capture
/capture
Browser automation and UI validation via the capture CLI. Interact with pages using accessibility-driven click, type, screenshot, a11y tree, JS exec, and HAR recording over CDP. Use when validating UI state, testing features in the browser, or manipulating a running web app.
- Author
- CaptainCrouton89 ↗
- Repository
- crouton-kit ↗
- Licence
- GPL-3.0
- Last repository change
- 02.10.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 02.10.2026, without references to retired models or APIs.
GPL-3.0, otwarta.
What it does and when to use it
Browser automation and UI validation via the capture CLI. Interact with pages using accessibility-driven click, type, screenshot, a11y tree, JS exec, and HAR recording over CDP. Use when validating UI state, testing features in the browser, or manipulating a running web app.
Original author description
Browser automation and UI validation via the capture CLI. Interact with pages using accessibility-driven click, type, screenshot, a11y tree, JS exec, and HAR recording over CDP. Use when validating UI state, testing features in the browser, or manipulating a running web app.
How it works
- Session Basics
- Validation Pattern
- Interaction Tips
SKILL.md preview
--- name: capture description: Browser automation and UI validation via the capture CLI. Interact with pages using accessibility-driven click, type, screenshot, a11y tree, JS exec, and HAR recording over CDP. Use when validating UI state, testing features in the browser, or manipulating a running web app. allowed-tools: Bash(capture:*), Read, Glob, Grep --- # Capture — Browser Automation Skill Browser automation via CDP for UI validation. For the full command reference, see [cli-reference.md](cli-reference.md). ## Session Basics 1. `capture session start --url <url>` — open a tab and start recording 2. Interact: `screenshot`, `click`, `type`, `a11y`, `exec`, `navigate` 3. `capture session stop <id>` — bundle artifacts; `capture session view <id>` to inspect Session context auto-fills `--target` and `--har` — no manual flag threading needed. **Target selection:** If the user hasn't specified which app or browser to target, ask before starting. Don't assume Chrome, a specific port, or a running tab — run `capture detect` to see what's available and confirm with the user when ambiguous. ## Validation Pattern When validating a UI feature: 1. Start a session targeting the page under test 2. Use `a11y --interactive` to understand what's on the page 3. Interact via `click` and `type` using accessible names (not selectors) 4. Take screenshots at key states 5. Use `exec` to check DOM or JS state when a11y isn't sufficient 6. Use `har read` to verify network requests if relevant (supports `--filter-url`, `--filter-status`, `--filter-method`, `--limit`; ID optional in an active session) 7. Stop the session and report pass/fail with evidence **HAR caveat:** the session HAR is populated by the commands that run — most reliably `navigate`. `click`/`type` capture the traffic that fires inside their settle window, but cross-navigation traffic after the frame changes is lossy. For continuous "click around" capture, run `capture record --duration N` in parallel. ## Interaction Tips - Always prefer `click "Name"` over `exec` with selectors — a11y names are stable - If `click` reports multiple matches, add `--role` to disambiguate - Run `a11y --interactive` before interacting to see available elements - `type --into "Field Name"` clicks the field first, then types — no separate click needed - After interactions, screenshot to capture the resulting state
Files in this package (2)
- SKILL.md 2 KB
- cli-reference.md 3 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · CaptainCrouton89/crouton-kit | 90 | GPL-3.0 |
| wenlan-app/wenlan | 100 | Apache-2.0 |
| wenlan-app/wenlan | 100 | Apache-2.0 |
| optimiziramsi/skills | 100 | MIT |
| Kolibee-GmbH/m2b | 100 | MIT |
| davepoon/buildwithclaude | 100 | MIT |
| aw3-technology/vibehub-plugins | 100 | MIT |
| anurag-rivora/product-brain-starter | 100 | MIT |
| borghei/Claude-Skills | 100 | MIT |
Identical content appears in 1 other GitHub folders. We show one copy with the highest score.
Database snapshot: 13.11.2026 · package version 4c6a057ed070 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100agent-browser
Headless browser automation CLI optimized for AI agents: drives a real browser via accessibility-tree snapshots and @e1-style refs for ~93% less context than raw DOM tools. Use whenever a task needs to interact with a live web page: click, fill forms, log in, extract text or… - 100browser
Drive a browser via CDP — navigate, click, type, screenshot. Profiles persist login state across sessions, so agents log in once and stay authenticated. Triggers on: 'automate a website', 'browser automation', 'click', 'screenshot', 'scrape', 'log in', 'fill form'. - 100agent-browser
Use the agent-browser CLI to exercise web interfaces, inspect rendered accessibility state, verify interactions, and capture screenshots. Use for browser-based UI testing and evidence collection. Do not use as a substitute for deterministic Playwright coverage when an automated… - 100agent-browser
Browser automation CLI for AI agents; use for web tasks - navigate, click, fill forms, screenshot, scrape, test web/Electron apps. - 100agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a… - 100agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a…