New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Audit AI Design Slop

by nirholas in nirholas/three.ws

Audit websites, apps, screenshots, mockups, and design code for harmful AI-design clichés, generic generated defaults, and established UI defects.

Apache-2.0Auto-check passedWriting & Content

Install Audit AI Design Slop

skills CLI
$ npx skills add nirholas/three.ws --skill audit-ai-design-slop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nirholas/three.ws audit-ai-design-slop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nirholas/three.ws.git skills-src && mkdir -p .claude/skills && cp -r skills-src/third_party/designcode-agent-skills/agent-skills/ui/audit-ai-design-slop .claude/skills/audit-ai-design-slop && rm -rf skills-src

Use ~/.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/

Facts

Skill name
audit-ai-design-slop
GitHub stars
229
Used in
1 other repo
Token cost
~1.6k tokens
SKILL.md length
713 words
Files
3
Skills in repo
92
Repo updated
First seen
Licence
Apache-2.0

At a glance

Audit websites, apps, screenshots, mockups, and design code for harmful AI-design clichés, generic generated defaults, and established UI defects.

  • Works in 5 steps: State what information, state, action,… → Ask whether removing it would improve… → If yes, recommend removal or… → …
  • The user wants evidence-backed design feedback
  • SKILL.md covers Boundaries, Audit the Evidence, Classify Findings and What to Flag, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Audit AI Design Slop is an agent skill from nirholas/three.ws. Audit websites, apps, screenshots, mockups, and design code for harmful AI-design clichés, generic generated defaults, and established UI defects. Use when the user wants evidence-backed design feedback, an anti-slop review, or a removal-first cleanup plan without a speculative redesign.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `REFERENCES.md` and `agents/openai.yaml`).

It sits in Writing & Content, covering Humanizing AI text and Design review and critique. The repository describes itself as: Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web… The licence is Apache-2.0.

When your agent uses it

  • The user wants evidence-backed design feedback
  • An anti-slop review
  • A removal-first cleanup plan without a speculative redesign

Example prompts

  • “/audit-ai-design-slop”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. State what information, state, action, hierarchy, or brand meaning it provides.
  2. Ask whether removing it would improve clarity without losing that role.
  3. If yes, recommend removal or consolidation.
  4. If no, recommend the smallest correction using the existing system.
  5. Suggest a replacement only when deletion would create a real loss.

What it can do on your machine

Read from SKILL.md and the folder at commit 66624fb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Audit AI Design Slop loads about 1.6k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 713 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from nirholas/three.ws at commit 66624fb, republished under its Apache-2.0 licence (© nirholas). 713 words, ~1,553 tokens.

Download SKILL.mdSave it as .claude/skills/audit-ai-design-slop/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
audit-ai-design-slop
description
Audit websites, apps, screenshots, mockups, and design code for harmful AI-design clichés, generic generated defaults, and established UI defects. Use when the user wants evidence-backed design feedback, an anti-slop review, or a removal-first cleanup plan without a speculative redesign.

Audit AI Design Slop

Run a diagnostic, evidence-backed audit. Identify the smallest set of removals or corrections that would improve the interface while preserving its existing direction.

Boundaries

  • Do not guess whether AI made the design.
  • Do not assign a numeric slop score.
  • Do not reject a visual technique in isolation. A gradient, serif, dark theme, glass effect, card, animation, or single-font system can be intentional.
  • Do not prescribe a new font, palette, layout, design system, or art direction unless the user explicitly asks for one.
  • Do not turn an audit into an implementation task.
  • Mark anything outside the visible or provided evidence as unknown.

Audit the Evidence

Inspect the artifact available in the request:

  • screenshots and recordings
  • rendered pages and relevant viewports
  • interaction and state changes
  • source code, tokens, assets, and copy
  • console or runtime failures when they affect the experience

For every finding, cite a concrete location, component, behavior, or line of copy. Do not report a generic tendency without evidence in the artifact.

For a full-page or full-site review, read ../no-ai-design-slop/ARTICLE.md and use only the catalog sections relevant to the inspected artifact. Do not turn every checklist match into a finding. Group symptoms by root cause and report the highest-impact evidence.

Classify Findings

Use one of these classes:

  • Quality defect: an established usability, accessibility, content, responsive, or runtime problem.
  • Slop pattern: a repeated default, decorative layer, or generated-looking convention with no useful role.

What to Flag

Decorative stacking

Flag combinations of glow, gradient text, glass, borders, shadows, grids, particles, beams, noise, floating shapes, or browser chrome when multiple layers perform the same decorative job or compete with the content.

