ai-agent-ux SKILL.md skillA

ai-agent-ux from varunk130/ai-ux-skill-library is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add varunk130/ai-ux-skill-library/ai-agent-ux@git:20261002.c25745d

Pins git:20261002.c25745d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
varunk130/ai-ux-skill-library
Path
skills/ai-agent-ux/SKILL.md
Versions recorded
4
Latest version
git:20261002.c25745d, committed Oct 2, 2026
First version recorded
Apr 3, 2026
Size
8,884 bytes
Repository stars
3
License
MIT

Design user experiences for autonomous AI agents that act on behalf of users - control panels, consent flows, action previews, audit trails, and undo mechanisms. Use when: agentic AI, autonomous agents, AI autonomy controls, agent UX, AI actions, computer use, agent consent, agent audit trail.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# AI Agent UX

Design experiences for AI that doesn't just suggest - it acts. Booking flights, sending emails, executing code, making purchases. The AUTONOMY framework ensures users stay in control while AI operates at machine speed.

## Core Principle

Agentic AI inverts the traditional UX model. In classical UX, users take actions and the system responds. In agentic UX, the **system takes actions and users supervise.** This requires an entirely new design vocabulary: previews instead of forms, audit trails instead of history, interrupts instead of navigation.

---

## The AUTONOMY Framework

| Letter | Principle | Design Question |
|---|---|---|
| **A** | Action Preview | Can the user see exactly what the agent will do before it does it? |
| **U** | User Override | Can the user stop, modify, or redirect the agent at any point during execution? |
| **T** | Tiered Authority | Does the agent's freedom scale appropriately with risk level? |
| **O** | Observable State | Can the user see what the agent is doing right now, in real time? |
| **N** | Narrated Reasoning | Does the agent explain why it chose this action over alternatives? |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add varunk130/ai-ux-skill-library/ai-agent-ux@sha256:bc0aaf368ef19a3f

The line at the top of this page pins the label git:20261002.c25745d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_sc6ycwofejrprxcx.svg)](https://markdownregistry.com/a/art_sc6ycwofejrprxcx)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Apr 3, 2026 and Oct 2, 2026, about one every 60 days.

versioncommittedcommitsizeaudit
git:20261002.c25745d latest2026-10-02 c25745d 8,884 BA view · diff
git:20260731.50632802026-07-31 5063280 8,832 BA view · diff
git:20260522.334c3db2026-05-22 334c3db 8,832 BA view · diff
git:20260403.b118c062026-04-03 b118c06 8,836 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8884 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

varunk130/ai-ux-skill-library · 3 stars · license MIT · pushed 2026-10-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_sc6ycwofejrprxcx
GET https://markdownregistry.com/api/v1/resolve?ref=varunk130/ai-ux-skill-library/ai-agent-ux
GET https://markdownregistry.com/api/v1/blob/bc0aaf368ef19a3f35b18b6f45a5b71a474ff8bfdbe6adf560cf8f52f3ab5a56

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from varunk130/ai-ux-skill-library

ai-accessibility-audit SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-accessibility-audit/SKILL.md · WCAG 2.2 Level AA accessibility audit for AI product surfaces - color contrast, focus order, ARIA usage, keyboard…
git:20260731.41488cf · audit A · 3 stars
ai-conversation-architect SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-conversation-architect/SKILL.md · Design conversational AI interfaces that feel natural, recover from failures gracefully, and build user trust through…
git:20260731.c851cc8 · audit A · 3 stars
ai-error-resilience SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-error-resilience/SKILL.md · Design graceful failure experiences for AI products - hallucinations, uncertainty, wrong outputs, and edge cases. Use…
git:20261002.c25745d · audit A · 3 stars
ai-feedback-loops SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-feedback-loops/SKILL.md · Design feedback mechanisms that help AI systems learn from users - thumbs up/down, preference ranking, corrections, and…
git:20260731.5f0a41e · audit A · 3 stars
ai-journey-mapper SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-journey-mapper/SKILL.md · Map human-AI interaction journeys - trust arcs, capability discovery paths, autonomy progression, and AI-specific…
git:20260731.16bb508 · audit A · 3 stars
ai-multimodal-output SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-multimodal-output/SKILL.md · Design how AI presents results across text, code, images, charts, and mixed media - response formatting, output…
git:20260731.59714f3 · audit A · 3 stars
ai-onboarding-calibration SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-onboarding-calibration/SKILL.md · Design onboarding experiences that help users build accurate mental models of AI capabilities, set expectations, and…
git:20261003.54bd2fa · audit A · 3 stars
ai-personalization-ethics SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-personalization-ethics/SKILL.md · Design AI-driven personalization that adapts interfaces to users while respecting privacy, avoiding filter bubbles, and…
git:20260731.2dac556 · audit A · 3 stars
ai-prompt-ux SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-prompt-ux/SKILL.md · Design the input experience for AI products - how users craft, structure, and refine their instructions to AI systems…
git:20260731.f85f24b · audit A · 3 stars
ai-safety-guardrails SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-safety-guardrails/SKILL.md · Design safety experiences for AI products - content moderation UX, bias detection surfaces, harm prevention patterns…
git:20261002.c25745d · audit A · 3 stars
ai-trust-transparency SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-trust-transparency/SKILL.md · Design explainability interfaces that help users understand AI decisions, build calibrated trust, and verify AI…
git:20261002.c25745d · audit A · 3 stars
ai-ux-eval SKILL.md skill
varunk130/ai-ux-skill-library · skills/ai-ux-eval/SKILL.md · Evaluate the UX quality of an AI product with a scored, repeatable rubric - eval set design, criteria that raters agree…
git:20261002.872e629 · audit A · 3 stars

Every file in varunk130/ai-ux-skill-library

Browse by kind, by grade A, or by owner.