kentoshimizu/sw-agent-skills/playwright
Claude Code and agent skill by kentoshimizu/sw-agent-skills
- community
Checking that the SKILL.md file is still in the repository.
Playwright browser verification workflow for user-journey evidence with deterministic replay artifacts. Use when web flows require executable browser evidence (trace/screenshot/replay logs) before merge or release; do not use for pure unit/API-only checks.
Install
npx vskill@latest install kentoshimizu/sw-agent-skills/playwrightSKILL.md
The same SKILL.md was published earlier as kentoshimizu/sw-agent-skills/playwright.
Playwright
Overview
Use this skill to validate browser-level behavior with reproducible artifacts that engineers can replay exactly.
Scope Boundaries
- Use this skill when the task matches the trigger condition described in
description. - Do not use this skill when the primary task falls outside this skill's domain.
Shared References
- Trigger examples:
references/trigger-and-examples.md- Replay determinism rules:
references/replay-determinism-rules.md
Templates And Assets
- Test plan template:
assets/playwright-test-plan-template.md- Command profile template:
assets/playwright-command-profile-template.md- Artifact checklist:
assets/playwright-artifact-checklist.md
Inputs To Gather
- Critical flows and acceptance expectations.
- Target browsers/devices and environment constraints.
- Auth/test-data setup and security constraints.
- Required artifacts for failure triage.
Deliverables
- Browser test scenario plan.
- Local-fast and CI-full command profiles.
- Trace/screenshot/video evidence for failures.
- Residual flakiness and ownership log.
Workflow
- Define scenarios with
assets/playwright-test-plan-template.md. - Define command profiles in
assets/playwright-command-profile-template.md. - Apply deterministic execution rules from
references/replay-determinism-rules.md. - Execute and capture artifacts.
- Validate evidence completeness via
assets/playwright-artifact-checklist.md.
Quality Standard
- Browser evidence is replayable without hidden steps.
- Artifacts map to explicit scenarios and failures.
- Critical flows include happy/edge/failure coverage.
Failure Conditions
- Stop when prerequisites for deterministic replay are missing.
- Stop when artifacts cannot reproduce observed failures.
- Escalate when external instability prevents reliable browser evidence.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/playwright/SKILL.md
Popularity
- Repository stars
- 5
- 7-day trend score
- 9
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 3 May 2026, 6 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/kentoshimizu/sw-agent-skills/playwright)