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 varunk130/ai-ux-skill-library --skill ai-onboarding-calibrationgit clone --depth 1 https://github.com/varunk130/ai-ux-skill-libraryWrote 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/varunk130/ai-ux-skill-library/ai-onboarding-calibration)<a href="https://agentmods.dev/skills/varunk130/ai-ux-skill-library/ai-onboarding-calibration"><img src="https://agentmods.dev/badge/skills/varunk130/ai-ux-skill-library/ai-onboarding-calibration/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/varunk130/ai-ux-skill-library/ai-onboarding-calibration"><img src="https://agentmods.dev/badge/skills/varunk130/ai-ux-skill-library/ai-onboarding-calibration.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 | $0.00059 | $0.02133 |
| Opus 5 | $0.00030 | $0.01066 |
| Sonnet 5 | $0.00012 | $0.00427 |
| Haiku 4.5 | $0.00006 | $0.00213 |
Grade A, and why
ai-onboarding-calibration 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 12d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Onboarding & Calibration
Design first-time and ongoing experiences that help users understand what AI can and cannot do, build accurate expectations, and discover capabilities at the right pace. The CALIBRATE framework treats onboarding as a continuous calibration process, not a one-time tutorial.
Core Principle
AI onboarding is fundamentally different from traditional software onboarding. In traditional software, features are deterministic - a button always does the same thing. In AI products, the same input can produce different outputs, capabilities have fuzzy boundaries, and what the AI "can do" depends on context. You are not teaching features. You are calibrating a mental model.
The CALIBRATE Framework
| Letter | Principle | Design Question |
|---|---|---|
| C | Communicate Boundaries | Does the user know what the AI is and isn't good at? |
| A | Anchor with Examples | Have you shown, not told, what the AI can do? |
| L | Layer Complexity | Do simple use cases come first, with advanced capabilities revealed over time? |
| I | Invite Experimentation | Is there a safe, low-stakes way to explore what the AI can do? |
| B | Build Incrementally | Does the user's understanding deepen with each interaction? |
| R | Recalibrate After Failures | When the AI disappoints, does the onboarding help users adjust expectations? |
| A | Adapt to Expertise | Does the experience change based on the user's skill level? |
| T | Track Understanding | Can you measure whether users have an accurate mental model? |
| E | Evolve with the Product | When AI capabilities change, does the onboarding update? |
The Mental Model Gap
The #1 onboarding failure in AI products: users arrive with the wrong mental model.
| Mental Model | What Users Expect | What Actually Happens | Design Intervention |
|---|---|---|---|
| Omniscient AI | AI knows everything, never wrong | AI has knowledge gaps and can hallucinate | Boundary disclosure: "I work best with X. I struggle with Y." |
| Search Engine | AI retrieves existing answers | AI generates novel responses (may be wrong) | Show that AI is creating, not retrieving: "Here's my analysis..." |
| Human Assistant | AI understands nuance, reads between lines | AI takes instructions literally | Teach prompting: show how specific instructions improve results |
| Magic Tool | One prompt = perfect output | Multiple iterations usually needed | Normalize iteration: "Let's refine this together" |
| Infallible Calculator | AI outputs are mathematically certain | AI outputs are probabilistic | Confidence indicators from the very first interaction |
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.
- 12d ago First seen · 168 lines · 59 tokens per session scan A a07066523c76
ai-onboarding-calibration is a skill published in the GitHub repository varunk130/ai-ux-skill-library (3 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 2,133 once invoked, about $0.0003 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
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
component-family-consistency
Buttons, inputs, pills, badges, calendars, and other interactive components form a visual family — they share the same border-radius, colour logic, shadow scale, border style, and spacing rhythm. Inconsistency between them breaks the sense of a coherent product. Use when building or reviewing a component library…
modular-scale-typography
Typography feels cohesive and intentional when font sizes follow a modular scale — a ratio-based sequence where every size is mathematically related to the others. Use when defining type scales, setting up design tokens, reviewing font size choices, or when typography feels inconsistent or arbitrary.
extract-design
Extract a complete design system — colors, typography, spacing, components, shadows, and W3C design tokens — from any live website using Dembrandt. Runs a headless browser against the URL and returns real computed values from the DOM. Use when you need a site's actual design tokens, want to reverse-engineer a visual…
paint
Paint a complete visual universe with genjutsu - art direction brainstorm, design system, implementation, audit. Anti-AI-slop design pipeline. Adapts to Web, Android (Compose), Apple (SwiftUI).
algorithmic-color-palette
Derive a full UI colour palette algorithmically from one or two brand colours. Darker and lighter variants for interactive states, desaturated greys from the brand hue for borders and backgrounds, and semantic colours that feel coherent with the brand rather than generic. Use when building a colour system from scratch…