Visual Style
calesthio/OpenMontage
Create, extract, and apply portable visual design systems via visual-style.md files.
Get honest design feedback. An agent skill from LeoYeAI/openclaw-master-skills.
$ npx skills add LeoYeAI/openclaw-master-skills --skill designers-eye -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills designers-eye --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/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/design-critique .claude/skills/designers-eye && 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 "designers-eye" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/design-critique into .claude/skills/designers-eye/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "designers-eye", 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/LeoYeAI/openclaw-master-skills/tree/main/skills/design-critiqueType 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 LeoYeAI/openclaw-master-skills --skill designers-eye -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills designers-eye --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/design-critique .agents/skills/designers-eye && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "designers-eye" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/design-critique into .agents/skills/designers-eye/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "designers-eye", 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 LeoYeAI/openclaw-master-skills --skill designers-eye -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills designers-eye --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/design-critique .cursor/skills/designers-eye && 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 "designers-eye" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/design-critique into .cursor/skills/designers-eye/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "designers-eye", 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/LeoYeAI/openclaw-master-skills.git --path skills/design-critique--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 LeoYeAI/openclaw-master-skills --skill designers-eye -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills designers-eye --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/design-critique .gemini/skills/designers-eye && 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 "designers-eye" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/design-critique into .gemini/skills/designers-eye/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "designers-eye", 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 LeoYeAI/openclaw-master-skills designers-eyeInstalls 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 LeoYeAI/openclaw-master-skills --skill designers-eye -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/design-critique .github/skills/designers-eye && 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 "designers-eye" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/design-critique into .github/skills/designers-eye/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "designers-eye", 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 LeoYeAI/openclaw-master-skills --skill designers-eye -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills designers-eye --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/design-critique .opencode/skills/designers-eye && 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 "designers-eye" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/design-critique into .opencode/skills/designers-eye/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "designers-eye", 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.
designers-eyeGet honest design feedback. An agent skill from LeoYeAI/openclaw-master-skills.
Designers Eye is an agent skill from LeoYeAI/openclaw-master-skills. Get honest design feedback. Upload any visual — UI design, logos, photos, graphics, PDFs — and get prioritized critique: what's broken, what works, what to polish. Theory-backed analysis using 11 frameworks.
Its SKILL.md is about 5.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `_meta.json`, `references/colour-theory.md` and `references/gestalt.md`).
It sits in Frontend & Design, covering Design review and critique, UI design and Logo and visual identity. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
12 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. 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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
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.
Designers Eye loads about 5.6k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 55 tokens; SKILL.md has 2,761 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 LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 2,761 words, ~5,597 tokens.
.claude/skills/designers-eye/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.A critical eye for design. Share a screenshot, image, or website URL and get honest, theory-backed feedback prioritized by impact.
Input: Any visual file — UI design (app & web), logos, photos, graphics, PDFs (as images), anything visual. Share directly in chat.
Analysis: Examined through 11 rigorous frameworks covering visual fundamentals, information hierarchy, usability, and platform expectations.
Output: Priority-ordered action list (critical → important → polish) with specific fixes linked to violated principles.
Share any image. That's it. UI design, logos, graphics, photos, PDFs exported as images, Figma frames — anything you can see gets the same treatment: theory-backed critique ranked by severity and actionability.
Every critique examines 11 dimensions:
1. Gestalt Principles — How elements group and relate (proximity, similarity, continuity, closure, figure/ground, common fate, prägnanz, uniform connectedness).
2. Visual Hierarchy — What's the focal point? Are reading paths clear? Do size, weight, colour, position, and whitespace align?
3. Colour Science (Itten) — Colour contrast types (hue, saturation, value, temperature, simultaneous). Harmony systems (complementary, triadic, analogous). Emotional temperature. Colour interaction and optical mixing. WCAG contrast (4.5:1 text, 3:1 UI). Colourblind accessibility.
4. Typography — Type scale coherence. Font pairings. Readability (16px+ body). Line length (45–75 chars). Line height (1.5+). Weight and style choices. Hierarchy through type.
5. Grid Structure & Alignment (Müller-Brockmann) — Underlying grid present? Alignment consistency. Modulation (repetition with variation). Spacing relationships and rhythm. Margins and gutters logical.
6. Composition & Moment (Freeman) — Viewpoint and perspective. Framing (what's included/excluded). Depth relationships (foreground, middle, background). Focus and blur (selective attention). Scale and proportion. Moment/timing (if applicable).
7. Information Design (Tufte) — Data-ink ratio (signal vs noise). Information density. Layering and progressive disclosure. Clarity of intent. Reducing cognitive load.
8. Reduction & Honesty (Rams/Bauhaus) — Nothing superfluous. Form follows function. Reduction to essentials. Timelessness and coherence. Honest representation.
9. Visual Balance & Weight — Symmetrical vs asymmetrical balance. Visual weight of elements. Tension and composition stability.
