Automated summary

This skill runs behavior tests against a web UI using sitetest by executing YAML runbooks, discovering testable behaviors from a captured site, or diffing against baselines.

Strengths

Headless runbook execution with reporting of passed/failed steps, timing and failure reasons
A discover mode that generates runbooks from a sitecap directory and reports confidence levels
Structured JSON or JUnit XML output suitable for CI pipelines
$VAR resolution from a .env file to support authentication flows

Limitations

Fully dependent on the sitetest npm package and the sitecap format, which the skill does not provide
Covers browser-driven web UIs only, with no API or unit-test support
Discovered runbooks are auto-generated and need manual review before being trusted

When to use it

Use it when you need to run or scaffold end-to-end behavior tests against an existing web interface.

When not to use it

Avoid it for unit tests, browserless API tests, or projects that do not use the sitetest/sitecap tooling.

Security analysis

Caution

Quality score78/100

Nothing here is destructive, obfuscated, or exfiltrating: commands are plain `npx sitetest run/discover` calls with documented flags. However, the skill executes an unpinned remote npm package, launches a real browser against arbitrary sites, and can inject .env credentials into automated flows, which are powerful capabilities with legitimate purpose. That places it at 'caution' rather than 'safe'.

Findings

•Runs unpinned third-party npm package via `npx sitetest` (supply-chain / arbitrary code execution risk from a remote registry package)
•Launches headless Chrome and drives a live web UI; test runs can perform real actions (logins, form submissions) against whatever site the runbook targets
•Accepts `-e <path-to-.env>` and resolves `$VAR` secrets inside runbooks, so credentials are fed into an automated browser flow with no guardrails or scope limits
•No allowed-tools declared, so the skill implicitly assumes shell/npx/Chrome access with no restriction on runbook paths or target URLs
•Writes generated runbooks to /tmp without cleanup guidance

How this analysis is made

Examples

Run a login flow test

/test tests/login-flow.yaml — run it headless and tell me which steps failed and why

Run the whole suite and keep going

/test tests/ --continue-on-error and summarize pass/fail plus timing per runbook

Discover testable behaviors

/test discover ./captures/example.com then read the generated runbooks and tell me how many pages and elements are covered

/test

Name: UI Behavior Testing with sitetest
Author: Skills Guide Bot

Run behavior tests against a web UI using sitetest — execute runbooks, discover testable behaviors, or capture baselines.

Usage

/test <runbook.yaml> [options]
/test discover <sitecap-dir>

Instructions

When this skill is invoked:

Running a runbook:

npx sitetest run <runbook.yaml> --headless

After the run completes, report the results: steps passed/failed, timing, and any failure reasons. If a capture diff fails, read the diff image to show what changed.

Discovering behaviors:

npx sitetest discover <sitecap-dir> -o /tmp/sitetest-runbooks

After discovery, read the generated YAML runbooks and summarize: how many pages, how many testable elements per page, confidence levels.

With env vars (for auth flows):

npx sitetest run <runbook.yaml> --headless -e <path-to-.env>

Options

Pass additional flags after the runbook path:

--headless — launch headless Chrome (default for skill)
--continue-on-error — run all steps even after failures
--output json — structured JSON output
--output junit — JUnit XML for CI
-e <path> — .env file for $VAR resolution in runbooks

Examples

/test tests/login-flow.yaml
/test tests/ --continue-on-error
/test discover ./captures/example.com

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/ui-behavior-testing-with-sitetest-mryiqh90/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/ui-behavior-testing-with-sitetest-mryiqh90' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/ui-behavior-testing-with-sitetest-mryiqh90/download' --output '.skill-downloads/ui-behavior-testing-with-sitetest-mryiqh90/SKILL.md.part' && mv '.skill-downloads/ui-behavior-testing-with-sitetest-mryiqh90/SKILL.md.part' '.skill-downloads/ui-behavior-testing-with-sitetest-mryiqh90/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/ui-behavior-testing-with-sitetest-mryiqh90/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.