RetentaRetenta

Evidence record · captured 2026-10-11

Web App Testing with Playwright

Has the agent test local web apps by writing native Python Playwright scripts, following a decision tree (static HTML vs dynamic app, server already running or not). It uses a bundled helper to start one or more dev servers, wait for their ports, run the test script and clean up, and examples for console-log capture and element discovery.

Community publisherUnverifiedSource reviewedBehavior not tested
Source review

Editorial assessment

This is a source-only assessment. It does not claim runtime or security testing.

What it does

Gives the agent a decision tree for driving a local web app with Python Playwright, plus a helper that owns dev-server lifecycle. Its core habit is reconnaissance first: render, wait for network idle, then pick selectors.

Best for

  • Checking that a local frontend change actually works in a real browser before reporting it done
  • Debugging UI behavior that needs console logs or a full-page screenshot
  • Testing a frontend and backend together by starting both servers in one command

Strengths in the source

  • scripts/with_server.py starts one or more server commands, polls each port until ready, runs the test command, and terminates every server in a finally block.
  • Tells the agent to wait for networkidle before inspecting the DOM of a dynamic app, the most common cause of empty or wrong selectors.
  • Tells the agent to run bundled scripts with --help and use them as black boxes rather than reading their source into context.
  • Ships small examples for console-log capture, element discovery and file:// automation of static HTML.

Limitations

  • Requires Python 3, the playwright package and installed browser binaries; none of these are set up by the skill.
  • with_server.py runs each --server value with shell=True, so it executes whatever command string the agent passes on the local machine.
  • Covers ad hoc automation scripts, not a test suite: no assertions framework, fixtures, CI setup or cross-browser guidance, and it targets local apps only.

When not to use it

  • Projects that already have a Playwright Test or Cypress suite, where adding to that suite is the better path
  • Testing deployed or third-party sites you do not control

Reviewed by Retenta editorial on 2026-10-11; scope: source only.

Files included in this review
  • skills/webapp-testing/SKILL.md

Evidence and boundaries

Execution · not tested

Retenta has not executed this skill.

Security · not tested

Bundles 2 scripts (scripts/with_server.py, examples/*.py) that the agent may run. Retenta has not run them or scanned them.

Pinned publisher source
skills/webapp-testing/SKILL.md
Revision
dbd4588f9e1033efb41dad4bef2f7947c8993d44
License evidence
Apache-2.0Retenta preserves the license text captured with this immutable upstream snapshot; no independent legal or security review is claimed.
Last source change
2025-12-01
Independent verification
Published by Anthropic, which does not own the product this skill covers. Not independently verified.
Upstream repository
Open publisher repository

Compatibility

Claude Code (plugin marketplace)

documented

Named in the upstream skill or repository documentation; not tested by Retenta.

Claude.ai

documented

Named in the upstream skill or repository documentation; not tested by Retenta.

Claude API (Skills API)

documented

Named in the upstream skill or repository documentation; not tested by Retenta.

Requirements and access

  • Python 3 + playwright (with browsers installed)
  • The app's dev server command

Referenced tools

No named tool is required by the reviewed SKILL.md.

Install from the source

Clones the current default branch, which may be newer than the reviewed revision dbd4588. The destination shown is Claude Code's personal skills folder; other agents read the same folder from their own skills directory.

View the SKILL.md at its source Verify the publisher's install documentation

More Web and frontend skills →

Install the full skill folder

git clone --depth 1 https://github.com/anthropics/skills.git
cp -R skills/skills/webapp-testing ~/.claude/skills/webapp-testing

Thyme RAG Capsules

Make this skill’s state durable, governed, and portable.

A Retenta capsule lets agents recall prior work, append provenance-stamped progress, and carry the memory to the next run.

Create durable agent memoryUnderstand the evidence labels