Component and template repetition

Flag:

  • card treatment applied to nearly every content block
  • repeated icon-heading-description tiles with interchangeable content
  • nested rounded containers that do not communicate hierarchy
  • generic landing-page sequences unrelated to the product's buying or usage journey
  • headings, labels, pills, or CTA blocks that restate nearby information
Typography and copy clutter

Flag:

  • duplicate text or unnecessary labels
  • empty superlatives, vague category claims, and generated filler
  • decorative type treatments that obscure hierarchy or readability
  • long centered paragraphs, awkward forced line breaks, or hard-to-scan text
  • inconsistent type roles that look accidental rather than expressive
Motion theater

Flag motion that delays access, repeats mechanically, distracts from reading, moves targets, blocks input, or lacks respect for reduced-motion preferences. Preserve motion that communicates state, causality, hierarchy, or spatial change.

Fake proof

Flag invented or unverifiable metrics, customers, testimonials, awards, ratings, activity, dashboards, charts, logos, and portraits when they are presented as evidence.

Show full SKILL.md (293 more words)Show less
Established UI failures

Flag:

  • unclear or competing primary actions
  • low contrast or unreadable content
  • clipping, overflow, overlap, or broken responsive behavior
  • broken assets, links, scripts, or controls
  • essential information available only on hover
  • missing states required by the observed flow
  • unclear labels, roles, feedback, or keyboard focus
  • accidental inconsistency in spacing, type, color, radius, or icons
  • visual hierarchy that contradicts task importance

Use the Removal Test

For every candidate:

  1. State what information, state, action, hierarchy, or brand meaning it provides.
  2. Ask whether removing it would improve clarity without losing that role.
  3. If yes, recommend removal or consolidation.
  4. If no, recommend the smallest correction using the existing system.
  5. Suggest a replacement only when deletion would create a real loss.

Default to subtraction. A replacement should inherit the product's existing language rather than introduce a new visual concept.

Prioritize

  • P0: blocks completion, creates a severe accessibility issue, or presents deceptive proof
  • P1: materially harms comprehension, trust, navigation, or interaction
  • P2: repeated slop or inconsistency that weakens hierarchy and identity
  • P3: minor polish issue with limited user impact

Return the five to eight highest-impact findings by default. Group repeated instances into one systemic finding.

Output

md
## Verdict
One concise paragraph about the dominant problems and what should be removed first.

## Checked scope
- Artifact, screen, state, and viewport actually inspected

## Findings
| Priority | Class | Pattern | Evidence | Harm | Remove or fix |
|---|---|---|---|---|---|
| P1 | Slop pattern | Repeated ornamental containers | Feature area uses the same layered card treatment for unrelated content | Flattens hierarchy and adds noise | Remove outer shells; retain grouping only where it communicates interaction |

## Unknowns
- Important states or behavior that could not be verified

Keep the report compact. Omit empty sections.

Feedback Rules

  • Lead with concrete evidence, not taste claims.
  • Name the pattern and its harm.
  • Recommend removal before restyling.
  • Avoid generic compliments and exhaustive low-impact nitpicks.
  • Preserve useful product-specific detail and intentional character.
  • Do not cite a standard unless it directly supports the finding.
  • Do not describe an aesthetic as universally bad.
  • If the user explicitly asks for design swaps, place an optional replacement after the removal recommendation and keep it consistent with the existing system.
  • End with the single removal or correction that would produce the largest improvement.

© nirholas, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in third_party/designcode-agent-skills/agent-skills/ui/audit-ai-design-slop of nirholas/three.ws.

  • SKILL.md
  • REFERENCES.md
  • agents/openai.yaml

Open the folder on GitHubat commit 66624fb

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in nirholas/three.ws, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Audit AI Design Slop 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.

Audit AI Design Slop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit AI Design Slop this skillnirholas/three.ws2291 repos~1.6kAutomated safety check: PassApache-2.0
HumanizerAzure-Samples/interview-coach-agent-framework17338 repos~5.8kAutomated safety check: PassMIT
Avoid AI Writingconorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMIT
User-Facing Text Cleanupguillaumemeyer/watermarks-remover24k—~3.5kAutomated safety check: PassMIT
Install Anti Sloptrycompai/crm11k1 repos~881Automated safety check: PassMIT
Stop SlopXe/site7328 repos~423Automated safety check: PassMIT

Similar skills

  • Humanizer

    Azure-Samples/interview-coach-agent-framework

    Official

    Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.

    173 GitHub starsUsed in 38 repos~5.8k tokens
    Writing & ContentAuto-check passed

  • Avoid AI Writing

    conorbronsdon/avoid-ai-writing

    Audit and rewrite content to remove AI writing patterns ("AI-isms").

    4.9k GitHub starsUsed in 3 repos~8.1k tokens
    Writing & ContentAuto-check passed

  • User-Facing Text Cleanup

    guillaumemeyer/watermarks-remover

    Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.