10. Usability Heuristics (Nielsen/Norman) — System visibility and status. Match between system and real world. User control and freedom. Consistency and standards. Error prevention and recovery. Recognition vs recall. Flexibility and efficiency. Aesthetic and minimalist design. Error messages. Help and documentation.
11. Platform Conventions — Web, mobile, social, print, email norms. Safe zones. Thumb-friendliness. Expected patterns.
The 10 usability heuristics (also called Nielsen's Heuristics) are industry-standard principles for evaluating interactive design. Every critique checks these:
Why this matters: These heuristics have guided UX design for 30+ years. They're universal across platforms and contexts. A design that violates one of them typically creates friction or confusion for users.
Findings are grouped by severity. Fix critical issues first.
Hard rule: Every finding — regardless of severity level — must include a Fix: line. A critique without a fix is incomplete. Never omit it.
Issues that break usability, accessibility, or core functionality. Fix immediately.
Example:
🔴 Critical — Text contrast fails WCAG AA
The white text on your light blue background achieves 3.2:1 contrast (need 4.5:1 for AA).
This violates: Accessibility / WCAG contrast requirement
Fix: Darken the blue to #0052CC or lighten the text to #F5F5F5. Verify contrast with a checker.Issues that hurt the experience or violate design principles without breaking core function. Fix soon.
Example:
🟡 Important — Hierarchy collapse in the heading area
Your H1 (28px) and H2 (24px) sizes violate the type scale ratio (need ~1.25× gap = 35px vs 28px).
This violates: Visual hierarchy / Type scale consistency
Fix: Increase H1 to 35px or decrease H2 to 22px to create a clear scale.Issues that elevate the design or address missed opportunities. Fix when time allows.
Example:
🟢 Polish — Spacing rhythm could be tightened
Your card padding is 20px but section margins are 40px, creating an inconsistent rhythm.
This violates: Gestalt proximity / Visual rhythm consistency
Fix: Use an 8px or 16px grid consistently. Stick to multiples: 8px, 16px, 24px, 32px, 40px, 48px.Elements close together are perceived as a group.
What to look for:
Common violations:
Fix pattern: Tighten spacing within groups; increase spacing between groups. Internal gap should be ≤50% of external gap.
Elements that look alike are perceived as related.
What to look for:
Common violations:
Fix pattern: Every visual difference should carry semantic weight.
The eye follows paths, lines, and curves.
What to look for:
Common violations:
Fix pattern: Establish strong alignment axes. Every element should anchor to an alignment line.
The mind completes incomplete shapes.
What to look for:
Common violations:
Fix pattern: Use enough visual cues to create the implied shape. If closure requires the user to work hard, add explicit containment.
Elements are perceived as either the subject (figure) or the background (ground).
What to look for:
Common violations:
Fix pattern: The figure must always win. Add overlay, reduce contrast, or simplify the ground.
Elements moving or pointing in the same direction are perceived as related.
What to look for:
Common violations:
Fix pattern: Movement and directionality must reinforce the mental model.
The eye prefers the simplest interpretation.
What to look for:
Fix pattern: Ask: what is the simplest visual form that communicates this? Default to that.
Elements with visible connections are perceived as related.
What to look for:
Fix pattern: When proximity alone isn't enough, add an explicit connector — border, line, shared container, or colour fill.
Every design should have exactly one primary focal point per view. The eye must have a clear entry point, a defined reading path, and a clear exit/CTA.
Size is the strongest hierarchy signal. The eye reads large before small.
Key ratios:
Fix pattern: Establish a type scale with meaningful jumps (modular scale: 1.25, 1.333, 1.5 ratio).
Fix pattern: Only one hue should "shout" at a time.
Isolation signals importance. The most isolated element draws the most attention.
| Failure | Effect | Fix |
|---|---|---|
| Everything the same size | No entry point | Establish a clear size scale with 3+ levels |
| 3+ elements at Level 1 | User paralysis | Reduce to one primary focal point per view |
| CTA buried in content | Low conversion | Isolate CTA with whitespace, size, and colour |
| No whitespace between levels | Levels blur | Add spacing to enforce visual separation |
| Text Type | AA (minimum) | AAA (enhanced) |
|---|---|---|
| Normal text (< 18pt / < 14pt bold) | 4.5:1 | 7:1 |
| Large text (≥ 18pt / ≥ 14pt bold) | 3:1 | 4.5:1 |
| UI components & graphic elements | 3:1 | — |
| Placeholder text | 4.5:1 | — |
| Disabled elements | Exempt | — |
Quick benchmarks:
| Temperature | Colours | Effect |
|---|---|---|
| Warm | Red, orange, yellow | Energy, urgency, warmth |
| Cool | Blue, green, purple | Calm, trust, professionalism |
| Neutral | Grey, black, white | Structure, stability |
Semantic colour conventions:
Use a mathematical ratio, not random sizes.
