core

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger

Before running any agent-browser command, or when the user needs to interact with a website, fill a form, click, extract data, screenshot, log in, test a web app, or automate browser tasks.

Working Mechanism

Teaches the snapshot-and-ref loop: open → snapshot -i → act on @eN refs → re-snapshot after page changes.
Covers navigation, element interaction (click/fill/type/select), text extraction, screenshots, tab management, auth, waiting, and parallel sessions.
Provides MCP and eve agent integration, plus reference docs for specialized cases.

Result

A reliable browser-automation foundation: agents act on compact accessibility-tree refs in low token cost, avoid stale-ref errors, and handle common web tasks with reproducible commands.

Use Cases

Two Typical Use Cases

Scenario 01

Automate authenticated dashboard scraping

A developer wants to automate checking a dashboard that requires login. They read core first, learn the snapshot-ref loop and auth handling from references/authentication.md, then script open → fill credentials → wait → snapshot → extract data. This avoids Playwright boilerplate and keeps token usage low, delivering a repeatable login-and-scrape flow.

Scenario 02

Low-token smoke test via screenshots

A QA engineer needs to click through a web app and capture screenshots of each step. Using core's quickstart and snapshot-ref commands, they drive the app via @eN refs, take screenshots, and manage tabs without a full browser framework. The result is a fast, low-token smoke test that finds UI breakages early.

Skill Relationships

Which Skills I Use · Which Skills Use Me

Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.

Tier 1 · These Skills Use Me

Tier 2 · Current Skill

coreCli Manual

Tier 3 · I Use These Skills

No explicit dependency on other Skills

Full Relationship Graph

Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.

Skill File

SKILL.md

Open in GitHub ↗

SKILL.mdLoading from GitHub…

Skill Composition

Open in GitHub ↗

SKILL.md7.7%
references69.2%
other23.1%

▸skills/core/
▸root
- ·SKILL.md
- ▸references
  - ·authentication.md
  - ·commands.md
  - ·profiling.md
  - ·proxy-support.md
  - ·session-management.md
  - ·snapshot-refs.md
  - ·trust-boundaries.md
  - ·video-recording.md
  - ·webgpu.md
- ▸templates
  - ·authenticated-session.sh
  - ·capture-workflow.sh
  - ·form-automation.sh

Per the Agent Skills spec, SKILL.md is the only required file. The colored bars classify the rest into the three spec-aligned optional directories (scripts / references / assets) and an 'other' bucket. The full directory tree is below.

Related in Skillset

You May Also Need These Skills

electron

Automate any Electron desktop app (Slack, VS Code, etc.) via agent-browser and Chrome DevTools Protocol. Launch app with remote debugging port, connect, snapshot and interact. Enables desktop UI automation, testing, data extraction and multi-app control without native code.

Cli Manual · Workflow

agent-browser

agent-browser is a fast Rust CLI for AI agents to automate browsers via Chrome CDP with accessibility snapshots. It handles web navigation, form filling, clicking, screenshots, data extraction, and testing, plus Electron/Slack/cloud browser tasks. Value: reliable, version-matched, agent-agnostic web automation without Playwright/Puppeteer.

Cli Manual

vercel-sandbox

Run agent-browser + headless Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Uses on-demand Linux VMs with Chromium and SDK helpers to run commands like screenshot, snapshot, and form fill. Delivers isolated, persistent, binary-limit-free browser automation with sub-second startup via snapshots.

Workflow

slack

Use browser automation (agent-browser) to interact with Slack workspaces: check unreads, send messages, search, extract data. Delivers unread reports, sent messages, and evidence screenshots without Slack API or tokens.

Workflow

/core

When It Triggers · How It Works · What It Produces

Trigger

Working Mechanism

Result

Two Typical Use Cases

Automate authenticated dashboard scraping

Low-token smoke test via screenshots

Which Skills I Use · Which Skills Use Me

Full Relationship Graph

SKILL.md

Skill Composition

You May Also Need These Skills

electron

agent-browser

vercel-sandbox

slack

When It Triggers · How It Works · What It Produces

Trigger

Working Mechanism

Result

Two Typical Use Cases

Automate authenticated dashboard scraping

Low-token smoke test via screenshots

Which Skills I Use · Which Skills Use Me

Full Relationship Graph

SKILL.md

Skill Composition

You May Also Need These Skills

electron

agent-browser

vercel-sandbox

slack