anti-ai-slop
Detect and remove generic AI-generated UI fingerprints such as templated SaaS structure, fake chrome, invented metrics, and repeated card rhythms.
Skill by SofianeBel
Chalk Labs
Need help deploying anti-ai-slop?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sofianebel-anti-ai-slop
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/anti-ai-slop
What's inside
- Skill name
anti-ai-slop- Description
- Detect and remove generic AI-generated UI fingerprints such as templated SaaS structure, fake chrome, invented metrics, and repeated card rhythms.
- License
- MIT
- Instructions
- 20 lines in SKILL.md · view on GitHub
Files (5)
- SKILL.md
- component-states.md · references/
- hallmark-inspired.md · references/
- slop-gates.md · references/
- structural-fingerprints.md · references/
SKILL.md (first lines)
# Anti-AI-Slop Use this skill when the UI is technically correct but looks generated, templated, or interchangeable with many AI-made pages. ## Workflow 1. Read the current UI and latest `artifacts/reports/visual-report.json`. 2. Check the Hallmark component for severe anti-slop failures first. 3. In `exact_mockup` mode, block slop without changing the mockup's intended structure. 4. In `design_dna` mode, extract visual rhythm and personality without copying pixels. 5. Run `npm run hallmark:audit` or the full `npm run validate:ui` after changes. ## References - `references/hallmark-inspired.md` - `references/structural-fingerprints.md` - `references/slop-gates.md` - `references/component-states.md`
From SofianeBel/codex-frontend-plugin, MIT.
More from SofianeBel/codex-frontend-plugin
- 0.476score
design-quality
SofianeBel
Audit and improve frontend design quality beyond screenshot similarity: typography, spacing, color, layout, responsive behavior, UX copy, and component polish.
SkillCFreshness: CClaude Code +9 - 0.471score
frontend-mockup
SofianeBel
Implement frontend screens from a mockup image and use the local visual-check loop to compare the result against the reference.
SkillCFreshness: CClaude Code +9 - 0.471score
motion-quality
SofianeBel
Audit and improve UI motion so animations are purposeful, subtle, accessible, performant, and not generic AI-generated decoration.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 4, 2026 (4 months ago)
- Last release
- Jun 4, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from SofianeBel
- 0.476score
design-quality
SofianeBel
Audit and improve frontend design quality beyond screenshot similarity: typography, spacing, color, layout, responsive behavior, UX copy, and component polish.
SkillCFreshness: CClaude Code +9 - 0.474score
repo-check
SofianeBel
Use when checking whether a folder is a Git repo, auditing dirty state, finding upstream/ahead/behind status, locating unresolved conflicts, or preparing a…
SkillCFreshness: CClaude Code +9 - 0.474score
git-branch-logic
SofianeBel
Use when naming branches, choosing a base branch, checking protected branches, or planning feature, fix, hotfix, release, or docs Git work.
SkillCFreshness: CClaude Code +9 - 0.474score
git-commit-discipline
SofianeBel
Use when staging files, creating commits, writing commit messages, splitting unrelated work, or checking Conventional Commit format.
SkillCFreshness: CClaude Code +9 - 0.471score
git-push-guardian
SofianeBel
Use before pushing, force pushing, setting upstream, publishing a branch, or deciding whether a branch is ready for remote.
SkillCFreshness: CClaude Code +9 - 0.471score
frontend-mockup
SofianeBel
Implement frontend screens from a mockup image and use the local visual-check loop to compare the result against the reference.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get anti-ai-slop running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
anti-ai-slop skill. Agent Mart. https://agentmart.dev/skills/sofianebel-anti-ai-slop (last updated 2026-10-24)