aidd-user-testing

A test-script generator for checking whether people and AI agents can complete a product journey. It uses a user journey and persona, including the person's skill level, patience, and goals.

In plain words
What is it for?
Creating think-aloud scripts for recorded human tests and executable browser-agent scripts with screenshots. It helps validate that users can complete a specified task.
Why use it?
It turns a journey description into repeatable checks, so teams do not have to design human and browser-agent tests by hand. It also makes confusing steps and failures easier to record.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/paralleldrive/aidd/aidd-user-testing
Any agent
npx skills add paralleldrive/aidd --skill aidd-user-testing
Clone the repo
git clone --depth 1 https://github.com/paralleldrive/aidd

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 992 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00992
Opus 5 $0.00016 $0.00496
Sonnet 5 $0.00007 $0.00198
Haiku 4.5 $0.00003 $0.00099

Measured 2d ago against content hash 4135d9a603cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aidd-user-testing 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (user-testing.test.js), 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.

ai/skills/aidd-user-testing/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Testing Generator

Use UserJourney and Persona from /aidd-product-manager

Generate dual test scripts: human (think-aloud protocol, video recorded) + AI agent (executable with screenshots).

Types

UserTestPersona { ...Persona role techLevel: "novice" | "intermediate" | "expert" patience: 1..10 goals: string[] }

UserTestStep { ...Step action intent success checkpoint?: boolean }

Scripts

HumanScript:template { """

Test: ${journey.name}

Persona: ${persona.name} — ${persona.role}

Pre-test

  • Start screen recording
  • Clear state (cookies, cache, cart)
  • Prepare credentials if needed

Instructions

Read each step out loud before attempting it. Think aloud as you work - this helps reviewers follow along.

Steps

For each step:

  • Goal: ${step.intent}
  • Do: ${step.action}
  • Think aloud: What do you see? Any friction?
  • Success: ${step.success}

Post-test

  • Stop recording
  • What was confusing?
  • What worked well?
  • Would you complete this in real life? """ }

AgentScript:template { """

Agent Test: ${journey.name}

Environment: Drive real browser, discover UI by looking (no source code access)

Persona behavior:

  • Patience: ${persona.patience}/10
  • Retry: ${persona.techLevel == "expert" ? "immediate" : "exponential backoff"}
  • On failure: ${persona.patience > 5 ? "retry" : "abort"}

Execution

For each step, narrate your thoughts like a human tester:

  1. Interact with real UI: ${step.action}
  2. Express confusion, expectations, what you see
  3. Validate rendered result: ${step.success}
  4. Screenshot browser viewport if checkpoint or failure
  5. Record: difficulty (easy/moderate/difficult), duration, what was unclear
  6. Retry with backoff if failed and patient

Output Format

# Test Report: ${journey.name}

**Completed**: X of Y steps

## Step: [step name]
- **Status**: ✓ Success / ✗ Failed
- **Duration**: Xs
- **Difficulty**: easy/moderate/difficult
- **Thoughts**: [What I saw, expected, any confusion]
- **Screenshot**: [path if captured]

## Blockers
- [Any steps that couldn't be completed and why]

""" }

Read the full file on GitHub · 149 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 149 lines · 33 tokens per session scan A 4135d9a603cb

Subscribe to this mod's changes

aidd-user-testing is a skill published in the GitHub repository paralleldrive/aidd (380 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 992 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

agent-browser

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

vercel-labs/open-agents · 51 tokens

computer-use

Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…

kirodotdev/KiroCrew · 105 tokens

feature-demo-recording

Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…

kirodotdev/KiroCrew · 90 tokens

browser-recording

Record a browser flow as a video/GIF for evidence — animations, transitions, and multi-step interactions that a still screenshot cannot prove. Drives the project's own Playwright through a bundled runner, then converts to mp4 + GIF via ffmpeg. Use when the user asks to record a demo, capture a GIF or video of the UI…

kirodotdev/KiroCrew · 85 tokens

web-browse

Open a REAL external web page so the user can see it in Kiro Crew's Browser panel. PRIMARY path is the browser MCP tool (drives the built-in native panel); playwright-cli is the fallback for remote/plain-browser sessions and for attached logged-in browsers. Use when the user wants to VIEW / verify / "show me" an…

kirodotdev/KiroCrew · 93 tokens

web-verify

Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…

kirodotdev/KiroCrew · 0 tokens