Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/aitechnerd-browse
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, devops, data, marketing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/browse
What's inside
- Skill name
browse- Description
- General-purpose browser automation using Playwright CLI. Navigate pages, interact with elements via accessibility refs, take screenshots, manage sessions, mock network requests. Use for ad-hoc browsing, system automations, deploy verification, form filling, data extraction. Much faster and cheaper than screenshot-based approaches — uses YAML accessibility snapshots.
- License
- MIT
- Instructions
- 238 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (1)
- SKILL.md
SKILL.md (first lines)
# Browse: Browser Automation with Playwright CLI
General-purpose browser automation via `playwright-cli`. Uses accessibility tree snapshots
(YAML with element refs) instead of screenshots for fast, cheap interaction.
## Core Workflow
```
open URL -> snapshot -> interact (click/fill/etc) -> snapshot -> ... -> close
```
Every interaction follows this loop:
1. **Open** a page: `playwright-cli open https://example.com`
2. **Snapshot** to see the page structure: `playwright-cli snapshot`
3. **Read the snapshot** YAML to find element refs (e8, e21, etc.)
4. **Interact** using refs: `playwright-cli click e8` or `playwright-cli fill e12 "hello"`
5. **Snapshot again** to verify the result
6. **Close** when done: `playwright-cli close`
## Element Refs
Snapshots produce YAML files in `.playwright-cli/` with an accessibility tree. Each
interactive element gets a ref like `e8`, `e21`, `e134`. Use these refs for all interactions.
```bash
# Take snapshot — returns path to YAML file
playwright-cli snapshot
# Read the YAML to find elements
# (only read when you need to find refs — don't read after every action)
```
Example snapshot excerpt:
```yaml
- button "Sign In" [ref=e8]
- textbox "Email" [ref=e12]
- textbox "Password" [ref=e14]
- link "Forgot password?" [ref=e16]
```
Use refs directly: `playwright-cli click e8`, `playwright-cli fill e12 "user@example.com"`
## Common Patterns
### Navigation
```bash
playwright-cli open https://example.com # Open URL in new browser
playwright-cli goto https://example.com/about # Navigate existing browser
playwright-cli go-back # Browser back
playwright-cli go-forward # Browser forward
playwright-cli reload # Refresh page
```
### Form Filling
```bash
playwright-cli snapshot # Find form element refs
playwright-cli fill e12 "user@example.com" # Fill text input
playwright-cli fill e14 "password123" # Fill password
playwright-cli select e18 "option-value" # Select dropdown
playwright-cli check e20 # Check checkbox
playwright-cli uncheck e20 # Uncheck checkbox
playwright-cli click e8 # Submit button
playwright-cli snapshot # Verify result
```
### Data Extraction
```bash
playwright-cli snapshot # Capture page structure
# Read the YAML — all visible text content is in the accessibility tree
# For dynamic data, use eval:
playwright-cli eval "document.querySelector('.price').textContent"
```
### Snapshot Diff (Before/After Evidence)
Capture what changed in the accessibility tree after an action:
```bash
# 1. Take "before" snapshot
playwright-cli snapshot
# Note the file path from output, e.g. .playwright-cli/page-...-before.yml
# 2. Perform the action
playwright-cli click e8
# 3. Take "after" snapshot
playwright-cli snapshot
# Note the file path, e.g. .playwright-cli/page-...-after.yml
# 4. Diff the two snapshots
diff .playwright-cli/page-*-before.yml .playwright-cli/page-*-after.yml
```
This shows exactly what appeared, disappeared, or changed in the DOM — much more
precise than comparing screenshots. Use for:
- Verifying a button click produced the expected state change
- Confirming form submission updated the page
- Detecting unintended side effects (elements that changed when they shouldn't)
- Before/after evidence in QA reports
**Tip:** For named diffs, copy snapshots to meaningful filenames:
```bash
playwright-cli snapshot
cp .playwright-cli/page-*.yml /tmp/before-login.yml
playwright-cli click e15 # submit login
playwright-cli snapshot
cp .playwright-cli/page-*.yml /tmp/after-login.yml
diff /tmp/before-login.yml /tmp/after-login.yml
```
### Screenshots and Visual Verification
```bash
playwright-cli screenshot # Full page screenshot
playwright-cli screenshot e42 # Screenshot specific elementFrom aitechnerd/ai-dev-team, MIT.
More from aitechnerd/ai-dev-team
- 0.433score
git-mastery
aitechnerd
Git workflows, commit conventions, branching strategies, and safe operations.
SkillDFreshness: D★ 1Claude Code +9 - 0.433score
qa-browser
aitechnerd
Systematically QA test a web application using Playwright CLI.
SkillDFreshness: D★ 1Claude Code +9 - 0.428score
hipaa
aitechnerd
HIPAA compliance review for healthcare software.
SkillDFreshness: D★ 1Claude Code +9 - 0.428score
eval
aitechnerd
Evaluate and improve AI Dev Team skills.
SkillDFreshness: D★ 1Claude Code +9 - 0.425score
scan
aitechnerd
Run all available security and quality scanners on the codebase.
SkillDFreshness: D★ 1Claude Code +9 - 0.425score
build-phase
aitechnerd
Implement phases from the active feature's technical plan.
SkillDFreshness: D★ 1Claude Code +9 - 0.425score
qa-check
aitechnerd
Quick QA check on current changes without the full pipeline.
SkillDFreshness: D★ 1Claude Code +9 - 0.425score
retro
aitechnerd
Weekly engineering retrospective.
SkillDFreshness: D★ 1Claude Code +9 - 0.425score
revert
aitechnerd
Revert a specific phase or the entire feature by logical unit.
SkillDFreshness: D★ 1Claude Code +9 - 0.425score
review
aitechnerd
Fix-first review pipeline.
SkillDFreshness: D★ 1Claude Code +9 - 0.425score
health
aitechnerd
Run code health checks: full assessment, targeted refactoring, or dependency updates.
SkillDFreshness: D★ 1Claude Code +9 - 0.422score
approve-plan
aitechnerd
Manually approve the active feature's technical plan.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 22, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/aitechnerd/ai-dev-team
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from aitechnerd
- 0.433score
qa-browser
aitechnerd
Systematically QA test a web application using Playwright CLI.
SkillDFreshness: D★ 1Claude Code +9 - 0.433score
git-mastery
aitechnerd
Git workflows, commit conventions, branching strategies, and safe operations.
SkillDFreshness: D★ 1Claude Code +9 - 0.428score
hipaa
aitechnerd
HIPAA compliance review for healthcare software.
SkillDFreshness: D★ 1Claude Code +9 - 0.428score
eval
aitechnerd
Evaluate and improve AI Dev Team skills.
SkillDFreshness: D★ 1Claude Code +9 - 0.425score
build-phase
aitechnerd
Implement phases from the active feature's technical plan.
SkillDFreshness: D★ 1Claude Code +9 - 0.425score
health
aitechnerd
Run code health checks: full assessment, targeted refactoring, or dependency updates.
SkillDFreshness: D★ 1Claude Code +9
Cite this page
browse skill. Agent Mart. https://agentmart.dev/skills/aitechnerd-browse (last updated 2026-10-24)