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 Uxcel-Lab/product-skills --skill onboardinggit clone --depth 1 https://github.com/Uxcel-Lab/product-skillsWrote 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/uxcel-lab/product-skills/onboarding)<a href="https://agentmods.dev/skills/uxcel-lab/product-skills/onboarding"><img src="https://agentmods.dev/badge/skills/uxcel-lab/product-skills/onboarding/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/uxcel-lab/product-skills/onboarding"><img src="https://agentmods.dev/badge/skills/uxcel-lab/product-skills/onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02117 |
| Opus 5 | $0.00036 | $0.01059 |
| Sonnet 5 | $0.00014 | $0.00423 |
| Haiku 4.5 | $0.00007 | $0.00212 |
Grade A, and why
ux-onboarding 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding Flow Skill
How this skill behaves (read first)
This is a generative skill, and onboarding is a prime over-design trap: the default instinct is a multi-screen tour nobody reads plus a wall of upfront questions and "enable all permissions" prompts — which actively blocks the product and drives drop-off. The lessons are blunt: most apps don't need a tutorial; users learn by using. So this skill gates hard:
- First gate: does this even need onboarding? Often the answer is "barely" — and the best onboarding is the lightest one that gets users to value.
- Apply the always-true core — the principles that hold for any first-run experience.
- Choose the method and asks deliberately — surface the context-dependent decisions with trade-offs; don't default to a 6-screen carousel.
Then hand off to the audits — especially dark-patterns (onboarding is where forced permissions/notifications and friend-spam concentrate).
Step 0 — Establish context, starting with the gate
Gate — does it need onboarding? Per the lessons, onboarding is warranted mainly when:
- the app is complex (explain features as users reach them, not upfront), or
- you genuinely need data to function (e.g. a banking app), or
- workflows are unique/unfamiliar, or
- a tutorial is expected (e.g. mobile gaming).
If none hold, recommend the lightest touch — empty-state nudges and contextual tips — over a tour. Then capture:
- Product complexity — learn-by-doing vs. genuinely needs explanation.
- What's truly required to start — the minimum data/permissions, if any.
- Audience — novice vs. expert; one persona or several (drives persona-based branching).
- Platform — mobile (system permission prompts, tight space) vs. web.
State assumptions if proceeding without answers.
The always-apply core (true for any onboarding)
- Front-load value; deliver an early win. Show the benefit before asking for anything. Duolingo ends onboarding with two real sentences. Early success drives retention.
- Keep it short. ~4–5 screens max; most users expect onboarding to take ≤60 seconds. If it feels like a lecture, users skip it.
- Ask for the minimum, and say why. Don't bombard with questions before trust is built. Every field/permission needs a clear "why now"; if you can't justify it at launch, collect it later, contextually.
- One thing at a time. One contextual tip at a time; introduce features at the pace users meet them. Less is more.
- Apply progressive disclosure. Primary/most-common features first; reveal advanced options on request. Keep to ≤2 levels of depth.
- Always skippable, with visible progress. Tell users how many steps and where they are; let them exit. Never trap them in the tour.
- Use empty states and success states. A blank screen is an onboarding opportunity (educational content + a clear CTA); a success state early creates a positive first connection.
- End with a clear, relevant CTA — the next logical action ("Start shopping", "Create your first project").
- Don't re-show completed onboarding. Track state; repeating tips after completion is friction.
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.
- 10d ago First seen · 122 lines · 71 tokens per session scan A 163a81db2029
ux-onboarding is a skill published in the GitHub repository Uxcel-Lab/product-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 2,117 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 2026-08-31.
Other skills, from other repositories
pm-brand-motion
A guided process for defining a brand's motion style and making a logo animation demonstration.
pm-proto
A product-prototyping workflow for planning how an application should work and what its screens should contain. It connects product requirements to interface layouts and interactions.
diagram-design
Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel, nested, tree, org chart, layer stack, Venn, pyramid/funnel, treemap, bar, line, Gantt and scatter charts, high-level…
design-mobile-apps
Use when the user wants to design a mobile app or UI screens, when they mention their Sleek (sleek.design) projects, or when implementing Sleek designs in code (HTML, React Native, SwiftUI).
dengguang-zhaoming-bikeng-zhinan
A Chinese-language knowledge guide about home lighting, including ceiling lights, light strips, color temperature, color rendering, and room zoning.
appllama-app-design-skill
Build native-feeling, benchmark-quality mobile app screens (Expo / React Native). Use when designing or implementing any mobile UI — screens, flows, onboarding, paywalls, tab bars, sheets, settings, empty states — or when polishing motion, navigation, typography, dark mode, or perceived performance. Enforces Apple HIG…