain.
For launch pages, app shells, public marketing surfaces, app store assets, or high-visibility dashboard work, end with:
Surface:
Done signal:
Evidence:
Blockers:
Accepted caveats:
Next action:
Status: ship | ship-with-caveats | holdUse hold when a core path is broken, claims are false, screenshots do not match
the implementation, accessibility blocks a primary action, or the live route
cannot be verified. Use ship-with-caveats only when the caveat is explicit,
non-critical, and acceptable for the launch stage.
Do not call work done because the code changed. Call it done only when the done signal has been checked or the remaining gap is named.
Findings lead, rationale follows. Name the file and the line. For builds, state what changed and show the render evidence. Do not narrate internal process step names in user-visible output.
© JasonColapietro, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (references) in vendorable/frontend-design-review of JasonColapietro/suede-creator-skills.
Open the folder on GitHubat commit e5f94d7
Frontend Design Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Frontend Design Review this skillJasonColapietro/suede-creator-skills | 127 | — | ~5.5k | Automated safety check: Pass | MIT | |
| Reimagine It AuditKayforkind/reimagine-it | 205 | — | ~756 | Automated safety check: Pass | MIT | |
| Design Reviewtsubotax/melta-ui | 201 | — | ~504 | Automated safety check: Pass | MIT | |
| Canva Design Feedbackcanva-sdks/canva-skills | 119 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Design Critiquepaperclipai/paperclip | 100k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Design CritiqueWrongStack/WrongStack | 374 | — | ~2.5k | Automated safety check: Pass | MIT |
Kayforkind/reimagine-it
Design Health — runs 19 deterministic quality checks on HTML output.
tsubotax/melta-ui
HTMLファイルをmelta UIデザインシステムに照らしてレビューし、違反を検出・分類・修正提案する。トリガー: 「デザインレビュー」「DSチェック」「禁止パターンチェック」「design review」「check compliance」「DS準拠確認」。対象ファイルのパスを引数で受け取る。
canva-sdks/canva-skills
Read a Canva design and return structured, actionable design feedback — visual hierarchy, copy/messaging, layout & spacing, consistency, readability, and accessibility.
paperclipai/paperclip
Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.
WrongStack/WrongStack
A skill your agent uses to audit an interface that already exists and say precisely why it looks generated, templated, or unfinished — a scored rubric across composition, typography, color, states…
wondelai/skills
Review designs, products, and features with Steve Jobs' standards: ruthless simplicity, focus, and end-to-end excellence.
JasonColapietro/suede-creator-skills
Lints a local music or media release folder and scores its readiness, flagging missing files, weak metadata, artwork and stem problems, split gaps and rights blockers.
JasonColapietro/suede-creator-skills
Turns messy creator materials into an offline rights-and-provenance transfer package: hashed asset inventory, intake manifest, credits, license notes and a missing-information report.
JasonColapietro/suede-creator-skills
Turns a video clip, interview moment or transcript into a package that bridges viewers to a long-form guide, with rights, claim and approval gates along the way.
JasonColapietro/suede-creator-skills
Checks a Suede AI MCP server release against a live process: the full JSON-RPC lifecycle, schemas, annotations, malformed input, catalog agreement and install docs.
JasonColapietro/suede-creator-skills
Takes a native Android app from product idea to Google Play release, covering Compose architecture, policy checks, privacy, billing, testing, signing and rollout.
JasonColapietro/suede-creator-skills
Suede-owned paid-media creative system for hooks, headlines, primary text, static and motion concepts, platform specs, review pages, and test-ready variant batches.
Categories
Design, review, and visually QA web and app interfaces against explicit design laws so shipped screens look intentional instead of generic AI output. Frontend Design Review is an agent skill from JasonColapietro/suede-creator-skills. Design, review, and visually QA web and app interfaces against explicit design laws so shipped screens look intentional instead of generic AI output.
Frontend Design Review fits situations like: tasks that involve Design review and critique.
Run `npx skills add JasonColapietro/suede-creator-skills --skill frontend-design-review -a claude-code`. Or copy the skill folder (vendorable/frontend-design-review in JasonColapietro/suede-creator-skills) into .claude/skills/frontend-design-review in your project. Claude Code loads it when a task matches its description.
Run `npx skills add JasonColapietro/suede-creator-skills --skill frontend-design-review -a codex`. Or copy the skill folder (vendorable/frontend-design-review in JasonColapietro/suede-creator-skills) into .agents/skills/frontend-design-review in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JasonColapietro/suede-creator-skills --skill frontend-design-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/frontend-design-review, .gemini/skills/frontend-design-review, .github/skills/frontend-design-review and .opencode/skills/frontend-design-review in your project.
Going by SKILL.md and its folder, Frontend Design Review needs the command-line tools its instructions call (npx and git). Our summary lists: Node.js.
SKILL.md contains no URLs. Its commands use npx and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Frontend Design Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.5k tokens (SKILL.md is roughly 22k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Frontend Design Review: Reimagine It Audit (Kayforkind/reimagine-it, 205 stars), Design Review (tsubotax/melta-ui, 201 stars), Canva Design Feedback (canva-sdks/canva-skills, 119 stars) and Design Critique (paperclipai/paperclip, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
JasonColapietro (a GitHub user) maintains it in JasonColapietro/suede-creator-skills, which has 127 GitHub stars. The repository holds 78 skills in this directory. The repository was last updated on October 10, 2026.
Source: JasonColapietro/suede-creator-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.