Agent skill

Playwriter

by brianlovin in brianlovin/agent-config

Control the user's currently open Chrome tab through the Playwriter CLI (no new browser launch).

No licenceAuto-check passed

Install Playwriter

skills CLI
$ npx skills add brianlovin/agent-config --skill playwriter -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install brianlovin/agent-config playwriter --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/brianlovin/agent-config.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/playwriter .claude/skills/playwriter && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
playwriter
GitHub stars
377
Used in
1 other repo
Token cost
~594 tokens
SKILL.md length
172 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
None found

At a glance

Control the user's currently open Chrome tab through the Playwriter CLI (no new browser launch).

  • Works in 4 steps: Ensure the Playwriter extension is… → Ensure CLI is available → Create/attach a session → …
  • You need to inspect live UI state
  • SKILL.md covers Quick Start, Core Workflow, Useful Commands and Troubleshooting, plus 1 more section
  • Calls npx

What it does

Playwriter is an agent skill from brianlovin/agent-config. Control the user's currently open Chrome tab through the Playwriter CLI (no new browser launch). Use when you need to inspect live UI state, run scripted browser actions, capture console output, or reproduce frontend issues directly in the user's tab.

Its SKILL.md is about 590 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: My coding agent config.

When your agent uses it

  • You need to inspect live UI state
  • Run scripted browser actions
  • Capture console output
  • Reproduce frontend issues directly in the users tab

Example prompts

  • “/playwriter”

Requirements

  • Node.js

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Ensure the Playwriter extension is enabled (green) on the target tab.
  2. Ensure CLI is available
  3. Create/attach a session
  4. Run commands against that session

What it can do on your machine

Read from SKILL.md and the folder at commit 1a9819e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • playwriter.dev

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Playwriter loads about 594 tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 172 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~594

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 172 words (~594 tokens).

“Use this skill to drive the user's active Chrome tab via Playwriter.”

— opening of SKILL.md by brianlovin
name
playwriter

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in skills/playwriter of brianlovin/agent-config.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 1a9819e

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in brianlovin/agent-config, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Playwriter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Playwriter compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Playwriter this skillbrianlovin/agent-config3771 repos~594Automated safety check: PassNone
Playwritermikeyobrien/ralph-orchestrator3.2k—~716Automated safety check: WarnMIT
Tabs Accessibilitythedaviddias/Front-End-Checklist74k—~409Automated safety check: PassMIT
Claude In Chromeasgeirtj/system_prompts_leaks69k—~1.2kAutomated safety check: PassCC0-1.0
Chrome Devtoolsgithub/awesome-copilot40k2 repos~1kAutomated safety check: PassMIT
Warp Tab Config Editorwarpdotdev/warp65k1 repos~291Automated safety check: PassAGPL-3.0

Similar skills

  • Playwriter

    mikeyobrien/ralph-orchestrator

    Browser automation via Playwriter (remorses) using persistent Chrome sessions and the full Playwright Page API.

    3.2k GitHub stars~716 tokensUpdated 4 days ago
    Productivity & AutomationAuto-check: warnings
  • Tabs Accessibility

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Make tabs keyboard navigable.

    74k GitHub stars~409 tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • Claude In Chrome

    asgeirtj/system_prompts_leaks

    Automates your Chrome browser to interact with web pages - clicking elements, filling forms, capturing screenshots, reading console logs, and navigating sites.

    69k GitHub stars~1.2k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Chrome Devtools

    github/awesome-copilot

    Official

    Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP.

    40k GitHub starsUsed in 2 repos~1k tokens
    Testing & QAAuto-check passed
  • Warp Tab Config Editor

    warpdotdev/warp

    Edits an existing Warp tab config TOML file in place from a plain-language request, keeping its structure and checking it against the tab-configs schema.

    65k GitHub starsUsed in 1 repo~291 tokens
    DevelopmentAuto-check passed
  • Reference for Warp tab config TOML files: where they live, how the pane list is structured, and what to ask before creating or editing one.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Productivity & AutomationAuto-check passed

More from brianlovin/agent-config

All 12 skills in this repo
  • Chrome Webstore Release Blueprint

    brianlovin/agent-config

    Guide a user end-to-end through setting up Chrome Web Store API release automation in any repository.

    377 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check: notes
  • Electron Wrapper

    brianlovin/agent-config

    Wrap a Bun web app into an Electron desktop app with native window management, auto-updates, code signing, and CI/CD distribution.

    377 GitHub stars~2.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Favicon

    brianlovin/agent-config

    Generate a complete set of favicons from a source image and update HTML.

    377 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check: notes
  • Rams

    brianlovin/agent-config

    Run accessibility and visual design review on components. An agent skill from brianlovin/agent-config.

    377 GitHub starsUsed in 1 repo~801 tokens
    Auto-check passed
  • Reclaude

    brianlovin/agent-config

    Refactor CLAUDE.md files to follow progressive disclosure principles.

    377 GitHub starsUsed in 1 repo~981 tokens
    Auto-check passed
  • Bun

    brianlovin/agent-config

    Use Bun instead of Node.js, npm, pnpm, or vite. An agent skill from brianlovin/agent-config.

    377 GitHub starsUsed in 1 repo~484 tokens
    Auto-check: notes

Questions about Playwriter

What does Playwriter do?

Control the user's currently open Chrome tab through the Playwriter CLI (no new browser launch). Playwriter is an agent skill from brianlovin/agent-config. Control the user's currently open Chrome tab through the Playwriter CLI (no new browser launch).

When should I use Playwriter?

Playwriter fits situations like: you need to inspect live UI state; run scripted browser actions; capture console output; reproduce frontend issues directly in the users tab.

How do I install Playwriter in Claude Code?

Run `npx skills add brianlovin/agent-config --skill playwriter -a claude-code`. Or copy the skill folder (skills/playwriter in brianlovin/agent-config) into .claude/skills/playwriter in your project. Claude Code loads it when a task matches its description.

How do I install Playwriter in Codex?

Run `npx skills add brianlovin/agent-config --skill playwriter -a codex`. Or copy the skill folder (skills/playwriter in brianlovin/agent-config) into .agents/skills/playwriter in your project. Codex loads it when a task matches its description.

Can I use Playwriter in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add brianlovin/agent-config --skill playwriter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/playwriter, .gemini/skills/playwriter, .github/skills/playwriter and .opencode/skills/playwriter in your project.

What does Playwriter need to run?

Going by SKILL.md and its folder, Playwriter needs the command-line tools its instructions call (npx). Our summary lists: Node.js.

Does Playwriter access the network?

SKILL.md names 1 domain. As links in the text: playwriter.dev. This is read from the text; nothing was executed.

Is Playwriter safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Playwriter use?

No licence was found for Playwriter or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Playwriter use?

About 594 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Playwriter?

Skills that share tags, products or a category with Playwriter: Playwriter (mikeyobrien/ralph-orchestrator, 3.2k stars), Tabs Accessibility (thedaviddias/Front-End-Checklist, 74k stars), Claude In Chrome (asgeirtj/system_prompts_leaks, 69k stars) and Chrome Devtools (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Playwriter?

brianlovin (a GitHub user) maintains it in brianlovin/agent-config, which has 377 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on March 25, 2026.

Source: brianlovin/agent-config on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.