perfect-ux

perfect-ux is a skill for Codex from Eid0lon/zero-slop. It costs 108 tokens per session (1,754 once invoked), scanned A, original, Apache-2.0.

A user-experience review guide for digital products. It examines whether people can understand the interface, complete important tasks, handle errors, and use it accessibly.

In plain words
What is it for?
Use it to define and map user tasks, audit or improve flows, strengthen error recovery and keyboard use, and verify journeys with builds and tests.
Why use it?
It helps find confusing steps, missing feedback, trust problems, and situations where users can get stuck. It turns those findings into focused improvements and checks whether the main journey works.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; mentions Codex.

Good fit Use it to define and map user tasks, audit or improve flows…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eid0lon/zero-slop/perfect-ux
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Eid0lon/zero-slop --skill perfect-ux
Clone the repo
git clone --depth 1 https://github.com/Eid0lon/zero-slop

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for perfect-ux

README.md
[![agentmods](https://agentmods.dev/badge/skills/eid0lon/zero-slop/perfect-ux.svg)](https://agentmods.dev/skills/eid0lon/zero-slop/perfect-ux)
Your own site
<a href="https://agentmods.dev/skills/eid0lon/zero-slop/perfect-ux"><img src="https://agentmods.dev/badge/skills/eid0lon/zero-slop/perfect-ux.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,754 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00108 $0.01754
Opus 5 $0.00054 $0.00877
Sonnet 5 $0.00022 $0.00351
Haiku 4.5 $0.00011 $0.00175

Measured 7d ago against content hash 1567b2f6f369, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

perfect-ux scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/perfect_ux_cli.py, scripts/test_perfect_ux_cli.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/perfect-ux/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perfect UX

Status: beta.

Perfect UX is the user-success layer. perfect-design makes the interface coherent and product-specific; no-slop blocks generic AI residue; reality-skill makes workflows real. Perfect UX asks: can the intended user understand what to do, finish the job, recover from problems, trust the system, and get faster over time?

Command Interface

Use references/command-interface.md.

Primary commands:

perfect-ux --contract [brief-or-target]
perfect-ux --map [brief-or-target]
perfect-ux --audit [target]
perfect-ux --fix [target]
perfect-ux --harden [target]
perfect-ux --judge [target]
perfect-ux --verify [target]
perfect-ux -e --audit [target]

Short flags:

  • -c, --contract: write the UX Contract before code.
  • -m, --map: map jobs, entry points, decisions, states, and recovery paths.
  • -a, --audit: find UX friction, ambiguity, accessibility blockers, trust gaps, and missing evidence.
  • -f, --fix: make the smallest coherent UX improvement pass.
  • --harden: add resilience, edge states, keyboard paths, recovery, and proof.
  • -j, --judge: run the strict UX judge panel.
  • --verify: prove the primary journey with build, tests, browser, accessibility, and task evidence.
  • -e, --economy: disable live subagent judges only when the user explicitly accepts a lower-cost review.

Default mode:

  • Existing UI target: --audit.
  • Editable request on an existing target: --fix.
  • Brief without target: --contract.

First Action

Load steps/step-00-command-router.md.

Step 00 parses command flags, discovers the product surface, resolves UX dials, loads only relevant references, and routes to contract, map, audit, fix, harden, judge, or verify.

Core References

Load only what the task needs:

  • references/command-interface.md: grammar, precedence, output contracts.
  • references/dials-and-presets.md: UX dials, presets, and pass thresholds.
  • references/research-synthesis.md: compressed research from NN/g, W3C/WAI, WCAG, GOV.UK, Apple HIG, Material, Fluent, Baymard, web.dev, design systems, and Human-AI guidance.
  • references/research-source-ledger.md: source map and what each source contributes.
  • references/ux-contract.md: pre-code contract and rejection rules.
  • references/ux-gates.md: the hard UX gates used for audit, fix, harden, and judge.
  • references/journey-playbook.md: jobs, IA, flow mapping, decision paths, onboarding, dashboards, commerce, AI tools, and expert use.
  • references/interaction-playbook.md: controls, forms, feedback, validation, recovery, keyboard, motion, mobile, and performance feel.
  • references/content-and-trust.md: UX writing, labels, claims, AI uncertainty, empty states, errors, consent, and trust boundaries.
  • references/measurement-and-research.md: usability testing, analytics, task metrics, research method choice, and evidence loops.
  • references/ecosystem-contract.md: ownership and composition with sibling skills.
  • references/judge-system.md: judge protocol and gate formula.
  • references/verification-playbook.md: build/browser/accessibility/task verification.
  • references/self-coaching.md: internal checklist for stuck or ambiguous UX decisions.

Read the full file on GitHub · 167 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 167 lines · 108 tokens per session scan A 1567b2f6f369

Subscribe to this mod's changes

perfect-ux is a skill published in the GitHub repository Eid0lon/zero-slop (12 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 108 tokens to every session and 1,754 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

design-taste-frontend

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

Leonxlnx/taste-skill · 61 tokens

image-to-code

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…

Leonxlnx/taste-skill · 116 tokens

html-artifacts

Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.

langchain-ai/open-swe · 51 tokens

brandkit

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…

Leonxlnx/taste-skill · 89 tokens

minimalist-ui

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

Leonxlnx/taste-skill · 34 tokens

skin-creator

Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.

netease-youdao/LobsterAI · 48 tokens