uidetox 0.2.0

Agent harness and CLI to eliminate AI slop from frontend code

UIdetox

An agent harness that eliminates "AI slop" from frontend code.

UIdetox is an amalgamation of pioneering UI engineering works—specifically drawing from desloppify, impeccable, taste-skill, and uncodixfy. It was created as an effective, dedicated agent harness for UI and frontend quality enforcement.

It gives your AI coding agent the instructions to identify, understand, and systematically fix generic AI-generated UI through a repeatable scan→fix loop combining design taste enforcement and anti-pattern detection.

The goal: frontend code that makes someone ask "how was this made?" — not "which AI made this?"

For your agent's consideration...

Paste this prompt into your agent:

SYSTEM INSTRUCTION: ELIMINATE AI SLOP.
Make this UI indistinguishable from hand-crafted, premium design.
Tools required: Python 3.11+, uidetox package.

STEPS:
1. `pip install uidetox`
2. `uidetox update-skill {editor}` (claude/cursor/gemini/codex/windsurf/copilot)
3. `uidetox setup --auto-commit` (Initialize design dials & track fixes)
4. `uidetox exclude <path>` (Skip vendor/dist/build nodes)
5. THE LOOP:
   - `uidetox scan .`
   - `uidetox next` (Batch issues for top file. READ SKILL.MD CONTEXT INJECTED)
   - Fix all issues in the file simultaneously.
   - `uidetox resolve <ID> --note "changed X"` (Resolves and auto-commits)
   - Repeat `uidetox next` until queue is empty.
5. `uidetox rescan` (Runs 18-rule static analyzer for slop).
6. Repeat loop until `uidetox status` Design Score >= 95. DO NOT STOP BEFORE 95.

ORCHESTRATOR MODE (For complex passes):
`uidetox loop --orchestrator` (Spawns 1-5 parallel sub-agents with memory).

MANDATORY RULES:
- Read `SKILL.md` before making design choices.
- Save architectural insights: `uidetox memory note "uses Radix"` 
- Do complete rewrites if needed. No lazy placeholders.
- Use slash commands (`uidetox polish src/Header.tsx`, `uidetox audit src/`) for targeted iterations.

From Vibe Coding to Vibe Design

Vibe coding gets things built fast. But the interfaces it produces have a smell — Inter font, purple-blue gradients, glassmorphism cards, bounce animations, hero metric dashboards. These patterns emerge because LLMs follow the path of least resistance through their training data. The result is an interface that works, but screams "AI made this" to anyone who's seen enough of them.

The core bet here is that an LLM with the right constraints can hold a frontend to a standard that used to require a senior designer paying close attention. Not by generating more of the same, but by knowing what not to do — and having a systematic loop to enforce it.

UIdetox defines what "designed" looks like as a Design Score worth optimizing. Not a lint score you game by suppressing warnings. Something where improving the number means the interface genuinely got better — better typography, better color, better states, better motion. The anti-slop rules are the difference between a useful signal and a vanity metric.

The hope is that anyone can use AI to build something a seasoned designer would look at and respect. That's the bar.

Installation

pip install uidetox

Then install the skill for your agent — this copies all design rules, reference files, and slash commands to the correct location automatically:

uidetox update-skill claude     # → .claude/skills/uidetox/
uidetox update-skill cursor     # → project root + .cursor/rules/uidetox.mdc
uidetox update-skill gemini     # → project root + GEMINI.md reference
uidetox update-skill codex      # → ~/.codex/skills/uidetox/
uidetox update-skill windsurf   # → project root + .windsurfrules
uidetox update-skill copilot    # → project root (SKILL.md + AGENTS.md)

Initialize and start scanning:

uidetox setup --auto-commit
uidetox scan .

Commands

CLI Commands (the loop engine)

Command	Purpose
uidetox scan	Full audit: auto-detect tooling → static analyzer → design review
uidetox check	Run tsc → lint → format in sequence, queue errors as T1 (--fix to auto-solve)
uidetox next	Batch issues for the top-priority file with SKILL.md context injection
uidetox resolve <id> --note "..."	Mark an issue as fixed (note is mandatory)
uidetox loop	Enter autonomous fix loop until target score is reached
uidetox loop --orchestrator	Sub-agent mode with auto-parallel (1-5 agents) and memory injection
uidetox status	Health dashboard with Design Score (--json for automation payload)
uidetox plan	Reorder the issue queue by priority
uidetox autofix	Batch-apply all safe T1 quick fixes (--dry-run to preview only)
uidetox memory	Read/write persistent agent memory (patterns, notes)
uidetox tree	Terminal tree of issue density
uidetox viz	HTML heatmap of the codebase
uidetox history	Score progression across runs (--full for details)
uidetox zone	Show/set/clear file zone classifications
uidetox suppress	Permanently silence false positive patterns
uidetox subagent	Manage sub-agent sessions and prompts
uidetox detect	Auto-discover linters, formatters, backends, databases, APIs
uidetox rescan	Clear queue, run 18-rule static analyzer, re-audit from scratch

Slash Commands (design skills)

All slash commands are now natively executable from the CLI — no need to read .md files manually:

Command	Purpose
uidetox audit [target]	Technical quality checks (a11y, perf, theming, responsive)
uidetox critique [target]	UX design review (hierarchy, emotion, composition)
uidetox normalize [target]	Align with design system standards
uidetox polish [target]	Final pre-ship quality pass
uidetox distill [target]	Strip to essence, remove complexity
uidetox clarify [target]	Improve unclear UX copy
uidetox optimize [target]	Performance improvements
uidetox harden [target]	Error handling, i18n, edge cases
uidetox animate [target]	Add purposeful motion
uidetox colorize [target]	Introduce strategic color
uidetox bolder [target]	Amplify boring designs
uidetox quieter [target]	Tone down overly bold designs
uidetox delight [target]	Add moments of joy
uidetox extract [target]	Pull into reusable components
uidetox adapt [target]	Adapt for different devices
uidetox onboard [target]	Design onboarding flows

Target can be a file, directory, or component name:

uidetox audit src/components/
uidetox polish src/Header.tsx
uidetox animate src/hero/

Configuration

Three design dials control output aesthetic (default: 8, 6, 4):

Dial	Low (1-3)	Mid (4-7)	High (8-10)
DESIGN_VARIANCE	Clean, centered, standard grids	Overlapping, varied sizes	Asymmetric, masonry, massive whitespace
MOTION_INTENSITY	CSS hover/active only	Fade-ins, smooth transitions	Scroll reveals, spring physics, magnetic effects
VISUAL_DENSITY	Art gallery, spacious	Standard web app	Cockpit mode, dense data

Override by editing SKILL.md or telling your agent directly: "Set DESIGN_VARIANCE to 3."

The AI Slop Test

If you showed this interface to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.

UIdetox trains your agent to avoid the telltale patterns:

• Inter font everywhere
• Purple-blue gradients
• Card grids with identical layouts
• Glassmorphism panels
• Hero metric dashboards
• Bounce animations
• Gray text on colored backgrounds
• Generic startup copy

Credits

This project was created as an effective agent harness for UI/frontend work, serving as an amalgamation of the following pioneering projects:

• desloppify by Pete O'Mallet — The original inspiration for systematic slop removal.
• impeccable by Paul Bakaus — Frontend design skill, 17 robust commands, and deep domain references.
• taste-skill by @lexnlin — Core generative design rules, creative arsenal, motion engine, and output enforcement.
• Uncodixfy — Comprehensive anti-AI-aesthetic pattern catalog and curated color palettes.

License

See individual source repositories for their respective licenses.