webwright Skill
Solve a user-specified web task code-as-action style by driving a local Playwright browser through one bash command at a time, saving screenshots and an action log into finalruns/run<id/, and visually verifying the result. Use when the user asks to automate a web task (search, filter, form-fill, multi-step flow, data e Published by microsoft in Webwright.
What is webwright Skill?
Solve a user-specified web task code-as-action style by driving a local Playwright browser through one bash command at a time, saving screenshots and an action log into finalruns/run<id/, and visually verifying the result. Use when the user asks to automate a web task (search, filter, form-fill, multi-step flow, data e Published by microsoft in Webwright. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Browser automation
- Data analysis
- Research
- Browser automation use cases
- Data analysis use cases
Technical details
- Install or run with Copy skill directory
When to use webwright Skill
- Use it for browser automation.
- Use it for data analysis.
- Use it for research.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/Webwright
- Skill file: skills/webwright/SKILL.md
What it does
Solve a user-specified web task code-as-action style by driving a local Playwright browser through one bash command at a time, saving screenshots and an action log into finalruns/run<id/, and visually verifying the result. Use when the user asks to automate a web task (search, filter, form-fill, multi-step flow, data e
Skill instructions
Webwright (Claude Code adaptation) You are the Webwright agent. Webwright is normally an LLM-driven loop that emits one JSON-wrapped bashcommand per turn against a local terminal + Playwright workspace. In Claude Code, you replace that loop directly: use the Bash tool the same way the bashcommand field is used in Webwright/src/webwright/config/base.yaml. You do NOT need to wrap your output in JSON — that constraint only existed because the original harness parsed model output. This skill keeps the workspace contract (plan.md, finalruns/run<id/ folders, instrumented finalscript.py, screenshots, action log) but replaces the OpenAI-backed imageqa and selfreflection tools with your own native abilities: you read PNGs with Read and verify success against plan.md yourself. No OPENAIAPIKEY or other model API keys required. Modes - Default (one-shot). finalscript.py solves the task for the literal values the user provided. Triggered by a plain prompt or by /webwright:run <task. - CLI tool (par
Explore related resources
Frequently asked questions
What is webwright?
webwright is a open-source AI agent skill with Copy skill directory. Solve a user-specified web task code-as-action style by driving a local Playwright browser through one bash command at a time, saving screenshots and an action log into finalruns/run<id/, and visually.
Who is webwright best for?
webwright is best for reusing agent instructions, scripts, and references, browser automation workflows, data analysis workflows, research workflows.
How do I install webwright?
Install or run webwright using Copy skill directory. Check webwright for the latest setup command.
Is webwright actively maintained?
webwright may need a closer maintenance check before production use.
Auto-fetched from GitHub.
