Skip to content
Back to search

anti-ai-slop-design

MarketplaceWorks with Claude CodeGitHub

Claude skill: workflow and prompting rules for non-generic UI, slide, and motion design

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/panyuti-ai--anti-ai-slop-design/badge.svg)](/listings/panyuti-ai--anti-ai-slop-design)

HTML

<a href="/listings/panyuti-ai--anti-ai-slop-design"><img src="/api/listings/panyuti-ai--anti-ai-slop-design/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Option 1: Clone and use

git clone https://github.com/panyuti-ai/anti-ai-slop-design.git
cd anti-ai-slop-design
claude

Inside that folder, run `/anti-ai-slop-design`. The skill lives in `.claude/skills/`, so it loads automatically for this folder only.

Option 2: Install as a plugin (any project)

/plugin marketplace add panyuti-ai/anti-ai-slop-design
/plugin install anti-ai-slop-design --marketplace panyuti-ai/anti-ai-slop-design

Plugin skills are namespaced, so it appears as `/anti-ai-slop-design:anti-ai-slop-design`.

Option 3: Manual copy

Copy `.claude/skills/anti-ai-slop-design/SKILL.md` into `~/.claude/skills/anti-ai-slop-design/SKILL.md` to use it in every project without a plugin.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 11 lines
  1. {
  2. "name": "anti-ai-slop-design",
  3. "owner": { "name": "panyuti-ai" },
  4. "plugins": [
  5. {
  6. "name": "anti-ai-slop-design",
  7. "source": "./",
  8. "description": "Workflow and prompting rules for getting non-generic UI, slide, and motion design out of Claude."
  9. }
  10. ]
  11. }
README.md · README · 216 lines
  1. <div align="center">
  2. # anti-ai-slop-design
  3. **Get distinctive UI, slide, and motion design out of Claude, not the same serif-and-orange look every time.**
  4. ![Type](https://img.shields.io/badge/type-Claude%20skill-black)
  5. ![License](https://img.shields.io/badge/license-MIT-black)
  6. ![Scope](https://img.shields.io/badge/scope-UI%20%C2%B7%20slides%20%C2%B7%20motion-black)
  7. [Install](#install) · [The method](#the-method) · [Prompts to copy](#prompts-to-copy) · [Checklist](#checklist) · [Source](#source-and-attribution)
  8. </div>
  9. ---
  10. ## The idea in one line
  11. > What you put in is what you get out. Give context, ask for breadth, then converge.
  12. Claude's default design tends to repeat itself: serif text, light gray background, orange accent, cards with a colored edge stripe. This skill is a working method for steering around that.
  13. ## Install
  14. ### Option 1: Clone and use
  15. ```bash
  16. git clone https://github.com/panyuti-ai/anti-ai-slop-design.git
  17. cd anti-ai-slop-design
  18. claude
  19. ```
  20. Inside that folder, run `/anti-ai-slop-design`. The skill lives in `.claude/skills/`, so it loads automatically for this folder only.
  21. ### Option 2: Install as a plugin (any project)
  22. ```text
  23. /plugin marketplace add panyuti-ai/anti-ai-slop-design
  24. /plugin install anti-ai-slop-design --marketplace panyuti-ai/anti-ai-slop-design
  25. ```
  26. Plugin skills are namespaced, so it appears as `/anti-ai-slop-design:anti-ai-slop-design`.
  27. ### Option 3: Manual copy
  28. Copy `.claude/skills/anti-ai-slop-design/SKILL.md` into `~/.claude/skills/anti-ai-slop-design/SKILL.md` to use it in every project without a plugin.
  29. ## The method
  30. Open each section to read the full rule. The same content lives in [`SKILL.md`](.claude/skills/anti-ai-slop-design/SKILL.md), which is what Claude loads.
  31. <details open>
  32. <summary><b>1. Start from context, not a blank request</b></summary>
  33. - Collect inputs before generating: screenshots as a mood board, pages that feel right, past work you like, and a short statement of what the thing is and how it should feel.
  34. - If a codebase exists, read it first (see step 4).
  35. </details>
  36. <details>
  37. <summary><b>2. Diverge, then converge</b></summary>
  38. 1. Ask for about 10 options that differ in fonts, colors, and visual style.
  39. 2. Pick pieces: "I like part of #1 and part of #3. Make 5 more that are different but built on those."
  40. 3. Repeat until one direction is clear.
  41. 4. Keep every version side by side on the canvas. Copy a version before changing it instead of overwriting.
  42. </details>
  43. <details>
  44. <summary><b>3. Wireframe first when the task is hard</b></summary>
  45. - Ask for several wireframes with different layouts before any font or color decision.
  46. - Ask Claude to name similar existing products, compare their layouts, and pick the one users already know how to use.
  47. </details>
  48. <details>
  49. <summary><b>4. Existing product: recreate from code</b></summary>
  50. - Tell Claude to read the relevant parts of the codebase and recreate the current state on the canvas, then produce variations from there.
  51. - Do not maintain long-lived design files. Recreate from current code each time.
  52. - To build, continue in the same session so styles, sizes, fonts, and colors carry over without translation loss.
  53. </details>
  54. <details>
