playwriter
Debug Live Chrome Tabs with Playwriter
Frontend issues are difficult to diagnose when they only appear in a user's active browser state. This skill inspects and automates that tab through Playwriter.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "playwriter" from https://skillstore.io/skills/brianlovin-playwriter.md and its manifest at https://skillstore.io/api/skills/brianlovin-playwriter/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "playwriter". Report the active page URL and title.
Expected outcome:
Connected to session 1. The active page is the account settings screen at the reported application URL.
Using "playwriter". Inspect the open options list and summarize its state.
Expected outcome:
- The list contains six visible options.
- The first option is selected.
- No loading or error message is visible.
Using "playwriter". Reproduce the save failure and capture evidence.
Expected outcome:
The Save action was confirmed before execution. The form remained open, and the console recorded a failed request at the observed timestamp.
Security Audit
High RiskAll 19 backtick alerts are Markdown formatting rather than Ruby or shell backtick execution, and the hardcoded URL is a documentation link. Semantic review found high-risk live-tab script access and medium-risk unpinned package execution through npx.
Confirmed security concerns (2)
Risk Factors
⚙️ External commands (19)
🌐 Network access (1)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/brianlovin-playwriter/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/brianlovin-playwriter?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/brianlovin-playwriter?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/brianlovin-playwriter/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/brianlovin-playwriter.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
brianlovin. (2026). playwriter security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/brianlovin-playwriter/audits/1BibTeX citation
@techreport{brianlovin-brianlovin-playwriter-2026,
author = {brianlovin},
title = {playwriter security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/brianlovin-playwriter/audits/1},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "playwriter security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "brianlovin"
date-released: "2026-08-21"
url: "https://skillstore.io/skills/brianlovin-playwriter/audits/1"
identifiers:
- type: other
value: "skillstore:brianlovin-playwriter:audit:1"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Reproduce a Frontend Defect
Inspect the live page, repeat the failing interaction, and record observed state changes.
Verify an Interactive Workflow
Exercise controls in an open application and confirm visible results without launching another browser.
Collect Browser Evidence
Capture page structure, console output, and timestamps for a support investigation.
Try These Prompts
Attach to the active Chrome tab. Report its URL and title without changing the page.
Attach to the active tab and collect an accessibility snapshot. Summarize the main controls and visible status messages.
Reproduce this issue in the active tab: [steps]. Confirm before mutations, capture console output, and report each observed state transition.
Inspect [component] in the active tab. Correlate accessibility data, console messages, and evaluated state, then identify the likely failure point.
Best Practices
- Confirm the session URL and title before inspecting or changing the page.
- Prefer read-only inspection and request confirmation before live mutations.
- Redact tokens, personal data, and private content from summaries.
Avoid
- Do not run arbitrary evaluation code without a defined debugging purpose.
- Do not install an unpinned package automatically in a sensitive environment.
- Do not perform destructive actions without explicit user confirmation.
Frequently Asked Questions
Does this skill launch a new browser?
What must be installed?
Can it inspect page structure?
Can it change the current page?
How does it avoid using the wrong tab?
How should sensitive data be handled?
Developer Details
Author
brianlovinLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
5772c9720ecbe72ed40cb7ea208d652c21c388a2
Maintenance freshness
8/22/2026
Usage
0 downloads · 0 views
File structure