playwright-cli
Browse the web using playwright-cli connected to your running Edge browser via the MCP Bridge extension. Use when the user asks to "open a webpage", "browse to", "take a screenshot", "read this page", "navigate to", "check this site", or needs to interact with web pages for research and exploration.
What this skill does
# Browser Automation with playwright-cli (Extension Mode)
## Hard Rules
1. **NEVER launch a new browser.** Every `open` command MUST include `--extension --browser=msedge`.
2. **NEVER use MCP.** This skill uses the CLI only. The MCP Bridge extension is just the transport layer.
3. **ALWAYS load the extension token** from `~/.copilot/skills/.env` before the first playwright-cli command.
4. **Gitignore snapshots.** Before first use, check the repo's `.gitignore` for `.playwright-cli/`. If missing, append it and inform the user. The CLI writes snapshot files to this folder in the current working directory.
## Phase 0: Load Token and Config
Before running any playwright-cli command, load the extension token:
```powershell
# Load token from .env
$envFile = Join-Path $HOME ".copilot" "skills" ".env"
if (Test-Path $envFile) {
Get-Content $envFile | ForEach-Object {
if ($_ -match '^\s*([^#][^=]+)=(.*)$') {
[System.Environment]::SetEnvironmentVariable($Matches[1].Trim(), $Matches[2].Trim(), 'Process')
}
}
} else {
Write-Error "Missing ~/.copilot/skills/.env with PLAYWRIGHT_MCP_EXTENSION_TOKEN"
}
```
Verify the token is set:
```powershell
if (-not $env:PLAYWRIGHT_MCP_EXTENSION_TOKEN) {
Write-Error "PLAYWRIGHT_MCP_EXTENSION_TOKEN not set. Check ~/.copilot/skills/.env"
}
```
### Internal Sites Config
Load `playwright-cli/config.json` (gitignored) which maps internal site URLs to keywords. When the user's request matches keywords for a site, navigate there automatically.
```powershell
$configFile = Join-Path $HOME ".copilot" "skills" "playwright-cli" "config.json"
if (Test-Path $configFile) {
$sites = (Get-Content $configFile -Raw | ConvertFrom-Json).sites
}
```
## Phase 1: Connect to Edge Browser
```bash
playwright-cli open --extension --browser=msedge
```
If `playwright-cli` is not found:
```bash
npx @playwright/cli@latest open --extension --browser=msedge
```
This connects to your running Edge browser via the MCP Bridge extension. It does NOT launch a new browser.
## Commands
### Navigation
```bash
playwright-cli goto <url>
playwright-cli go-back
playwright-cli go-forward
playwright-cli reload
```
### Reading Pages
```bash
playwright-cli snapshot # accessibility tree with element refs
playwright-cli snapshot --filename=page.yml # save to specific file
playwright-cli screenshot # capture visible page
playwright-cli screenshot --filename=f.png # save with specific name
playwright-cli screenshot <ref> # screenshot a specific element
```
### Interacting
```bash
playwright-cli click <ref> # click an element by ref
playwright-cli type <text> # type text into focused element
playwright-cli fill <ref> <text> # fill a specific input
playwright-cli hover <ref> # hover over element
playwright-cli select <ref> <val> # select dropdown option
playwright-cli check <ref> # check a checkbox
playwright-cli uncheck <ref> # uncheck a checkbox
playwright-cli press <key> # press a key (Enter, ArrowDown, etc.)
```
### Tabs
```bash
playwright-cli tab-list # list all tabs
playwright-cli tab-new [url] # open a new tab
playwright-cli tab-select <index> # switch to tab by index
playwright-cli tab-close [index] # close a tab
```
### JavaScript
```bash
playwright-cli eval "document.title"
playwright-cli eval "el => el.textContent" <ref>
```
### Session Management
```bash
playwright-cli list # list active sessions
playwright-cli close # close the connection
playwright-cli close-all # close all sessions
```
## Snapshots
After each command, playwright-cli returns a snapshot of the page state. Snapshots contain element refs (e.g., `e1`, `e5`, `e12`) that you use with `click`, `fill`, `hover`, etc.
```bash
> playwright-cli goto https://example.com
### Page
- Page URL: https://example.com/
- Page Title: Example Domain
### Snapshot
[Snapshot](.playwright-cli/page-2026-02-14T19-22-42-679Z.yml)
```
Use `playwright-cli snapshot` to take one on demand.
## Example: Research a Web Page
```bash
playwright-cli open --extension --browser=msedge
playwright-cli goto https://example.com/article
playwright-cli snapshot
# Read the snapshot to understand page structure
playwright-cli screenshot --filename=article.png
playwright-cli close
```
## Example: Fill a Form
```bash
playwright-cli open --extension --browser=msedge
playwright-cli goto https://example.com/form
playwright-cli snapshot
playwright-cli fill e1 "[email protected]"
playwright-cli fill e2 "some text"
playwright-cli click e3
playwright-cli snapshot
playwright-cli close
```
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.