Updated: Jul 19, 2026
Version: v1.1
Sources: 1 source
Status: Published

webapp-testing

Web app testing

Anthropic

Verifies a local browser journey and produces reproducible evidence without deploying the application.

License: Apache-2.0
Risk: Risk level: high

Risk profile

This is a risk profile, not a certification or a safety guarantee.

What can it read? Present: It can read what the local app shows in the browser, including the page structure.
What can it create or change? Present: It can create test scripts, save screenshots, and change the local test app while it runs.
Can it use the internet or send data? Not evaluated: The published fields do not say whether this skill can use the internet or send data.
Can it use saved logins or a paid quota? Not evaluated: The published fields do not say whether this skill can use saved logins or a paid quota.
Which action needs your approval? Not evaluated: The published fields do not say which actions need your approval first.
When was the source verified, and has the snapshot changed since? Present: The source was last verified on 2026-07-19. The published snapshot still matches that verification. This is not a live check of the upstream source.

Canonical source: https://github.com/anthropics/skills/blob/fa0fa64bdc967915dc8399e803be67759e1e62b8/skills/webapp-testing/SKILL.md(opens in a new tab)
Source revision: fa0fa64bdc967915dc8399e803be67759e1e62b8
License: Apache-2.0
Verification date: 2026-07-19
Source status: Verified
Change status: Snapshot consistent; The published snapshot still matches the last verification. This is not a live check of the upstream source.

Understand

Covered goals

test a local web application
verify UI behavior
capture reproducible browser evidence

Inputs → outputs

local application URL or static HTML file
user journey and expected behavior
server command and port when the application is not already running

native Python Playwright automation script
observed UI behavior, screenshots, rendered DOM evidence, or browser console logs

Recognize

Verbatim from the English source

Triggers

test this web app
validate a UI flow
reproduce a browser issue

Non-triggers

deploy an application
test a remote production mutation without authorization
replace unit tests with screenshots

Choose

Verbatim from the English source

Permissions

write and execute scoped Python Playwright scripts
launch a local browser and read rendered application state
start and stop explicitly scoped local application servers
interact with and potentially mutate local test application state

External effects

local browser and optional application-server processes are started and stopped
Python scripts, screenshots, DOM captures, and logs can be written to disk
browser actions can mutate the local application's test state

Compatibility

local web applications in a Python environment with Playwright and Chromium

Required tools

Python
Playwright synchronous API and Chromium
optional scripts/with_server.py helper for local server lifecycle

Check permissions and confirm every external effect before using this skill.

Compare

Works withWeb interface audit Works withReact best practices

Understand → Recognize → Choose → Compare

Pack for your agent

Pre-written instruction by SkillCodex — your request is neither sent nor used to adapt this text; no content is generated, and copying executes nothing.

Use in your agent

Complete the task with Web app testing

# Use Web app testing in your agent

## Objective
Use the existing webapp-testing skill only when it directly covers the requested task.

## Prerequisites
- local application URL or static HTML file
- user journey and expected behavior
- server command and port when the application is not already running
- Python
- Playwright synchronous API and Chromium
- optional scripts/with_server.py helper for local server lifecycle

## Permissions
- write and execute scoped Python Playwright scripts
- launch a local browser and read rendered application state
- start and stop explicitly scoped local application servers
- interact with and potentially mutate local test application state

## External effects
- local browser and optional application-server processes are started and stopped
- Python scripts, screenshots, DOM captures, and logs can be written to disk
- browser actions can mutate the local application's test state

## Procedure
- Open the canonical source pinned to revision fa0fa64bdc967915dc8399e803be67759e1e62b8.
- Read the skill instructions before calling its tools.
- Ask for confirmation before any paid, destructive, or remote effect not already authorized.
- Run the procedure within the requested scope and retain useful evidence.

## When not to use
- deploy an application
- test a remote production mutation without authorization
- replace unit tests with screenshots

## Expected result
- native Python Playwright automation script
- observed UI behavior, screenshots, rendered DOM evidence, or browser console logs

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

Requires · Python
Requires · Playwright synchronous API and Chromium
Requires · optional scripts/with_server.py helper for local server lifecycle

Why it works

Activation is limited to tasks the skill actually covers.
Permissions, tools, and external effects are visible before execution.
Confirmation and the output format keep actions controllable.

Try next

Check the Web app testing result

# Verify the Web app testing outcome

## Objective
Check that the webapp-testing skill was used within scope and that its effects match the authorized request.

## Checks
- Compare the source and revision with the manifest.
- Separate local, browser, and external evidence.
- Report any permission or effect that was not disclosed.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

sha256:f701ccd98bf70fde21cd1638e5feb07fa563e85bef3479eb9a2f83fe518ff2c9

Verify in your agent

Confirm that Web app testing produced the right outcome

# Verify Web app testing in your agent

## Result to check
Verify the use of webapp-testing for the current bounded task.

## Failure signals
- The source or revision does not match the manifest.
- A permission or external effect was not disclosed.
- The output does not match the expected artifacts.
- The skill activated for a declared non-trigger.

## Checks
- Compare the SHA-256 of SKILL.md with sha256:51b7349e77ec63b7744a6f63647e7566a0b4d2e301121cc10e8c2113af6556a2.
- Confirm the permissions actually used and the observed effects.
- Verify artifacts with the narrowest available test.
- Separate local, browser, and external evidence in the report.

