Skip to content
Back to search

kill-ai-slop

SkillWorks with Claude CodeGitHub

A field guide to the visual & copy tics of AI-generated products — and an Agent Skill that scans your project and strips them out. https://killaislop.com

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/yetone-kill-ai-slop/badge.svg)](/listings/yetone-kill-ai-slop)

HTML

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

Install

i

Install instructions from the README

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

Install it without touching a single file: paste this to your coding agent (Claude Code, Cursor, etc.) and it fetches the skill and drops it into its own skills directory for you.

Install the kill-ai-slop skill from
https://github.com/yetone/kill-ai-slop/tree/main/skill

Copy everything in that directory into a kill-ai-slop/ folder
inside your agent's skills directory, then confirm it's registered.

Then just tell it to "kill the AI slop in this project". Prefer to install by hand? See `skill/README.md`.

You can also run the scanner directly. Point it at any web project:

node skill/scripts/scan.mjs path/to/project          # grouped report
node skill/scripts/scan.mjs path/to/project --json    # machine-readable

`--only=` / `--skip=` filter by tell id, `--exclude=` drops paths, `--rules=extra.mjs` loads your own language- or stack-specific tells, and `deslop-ignore` comment directives suppress hits you've confirmed as intentional — see `skill/README.md`.

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.

README.md · README · 100 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Kill AI Slop
  2. **[killaislop.com](https://killaislop.com)**
  3. Vibe-coded products are ugly in the same specific way: indigo gradients, glowing
  4. cards, emoji everywhere, a mascot in every corner, ALL-CAPS stat-cards. It's what
  5. a machine reaches for when it has no taste but wants to look impressive, and it's
  6. so common you've stopped seeing it.
  7. **Kill AI Slop** is two things:
  8. 1. **A website**, a multilingual field guide (English, Chinese, Japanese, and
  9. Korean) that catalogues 33 AI-slop tells, each with an interactive
  10. before→after demo showing the clean fix. The site is itself built as a
  11. rebuttal to everything it catalogues.
  12. 2. **An Agent Skill**, `kill-ai-slop`, which turns that catalogue into action:
  13. it scans a web project for the code-level signals of each tell, explains why
  14. each reads as machine-made, and proposes (or applies) the clean fix.
  15. Every tell is one you can find in real, shipped products, not a strawman. Each
  16. entry rebuilds the tell in plain HTML so you can see the machine-default and the
  17. clean fix side by side.
  18. ## Repo layout
  19. ```
  20. website/ Astro site, the field guide (multilingual, static, zero-JS-by-default)
  21. skill/ the kill-ai-slop Agent Skill (SKILL.md + references + scanner)
  22. ```
  23. ## The website
  24. Live at **[killaislop.com](https://killaislop.com)**. To run it locally:
  25. ```bash
  26. cd website
  27. npm install
  28. npm run dev # http://localhost:4321
  29. npm run build # → dist/ (static, deploy anywhere)
  30. ```
  31. Design system: paper + ink, **one** editorial red used like a proofreader's pen,
  32. hierarchy from scale and space, hairline rules, no gradients / emoji / glass /
  33. badges. See `website/src/styles/tokens.css` for the rules it holds itself to,
  34. and `website/src/data/catalogue.ts` for the taxonomy (the single source of truth
  35. shared with the skill).
  36. ## The skill
  37. ### Universal agent installer
  38. Run the following command and follow the prompt to install it to your favorite coding agents:
  39. ```
  40. npx skills add yetone/kill-ai-slop
  41. ```
  42. ### Manual installation
  43. Install it without touching a single file: paste this to your coding agent (Claude
  44. Code, Cursor, etc.) and it fetches the skill and drops it into its own skills
  45. directory for you.
  46. ```
  47. Install the kill-ai-slop skill from
  48. https://github.com/yetone/kill-ai-slop/tree/main/skill
  49. Copy everything in that directory into a kill-ai-slop/ folder
  50. inside your agent's skills directory, then confirm it's registered.
  51. ```
  52. Then just tell it to "kill the AI slop in this project". Prefer to install by hand?
  53. See `skill/README.md`.
  54. You can also run the scanner directly. Point it at any web project:
  55. ```bash
  56. node skill/scripts/scan.mjs path/to/project # grouped report
  57. node skill/scripts/scan.mjs path/to/project --json # machine-readable
  58. ```
  59. `--only=` / `--skip=` filter by tell id, `--exclude=` drops paths,
  60. `--rules=extra.mjs` loads your own language- or stack-specific tells, and
  61. `deslop-ignore` comment directives suppress hits you've confirmed as
  62. intentional — see `skill/README.md`.
  63. ## License
  64. [Apache-2.0](LICENSE).
  65. The scanner is dependency-free and never edits files. In an Agent-Skills host
  66. (e.g. Claude Code), invoke the skill and it will scan, triage, report, then fix,
  67. following `skill/SKILL.md`. See `skill/references/` for the taxonomy, detection
  68. patterns, and remediation playbook, and `skill/README.md` for install steps.
  69. ## Every example is a rebuild
  70. The demos are reconstructed in plain HTML, for commentary, criticism, and
  71. education. The point is not to dunk on any one project. It's to make the ugly
  72. defaults visible again, so you can choose against them.

Ratings and comments

Sign in to rate this skill.

Sign in

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