    24k GitHub stars~3.5k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed

  • Install Anti Slop

    trycompai/crm

    Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.

    11k GitHub starsUsed in 1 repo~881 tokens
    Writing & ContentAuto-check passed

  • Stop Slop

    Xe/site

    Remove AI writing patterns from prose. An agent skill from Xe/site.

    732 GitHub starsUsed in 8 repos~423 tokens
    Writing & ContentAuto-check passed

  • Chinese Text Humanizer

    op7418/Humanizer-zh

    Edits Chinese articles, comments and documents to remove filler, repetition and template phrasing while keeping the facts, the level of certainty and the author's voice.

    19k GitHub stars~2k tokensUpdated 17 days ago
    Writing & ContentAuto-check passed

More from nirholas/three.ws

All 92 skills in this repo

  • Add Shader Cursor Trail

    nirholas/three.ws

    Add the Shaders WebGPU mouse effect used for the Tidal Commons hero: a white twinkling halftone cursor trail driven by ChromaFlow, masked through a DotGrid, finished with chromatic ripples and film…

    229 GitHub starsUsed in 1 repo~760 tokens
    Auto-check passed

  • Publish Project To GitHub

    nirholas/three.ws

    Package a finished local project into an intentional GitHub repository, create a strong README and visual preview, push it safely, configure a public GitHub Pages URL when the project is compatible…

    229 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check: notes

  • Audit Reference Originality

    nirholas/three.ws

    Audit a website or digital experience against its supplied source references for originality and plagiarism risk.

    229 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

  • Build Daily Inspiration Sites

    nirholas/three.ws

    Turn a completed daily UI inspiration capture into exactly five original landing-page builds, one per separate Codex task, using Sites.

    229 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed

  • Write Like Meng On X

    nirholas/three.ws

    Write, rewrite, review, or continuously refine X/Twitter posts in Meng To's current voice using his deduplicated authored-post corpus, personal and product context, shared resources, and Content…

    229 GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed

  • Browser Video Recording

    nirholas/three.ws

    Create polished 60 fps 4:3 4K browser screen-recording style videos from Codex in-app browser captures, with browser-only crop, natural macOS cursor styling, deliberate click choreography…

    229 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed

Categories

Questions about Audit AI Design Slop

What does Audit AI Design Slop do?

Audit websites, apps, screenshots, mockups, and design code for harmful AI-design clichés, generic generated defaults, and established UI defects. ws. Audit websites, apps, screenshots, mockups, and design code for harmful AI-design clichés, generic generated defaults, and established UI defects.

When should I use Audit AI Design Slop?

Audit AI Design Slop fits situations like: the user wants evidence-backed design feedback; an anti-slop review; A removal-first cleanup plan without a speculative redesign.

How do I install Audit AI Design Slop in Claude Code?

Run `npx skills add nirholas/three.ws --skill audit-ai-design-slop -a claude-code`. Or copy the skill folder (third_party/designcode-agent-skills/agent-skills/ui/audit-ai-design-slop in nirholas/three.ws) into .claude/skills/audit-ai-design-slop in your project. Claude Code loads it when a task matches its description.

How do I install Audit AI Design Slop in Codex?

Run `npx skills add nirholas/three.ws --skill audit-ai-design-slop -a codex`. Or copy the skill folder (third_party/designcode-agent-skills/agent-skills/ui/audit-ai-design-slop in nirholas/three.ws) into .agents/skills/audit-ai-design-slop in your project. Codex loads it when a task matches its description.

Can I use Audit AI Design Slop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nirholas/three.ws --skill audit-ai-design-slop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-ai-design-slop, .gemini/skills/audit-ai-design-slop, .github/skills/audit-ai-design-slop and .opencode/skills/audit-ai-design-slop in your project.

What does Audit AI Design Slop need to run?

SKILL.md names no scripts, command-line tools or credentials: Audit AI Design Slop is instructions for the agent only.

Does Audit AI Design Slop access the network?

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.

Is Audit AI Design Slop safe to install?

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.

What licence does Audit AI Design Slop use?

Audit AI Design Slop is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audit AI Design Slop use?

About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Audit AI Design Slop?

Skills that share tags, products or a category with Audit AI Design Slop: Humanizer (Azure-Samples/interview-coach-agent-framework, 173 stars), Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars), User-Facing Text Cleanup (guillaumemeyer/watermarks-remover, 24k stars) and Install Anti Slop (trycompai/crm, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit AI Design Slop?

nirholas (a GitHub user) maintains it in nirholas/three.ws, which has 229 GitHub stars. The repository holds 92 skills in this directory. The repository was last updated on October 10, 2026.

Source: nirholas/three.ws on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.