#678 by GitHub stars

yetone/kill-ai-slop

Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Detects

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skill/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → f6e2ae32b304

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit f6e2ae32b30443ec7bd0da4da971ee18d8f8ffcb

1.4kGitHub stars
13stars in 7 days
1skill in this repository
0commits in 30 days

Heat

5.3
  • Star growth, last 7 daysAhead of 83% of tracked repositories
  • Star growth, last 24 hoursAhead of 89% of tracked repositories
  • Rank movement, last 7 daysAhead of 30% of tracked repositories
  • Commits, last 30 daysAhead of 0% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 2, 2026Nov 6, 20261,414

Individual skills in this repository

How it works

kill-ai-slop

When your agent uses it

Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Detects and fixes the catalogue of tells: indigo→violet gradients, gradient-clip headlines, the default semantic palette, one-hue status boxes, atmospheric gradients, serif-italic emphasis, highlighted keywords, AI copywriting voice ("not just X — it's Y"), emoji everywhere, glowing status dots, wobbling spinners, colored-left-border callouts, pastel icon tiles, glassmorphism, over-rounding, oversized shadows, borders that die at corners, badge & pill spam, AI-drawn SVG icons, kickers over every heading, flat type hierarchies, invented stat rows, 01/02/03 section markers, cards nested in cards, the default Inter/Space Grotesk look, and more. Works on HTML/CSS, React/Vue/Svelte/Astro, Tailwind, PHP, and Markdown copy.

What it loads into context

Frontmatter

283 tokens

Always available to the agent

SKILL.md

1,415 tokens

When the skill is activated

Reference documents

16,946 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Workflow
  2. Guardrails
  3. References

Scripts executed separately

  • scripts/rules.ru.mjs
  • scripts/scan.mjs
  • scripts/scan.test.mjs

Files

  • README.mddoc5,104 bytes
  • SKILL.mdcore5,674 bytes
  • SKILL.mdcore5,674 bytes
  • references/detection.mddoc20,020 bytes
  • references/fixes.mddoc15,725 bytes
  • references/taxonomy.mddoc20,372 bytes
  • scripts/rules.ru.mjsruns1,198 bytes
  • scripts/scan.mjsruns22,085 bytes
  • scripts/scan.test.mjsruns7,595 bytes
Read SKILL.md

# Kill AI Slop

AI slop is **ugly** in a specific way: it piles on every possible style and
detail without settling on a focus. A gradient, a glow, a mascot, emoji, a wall
of glowing cards, every default switched on at once, until every product looks
like the same garish template. It reads as "designed" in a thumbnail and falls
apart the moment anyone looks. Your job is to strip it back to something a
person would actually choose.

The principles, held on every fix you make:

1. **Decide before you decorate.** Every visual choice must be explainable.
2. **One accent, one voice.**
3. **Hierarchy from scale and space.** Coloring words or swapping fonts is a shortcut.
View the complete source on GitHub

Skills included

  • kill-ai-slop

Repository facts

License
Apache-2.0
Created
Jul 10, 2026
Last pushed
Sep 15, 2026
Forks
64
Open issues
1
Project activity
Active

