TASK GUIDE · SOURCE-AWARE

Best Agent Skills for web application testing

A minimal Skill plan for browser behavior, logs, screenshots, and repeatable acceptance checks.

Build this plan for my Agent ↗
Desired outcome

Prove the critical user flow works in a real browser and leave repeatable evidence.

Safe working boundary

Use test data and a local or explicitly approved environment.

01 · SKILL STACK

A minimal three-role stack

Each role has one job. The personalized builder can adjust the selection for your Agent without changing the decision logic.

01 · Core execution

playwright-workflows

Exercises the real user flow in a browser.

Main limitation
Detailed package files are not fully catalogued.
First risk
Review before install
Source evidence
Editorial source
Inspect the Skill ↗
02 · Guardrail

web-design-guidelines

Defines scope and prevents a broad, unfocused test run.

Main limitation
It depends on network access and a live guideline document whose contents can change over time.
First risk
Rule drift or context-free findings
Source evidence
Pinned · b8caa260
Inspect the Skill ↗
03 · Evidence

minimal-run-and-audit

Retains visual and runtime evidence for review.

Main limitation
It does not choose the reproduction target, train a model, conduct broad paper analysis, or hide scientific-meaning changes.
First risk
Scientific changes hidden as setup fixes
Source evidence
Pinned · 3ab50525
Inspect the Skill ↗

02 · ACCEPTANCE

How to know the task is finished

  1. Run one critical flow from a clean browser state.
  2. Assert the expected page state, not only a successful click.
  3. Save the failure signal needed to reproduce any defect.

03 · STOP CONDITIONS

When to stop

  • The test requires production credentials or personal data.
  • The script performs destructive actions without isolation.
  • A flaky result is reported as a pass.

04 · METHOD

How this guide was produced

SkillSignal maps a defined task to three non-overlapping responsibilities, then selects from reviewed catalog metadata. Agent fit, source state, permissions, and published scores are evaluated with deterministic rules. No LLM writes or reorders the recommendation at request time.