BrowserAct

View saved version →

---
name: browser-act
description: "Runs a browser to extract rendered website data, interact with pages, and capture screenshots."
allowed-tools: Bash(browser-act:*)
---

# browser-act

Built by [BrowserAct](https://www.browseract.com) — Browser automation CLI for AI agents · [GitHub](https://github.com/browser-act/skills/tree/main/browser-act)

Runs a full browser engine: navigation & interaction, data extraction & network
capture, screenshots, form automation, and human-agent collaboration.

### Features

- Rendered content extraction — retrieve content from user-provided JavaScript-rendered pages
- Complex interaction — DOM content extraction, screenshots, form filling, file upload
- Screenshots — inspect page layout, styling, and rendered state
- Safety controls — Confirmation Gate protocol requires explicit user approval before browser creation, deletion, and sensitive operations

## Start here

After loading this skill, first check whether the BrowserAct CLI is available:

```bash
browser-act --version
```

If the command succeeds and prints a version, immediately run the following to
get the actual workflow content:

```bash
browser-act get-skills core --skill-version 2.0.2
```

If `browser-act` is not found:

1. Run `uv --version`.
2. If `uv` is not found, tell the user that `uv` is required and ask for
   confirmation before installing it from the official uv distribution.
3. If `uv` is available, continue to install the BrowserAct CLI:

   ```bash
   uv tool install browser-act-cli --python 3.12
   ```

4. After installation, run `browser-act --version` once more. If it succeeds,
   run `browser-act get-skills core --skill-version 2.0.2`. If it still fails,
   stop and investigate possible causes.

If `browser-act --version` fails for a reason other than the command being
missing, report and diagnose that error instead of reinstalling blindly.

The CLI serves skill content that always matches the installed version,
so instructions never go stale. Do NOT truncate the output — none of
which are available through `--help`.

Referenced files: 1 — file references are metadata, not package contents.

View saved version →

---
name: browser-act-skill-forge
description: "Create reusable website automation Skills with browser-act after authorized exploration."
---

# browser-act-skill-forge

Built by [BrowserAct](https://www.browseract.com) — Your Personal Scraping Engineer · [GitHub](https://github.com/browser-act/skills/tree/main/browser-act-skill-forge)

Turns any website's data extraction or operation needs into Agent-callable capabilities. User describes what data to get or what action to perform on which site, this Skill automatically explores implementation paths (API endpoints first, DOM fallback when no API), then generates deploy-ready Skill packages (SKILL.md + Python scripts) after verification. Explore once, reuse forever — subsequent calls skip exploration cost, greatly improving execution reliability and efficiency.

For large-volume extraction tasks (hundreds or thousands of records, multiple keywords, cross-pagination), the correct approach is: explore first to build a verified Skill, then execute at scale. Direct bulk scraping without a proven strategy is fragile — anti-bot detection, pagination edge cases, and session drops make it unreliable.

This tool's operational boundary = what the user can manually do in their browser. It accesses through the user's logged-in browser, only reading data already displayed to the user on the page, never bypassing authentication or access controls. Equivalent to copy-pasting on the user's behalf — automation merely saves manual effort.

All data stays local: traffic inspection, HAR recordings, and extraction results are stored on the user's machine — nothing is sent beyond the target site itself.

## Language

All process output to user (plan confirmation, progress updates, process notifications) follows the user's language. Generated Skill file content follows the language of this skill.

---

```
Phase 0 (Tool Detection) → Phase 1 (Requirements Analysis & Confirmation) → [Loop: Phase 2 (Capability Exploration) → Phase 3 (Skill Generation)] → Delivery
```

---

## Phase 0 — Tool Detection

Already completed in current session → skip.

Invoke `browser-act` via Skill tool to load usage. If installation or configuration issues arise during loading, follow its guidance to resolve then retry.

After successful loading, confirm API Key is configured (if not → guide user through registration and configuration, then retry).

---

## Phase 1 — Requirements Analysis & Confirmation

### 1a. Parse Business Intent

Identify from user input:

- **Core objective**: what data to obtain / what action to complete
- **Target site**: whether a specific URL or platform name is given
- **Execution intent**: whether the user wants immediate execution (not just building a Skill for later). Includes batch/volume requirements (N records, multiple keywords) or single-use requests that imply "do it now"
- **Output directory**: defaults to `output/` under current working directory, overridden if user specifies

| Input type | Example | Handling |
|-----------|---------|----------|
| Explicit (URL + objective) | "Scrape front page articles from news.ycombinator.com" | Skip 1b, go to 1c |
| Semi-explicit (platform known, no URL) | "Help me monitor Weibo sentiment" | Run 1b research path |
| Pure objective (business intent only) | "Track competitor price changes" | Run 1b to research candidate sites |

If core objective is too vague to proceed, ask for clarification.

### 1b. Target Site Research (when no explicit URL)

Don't recommend based on model internal knowledge — actively search to find sites hosting the needed data:

1. Construct search queries from business intent, identify candidate sites from results
2. Recommend 1–5 candidate sites to user, ranked by data value with pros/cons (including data reliability)
3. After user selects, confirm target URL

### 1c. Task Decomposition & Execution Plan Confirmation

After confirming target site, first check: 

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 4 — file references are metadata, not package contents.