Common ratios:
Example scale (1.25 ratio, base 16px):
Body: 16px → H6: 20px → H5: 25px → H4: 31px → H3: 39px → H2: 49px → H1: 61pxStick to 2 fonts maximum. 3+ different faces = chaotic.
| Failure | Fix |
|---|---|
| Body text < 14px | Use 16px minimum |
| No type scale | Define a modular scale |
| Line height too tight | Use 1.5–1.6 for body |
| Line length > 100 chars | Cap at 75 characters |
| 3+ font families | Limit to 2 max |
| All-caps body copy | Use sentence case |
Users should always know what's happening. Show state. Every action needs visible feedback.
Violations: No loading indicator, silent form submission, no current-page indicator.
Speak the user's language. Use familiar words and real-world metaphors.
Violations: Technical jargon in labels, unlabelled icon-only buttons, insider acronyms in public copy.
Always provide undo, cancel, and escape routes.
Violations: Destructive actions without confirmation, modals with no close button, no way to reset a form.
Users learn from one part of the system and expect it everywhere.
Violations: Primary actions in different colours across pages, inconsistent button placement, terminology shifts (search vs. find, delete vs. remove).
Design to prevent errors before they happen.
Violations: Required fields with no indication, no inline validation, tiny touch targets, no confirmation before navigating away from unsaved work.
When errors happen, recovery should be simple. Error messages should be plain language with a specific problem and clear fix.
Violations: "Invalid input" without saying which field, error shown at top of form while problem field is at bottom, red text on red background.
Design for both novices and experts. Shortcuts shouldn't hide core paths.
Violations: No keyboard shortcuts, forced multi-step processes that could be single-click, frequently-used settings buried in sub-menus.
Every element should serve a purpose. Remove clutter.
Violations: Distracting animations, excessive borders/dividers, decorative icons that convey no information, backgrounds that reduce text legibility.
Help should be in context, task-focused, and specific.
Violations: No help text for complex interactions, "Learn more" links leading to marketing pages, help docs at odds with actual UI behaviour.
Make actions and options visible. Minimize memory load.
Violations: Actions hidden in menus, icon-only toolbars with no labels, multi-step form with no current step indicator.
Interactive elements should look interactive.
outline: none)© LeoYeAI, 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 7 other files (references) in skills/design-critique of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Designers Eye 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 |
|---|---|---|---|---|---|---|
| Designers Eye this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.6k | Automated safety check: Pass | MIT | |
| Visual Stylecalesthio/OpenMontage | 66k | — | ~1.5k | Automated safety check: Pass | AGPL-3.0 | |
| Design Reviewjezweb/claude-skills | 1.1k | — | ~2.1k | Automated safety check: Pass | MIT | |
| Brand Agencyglebis/claude-skills | 391 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Design Auditbencium/bencium-marketplace | 446 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Design Critiquemohitagw15856/pm-claude-skills | 1.4k | — | ~1.5k | Automated safety check: Pass | MIT |
calesthio/OpenMontage
Create, extract, and apply portable visual design systems via visual-style.md files.
jezweb/claude-skills
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour.
glebis/claude-skills
Applies Agency brand colors and typography to artifacts including presentations, SVG graphics, documents, and web interfaces.
bencium/bencium-marketplace
Premium UI/UX design audit and refinement skill. An agent skill from bencium/bencium-marketplace.
mohitagw15856/pm-claude-skills
Give structured, constructive feedback on any design using UX frameworks.
holaboss-ai/holaOS
Pushes an agent past generic defaults when designing dashboards, admin panels, SaaS apps and tools, with attention to structure, type, navigation and how data is shown.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Categories
Get honest design feedback. An agent skill from LeoYeAI/openclaw-master-skills. Designers Eye is an agent skill from LeoYeAI/openclaw-master-skills. Get honest design feedback.
Designers Eye fits situations like: tasks that involve Design review and critique; tasks that involve UI design; tasks that involve Logo and visual identity.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill designers-eye -a claude-code`. Or copy the skill folder (skills/design-critique in LeoYeAI/openclaw-master-skills) into .claude/skills/designers-eye in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill designers-eye -a codex`. Or copy the skill folder (skills/design-critique in LeoYeAI/openclaw-master-skills) into .agents/skills/designers-eye 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 LeoYeAI/openclaw-master-skills --skill designers-eye -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/designers-eye, .gemini/skills/designers-eye, .github/skills/designers-eye and .opencode/skills/designers-eye in your project.
SKILL.md names no scripts, command-line tools or credentials: Designers Eye is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. 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.
Designers Eye is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.6k 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 10k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Designers Eye: Visual Style (calesthio/OpenMontage, 66k stars), Design Review (jezweb/claude-skills, 1.1k stars), Brand Agency (glebis/claude-skills, 391 stars) and Design Audit (bencium/bencium-marketplace, 446 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.