  55. <summary><b>5. Decide style before producing a full deck</b></summary>
  56. For presentations, agree on the visual style first. Redoing a whole deck in the wrong style wastes tokens.
  57. </details>
  58. <details>
  59. <summary><b>6. Block Claude's default look</b></summary>
  60. - Name Claude's habits in the prompt and forbid them unless asked.
  61. - Better: supply the brand or identity yourself (colors, fonts, tone). Brand context is a durable asset that works across models.
  62. - If output feels corporate, say so and push: "Too corporate. Use full creative range. Make it feel like a film, not a slide deck."
  63. </details>
  64. <details>
  65. <summary><b>7. Give feedback efficiently</b></summary>
  66. - High-level direction works ("make the card list denser, no subheadings, no dividers"), as do small specifics ("reduce left padding", "align icons to cells").
  67. - Voice notes are fine for loose thoughts.
  68. - Use comments pinned to an element or a video timestamp instead of describing location in words. Then ask Claude to process all comments.
  69. - Let Claude ask about 8 clarifying questions before designing. Answering is easier than guessing what a designer would ask. Allow skipping.
  70. </details>
  71. <details>
  72. <summary><b>8. Motion and animation</b></summary>
  73. - Claude can track many things at once; people cannot. Require one focal change at a time.
  74. - Leave reading time: when text appears, ask whether people have enough time to read it before the next element, and whether their eyes are where the next action happens.
  75. - If it looks like static slides, ask for continuous movement, such as a single line the eye follows.
  76. - Process: storyboard (static, cheap) → a few visual style options → pick one → iterate → comment-based polish.
  77. </details>
  78. <details>
  79. <summary><b>9. Dashboards</b></summary>
  80. - Give Claude the data source (spreadsheet link, MCP connector) and ask it to "make this a dashboard". Leaving the metrics unspecified can produce useful surprises.
  81. - Connect live data when the source supports it.
  82. - Check numbers against their source: inspect the code Claude used to fetch each figure.
  83. </details>
  84. <details>
  85. <summary><b>10. Evaluate results</b></summary>
  86. - Prefer yes/no checks over 1-5 scores.
  87. - Automate only basics: text overlap, and whether 10 runs all pick the same font and color.
  88. - Taste still needs a human reviewing outputs and transcripts.
  89. - To test a skill that produces videos or designs, run several fresh sessions that see only the skill plus a one-line request, then review the results yourself.
  90. </details>
  91. ## Prompts to copy
  92. <details>
  93. <summary><b>Diverge</b></summary>
  94. ```text
  95. Here is what we're designing and how it should feel: <description>.
  96. Reference screenshots attached. Give me 10 options that differ in fonts,
  97. colors, and visual style.
  98. ```
  99. </details>
  100. <details>
  101. <summary><b>Converge</b></summary>
  102. ```text
  103. None is perfect. I like <part> of #1 and <part> of #3. Make 5 more that
  104. are different from each other but built on those.
  105. ```
  106. </details>
  107. <details>
  108. <summary><b>Recreate from code</b></summary>
  109. ```text
  110. Read the relevant parts of the codebase, recreate the current <screen> on
  111. the canvas, then give me variations. Keep the original next to them.
  112. ```
  113. </details>
  114. <details>
  115. <summary><b>Block the defaults</b></summary>
  116. ```text
  117. You tend to overuse the same two fonts and two colors (serif text, light
  118. gray background, orange accent, card edge stripes). Do not use them unless
  119. I ask or it is clearly right for this design.
  120. ```
  121. </details>
  122. <details>
  123. <summary><b>Motion pacing</b></summary>
  124. ```text
  125. People can only focus on one thing at a time and read slowly. Make one
  126. focal change at a time, and leave enough time for text to be read before
  127. the next element appears.
  128. ```
  129. </details>
  130. ## Checklist
  131. - [ ] Context supplied (mood board, references, codebase)
  132. - [ ] 10 divergent options requested, then a converged round
  133. - [ ] Wireframes first if the layout is the hard part
  134. - [ ] Default fonts and colors explicitly excluded, or brand supplied
  135. - [ ] Versions kept side by side
  136. - [ ] Motion: one focal change at a time, reading time left
  137. - [ ] Data figures traced to source
  138. - [ ] A human has looked at the output
  139. ## Source and attribution
  140. This is an independent summary of practices discussed in the video "Full Tutorial: How to Fix AI Slop with Claude Design in 40 Minutes" (Peter Yang interviewing Nate Parrott): https://www.youtube.com/watch?v=604T-74s3KE
  141. It contains no transcript text. It is not affiliated with or endorsed by the interviewer, the guest, or Anthropic. Any errors in interpretation are mine.
  142. ## License
  143. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.