## Expected result
- native Python Playwright automation script
- observed UI behavior, screenshots, rendered DOM evidence, or browser console logs

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

Requires · Python
Requires · Playwright synchronous API and Chromium
Requires · optional scripts/with_server.py helper for local server lifecycle

Why it works

The check starts from the manifest and expected artifacts, not a general impression.
Observed permissions and effects are compared with what was disclosed.
Local, browser, and external evidence stay separate in the verdict.

Try next

Prepare the next Web app testing check

# Make the Web app testing check reusable

## Objective
Turn the successful checks into a bounded checklist for the next use of webapp-testing.

## Checks
- Keep only observable signals.
- Tie each permission to its expected effect.
- Add an explicit stop if the source or revision changes.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

sha256:95ff794874deb1f7a4190401e975ae8a5d83903b3332000f72138593890f0567

Pack digest: sha256:01522b4d0fe743448d5cb39f34f2aa3ac42b20ea88074df012ba71c09b56ce2b

Source provenance

Open the canonical source

Source revision: fa0fa64bdc967915dc8399e803be67759e1e62b8
Digest: sha256:51b7349e77ec63b7744a6f63647e7566a0b4d2e301121cc10e8c2113af6556a2

Risk profile

This is a risk profile, not a certification or a safety guarantee.

What can it read?

Present

It can read what the local app shows in the browser, including the page structure.

What can it create or change?

Present

It can create test scripts, save screenshots, and change the local test app while it runs.

Can it use the internet or send data?

Not evaluated

The published fields do not say whether this skill can use the internet or send data.

Can it use saved logins or a paid quota?

Not evaluated

The published fields do not say whether this skill can use saved logins or a paid quota.

Which action needs your approval?

Not evaluated

The published fields do not say which actions need your approval first.

When was the source verified, and has the snapshot changed since?

Present

The source was last verified on 2026-07-19. The published snapshot still matches that verification. This is not a live check of the upstream source.

Canonical source

https://github.com/anthropics/skills/blob/fa0fa64bdc967915dc8399e803be67759e1e62b8/skills/webapp-testing/SKILL.md

Source revision

fa0fa64bdc967915dc8399e803be67759e1e62b8

License

Apache-2.0

Verification date

2026-07-19

Source status

Verified

Change status

Snapshot consistent

The published snapshot still matches the last verification. This is not a live check of the upstream source.

Understand

Covered goals

test a local web application
verify UI behavior
capture reproducible browser evidence

Inputs → outputs

local application URL or static HTML file
user journey and expected behavior
server command and port when the application is not already running

native Python Playwright automation script
observed UI behavior, screenshots, rendered DOM evidence, or browser console logs

Choose

Verbatim from the English source

Permissions

write and execute scoped Python Playwright scripts
launch a local browser and read rendered application state
start and stop explicitly scoped local application servers
interact with and potentially mutate local test application state

External effects

local browser and optional application-server processes are started and stopped
Python scripts, screenshots, DOM captures, and logs can be written to disk
browser actions can mutate the local application's test state

Compatibility

local web applications in a Python environment with Playwright and Chromium

Required tools

Python
Playwright synchronous API and Chromium
optional scripts/with_server.py helper for local server lifecycle

Check permissions and confirm every external effect before using this skill.

# Use Web app testing in your agent ## Objective Use the existing webapp-testing skill only when it directly covers the requested task. ## Prerequisites - local application URL or static HTML file - user journey and expected behavior - server command and port when the application is not already running - Python - Playwright synchronous API and Chromium - optional scripts/with_server.py helper for local server lifecycle ## Permissions - write and execute scoped Python Playwright scripts - launch a local browser and read rendered application state - start and stop explicitly scoped local application servers - interact with and potentially mutate local test application state ## External effects - local browser and optional application-server processes are started and stopped - Python scripts, screenshots, DOM captures, and logs can be written to disk - browser actions can mutate the local application's test state ## Procedure - Open the canonical source pinned to revision fa0fa64bdc967915dc8399e803be67759e1e62b8. - Read the skill instructions before calling its tools. - Ask for confirmation before any paid, destructive, or remote effect not already authorized. - Run the procedure within the requested scope and retain useful evidence. ## When not to use - deploy an application - test a remote production mutation without authorization - replace unit tests with screenshots ## Expected result - native Python Playwright automation script - observed UI behavior, screenshots, rendered DOM evidence, or browser console logs ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.

# Verify the Web app testing outcome ## Objective Check that the webapp-testing skill was used within scope and that its effects match the authorized request. ## Checks - Compare the source and revision with the manifest. - Separate local, browser, and external evidence. - Report any permission or effect that was not disclosed. ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.

# Verify Web app testing in your agent ## Result to check Verify the use of webapp-testing for the current bounded task. ## Failure signals - The source or revision does not match the manifest. - A permission or external effect was not disclosed. - The output does not match the expected artifacts. - The skill activated for a declared non-trigger. ## Checks - Compare the SHA-256 of SKILL.md with sha256:51b7349e77ec63b7744a6f63647e7566a0b4d2e301121cc10e8c2113af6556a2. - Confirm the permissions actually used and the observed effects. - Verify artifacts with the narrowest available test. - Separate local, browser, and external evidence in the report. ## Expected result - native Python Playwright automation script - observed UI behavior, screenshots, rendered DOM evidence, or browser console logs ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.

# Make the Web app testing check reusable ## Objective Turn the successful checks into a bounded checklist for the next use of webapp-testing. ## Checks - Keep only observable signals. - Tie each permission to its expected effect. - Add an explicit stop if the source or revision changes. ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.