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.
npx skills add tobihagemann/turbo --skill user-experiencegit clone --depth 1 https://github.com/tobihagemann/turboWrote 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.
[](https://agentmods.dev/skills/tobihagemann/turbo/user-experience)<a href="https://agentmods.dev/skills/tobihagemann/turbo/user-experience"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/user-experience/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tobihagemann/turbo/user-experience"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/user-experience.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.00488 |
| Opus 5 | $0.00036 | $0.00244 |
| Sonnet 5 | $0.00014 | $0.00098 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
user-experience 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 6d ago.
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.
What it actually says
User Experience
Apply this lens to any user-facing change, both before committing to an approach and when judging a built experience. Keep the work anchored to what the user is trying to accomplish.
Lead with the user's goal rather than a list of surface fixes. A pile of small corrections ("relabel this", "move that") is a sign the underlying flow was never examined. Start from intent and work down to detail.
Scope: this lens covers whether a change serves the user and whether the path through it is coherent. Visual and aesthetic craft — typography, color, spacing, motion polish — is a separate concern and stays out of scope here.
Understanding
Establish what the user actually needs before shaping a solution.
- Name the user and the job they came to do.
- Separate the stated request from the goal behind it, and solve the goal.
- Ground claims about user needs in evidence (observed behavior, recurring reports, real usage). Flag a need that is assumed rather than known.
Bridging
Translate the need into the right solution rather than the first one that comes to mind.
- Check that the solution addresses the goal, not just the visible symptom.
- Weigh whether the change adds a step, a screen, or a concept the user must learn, and whether that cost is justified.
- Prefer the path that removes work for the user over one that adds configuration or choices.
- Watch for solving a builder's convenience at the user's expense.
Flowing
Trace the path the user takes from end to end.
- Follow the full journey: how the user arrives, the change itself, and what happens after.
- Walk the unhappy paths in the running software when it can be run: empty states, seeded defaults, errors, interruptions, first-time versus returning use. Flag any of these judged from source alone.
- Confirm the user always knows what just happened and what to do next.
- Surface friction: redundant steps, dead ends, and points where the user must hold state in their head.
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.
- 6d ago First seen · 39 lines · 71 tokens per session scan A e3a447545353
user-experience is a skill published in the GitHub repository tobihagemann/turbo (402 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 488 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
design-swarm
Orchestrate a team of 10 design agents for holistic UI audit, ideation, and implementation. Use when: "design swarm", "holistic audit", "design review with all lenses", "full design analysis". Modes: audit, ideate, implement (any combination). Targets: screenshots, URLs, file paths, or text briefs.
visual-explainer
Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to…
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
taste
Use when improving the visual taste, positioning, polish, trust, and conversion clarity of a website or product UI. Runs a category-first visual audit, applies a decisive design pass, and verifies the result with screenshots rather than subjective vibes.
flowchart-creator
Create HTML flowcharts and process diagrams with decision trees, color-coded stages, arrows, and swimlanes. Use when users request flowcharts, process diagrams, workflow visualizations, or decision trees.