Rank over the last 12 weeks

Now #678 · best #538 · down 104 in 30 days

  1. #669 on Oct 31
  2. #673 on Nov 1
  3. #674 on Nov 2
  4. #677 on Nov 3
  5. #676 from Nov 4 to Nov 5
  6. #678 since Nov 6
79 earlier periods
  1. #601 on Aug 2
  2. #585 on Aug 7
  3. #578 from Aug 8 to Aug 9
  4. #604 on Aug 10
  5. #599 on Aug 11
  6. #586 on Aug 12
  7. #591 on Aug 13
  8. #580 on Aug 14
  9. #558 on Aug 15
  10. #567 on Aug 16
  11. #564 on Aug 17
  12. #581 on Aug 18
  13. #567 on Aug 19
  14. #566 on Aug 20
  15. #571 on Aug 21
  16. #550 on Aug 22
  17. #570 on Aug 23
  18. #573 on Aug 24
  19. #587 on Aug 25
  20. #580 on Aug 27
  21. #587 on Aug 28
  22. #553 on Aug 29
  23. #546 on Aug 30
  24. #572 on Aug 31
  25. #579 on Sep 1
  26. #571 on Sep 2
  27. #553 on Sep 4
  28. #550 on Sep 5
  29. #561 on Sep 6
  30. #568 on Sep 7
  31. #581 on Sep 8
  32. #568 on Sep 9
  33. #569 on Sep 10
  34. #560 on Sep 11
  35. #556 on Sep 12
  36. #557 on Sep 13
  37. #576 on Sep 14
  38. #566 on Sep 15
  39. #578 on Sep 16
  40. #576 on Sep 17
  41. #578 on Sep 18
  42. #553 on Sep 19
  43. #563 on Sep 20
  44. #568 on Sep 21
  45. #573 on Sep 22
  46. #560 on Sep 23
  47. #545 on Sep 24
  48. #538 on Sep 25
  49. #542 on Sep 26
  50. #559 on Sep 27
  51. #562 on Sep 28
  52. #580 on Sep 29
  53. #569 on Sep 30
  54. #555 on Oct 1
  55. #562 on Oct 2
  56. #544 on Oct 3
  57. #547 on Oct 4
  58. #556 on Oct 5
  59. #569 on Oct 6
  60. #574 on Oct 7
  61. #589 on Oct 9
  62. #572 on Oct 10
  63. #569 on Oct 11
  64. #579 from Oct 12 to Oct 13
  65. #591 on Oct 14
  66. #584 on Oct 15
  67. #590 on Oct 16
  68. #581 on Oct 17
  69. #577 on Oct 18
  70. #596 on Oct 19
  71. #608 on Oct 20
  72. #613 on Oct 21
  73. #601 on Oct 22
  74. #594 on Oct 23
  75. #584 on Oct 24
  76. #653 on Oct 25
  77. #661 on Oct 28
  78. #666 on Oct 29
  79. #667 on Oct 30

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 3, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 1 note
  • skill/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 10 signals by file

skill/README.md

  • Network accessline 3
    Scan a web project for **AI slop**, the generic machine-default visual and copy tics of vibe-coded products, and strip it out. This skill turns the catalogue at **[killaislop.com](https://killaislop.com)** into action: it detects 35 tells
  • Network accessline 4
    tics of vibe-coded products, and strip it out. This skill turns the catalogue at **[killaislop.com](https://killaislop.com)** into action: it detects 35 tells from their code-level signals, explains why each reads as machine-made, and
  • Network accessline 5
    **[killaislop.com](https://killaislop.com)** into action: it detects 35 tells
  • Network accessline 27
    This is an [Agent Skill](https://docs.claude.com/en/docs/agents-and-tools/agent-skills/overview). You don't need to configure anything by hand. Tell your coding agent, in plain language, to fetch it from this repo and install it wherever th
  • Network accessline 33
    Install the kill-ai-slop skill from https://github.com/yetone/kill-ai-slop/tree/main/skill
  • Network accessline 34
    https://github.com/yetone/kill-ai-slop/tree/main/skill
  • Network accessline 53
    git clone https://github.com/yetone/kill-ai-slop

skill/scripts/rules.ru.mjs

  • Executable scriptline 1
    Executable file

skill/scripts/scan.mjs

  • Executable scriptline 1
    #!/usr/bin/env node

skill/scripts/scan.test.mjs

  • Executable scriptline 1
    Executable file

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

No combined signals at this commit.

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md skill/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skill/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skill/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skill/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skill/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skill/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

yetone/kill-ai-slop: #678 on hotskills, 1.4k stars

[![yetone/kill-ai-slop on hotskills](https://hotskills.dev/badge/yetone-kill-ai-slop.svg)](https://hotskills.dev/skill/yetone-kill-ai-slop/)