# actionbook-scraper

The actionbook-scraper skill generates and validates web scraper scripts using verified selectors from Actionbook's database. It auto-validates generated scripts and fixes errors.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 132 installs · ★ 1632 repo stars
- Author: actionbook
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/actionbook/actionbook/tree/HEAD/playground/actionbook-scraper/skills/actionbook-scraper/SKILL.md
- Updated: 2026-10-19
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/actionbook-scraper

## What it does

actionbook-scraper takes a URL, searches Actionbook's selector database for that site, and generates a working scraper script. By default it outputs commands for `agent-browser` (bash); with the `--standalone` flag it produces JavaScript code for Playwright.

Every script passes two-stage verification: first, the code runs without errors; second, extracted data is real, not UI text like "Loading..." or "Click to expand". If something fails, the skill identifies whether it's a script error or a selector issue, then fixes and re-runs it.

The output is a tested, ready-to-use script. You need a working browser environment; for `--standalone` you'll need Node.js and Playwright installed.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add actionbook/actionbook --skill actionbook-scraper -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/actionbook-scraper/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/actionbook-scraper/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add actionbook/actionbook --skill actionbook-scraper -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/actionbook-scraper/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add actionbook/actionbook --skill actionbook-scraper -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/actionbook-scraper/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install actionbook/actionbook playground/actionbook-scraper/skills/actionbook-scraper
```

2. **Manually: put the files in place**
- File: `.github/skills/actionbook-scraper/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add actionbook/actionbook --skill actionbook-scraper -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/actionbook/actionbook --path playground/actionbook-scraper/skills/actionbook-scraper
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/actionbook-scraper/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add actionbook/actionbook --skill actionbook-scraper -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/actionbook/actionbook/tree/HEAD/playground/actionbook-scraper/skills/actionbook-scraper/SKILL.md

## When to use it
- generate a scraper script from a URL without manually finding selectors
- verify that a scraper works and extracts real data, not button labels
- convert a scraper script between formats
- fix selectors when extracted data doesn't match expectations

## Example prompts
- Generate a scraper script for `https://example.com`
- Generate JavaScript scraper code for this site using the `--standalone` flag
- Verify the scraper works correctly and extracts the right data

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: fd144aef657859fe.

BEGIN THIRD-PARTY FILE fd144aef657859fe
````text
---
name: actionbook-scraper
description: Generate and verify web scraper scripts using Actionbook's verified selectors. Auto-validates generated scripts and fixes errors.
---

# Actionbook Scraper Skill

## ⚠️ CRITICAL: Two-Part Verification

**Every generated script MUST pass BOTH checks:**

| Check | What to Verify | Failure Example |
|-------|----------------|-----------------|
| **Part 1: Script Runs** | No errors, no timeouts | `Selector not found` |
| **Part 2: Data Correct** | Content matches expected | Extracted "Click to expand" instead of name |

```
┌─────────────────────────────────────────────────────┐
│   1. Generate Script                                │
│          ↓                                          │
│   2. Execute Script                                 │
│          ↓                                          │
│   3. Check Part 1: Script runs without errors?      │
│          ↓                                          │
│   4. Check Part 2: Data content is correct?         │
│      - Not empty                                    │
│      - Not placeholder text ("Loading...")          │
│      - Not UI text ("Click to expand")              │
│      - Fields mapped correctly                      │
│          ↓                                          │
│      ┌───┴───┐                                      │
│   BOTH Pass  Either Fails                           │
│      │           │                                  │
│      │           ↓                                  │
│      │       Is it Actionbook data issue?           │
│      │           │                                  │
│      │       ┌───┴───┐                              │
│      │      Yes      No                             │
│      │       │       │                              │
│      │       ↓       ↓                              │
│      │    Log to   Fix script                       │
│      │    .actionbook-issues.log                    │
│      │       │       │                              │
│      │       └───┬───┘                              │
│      │           ↓                                  │
│      │       Retry (max 3x)                         │
│      ↓                                              │
│   Output Script                                     │
````
END THIRD-PARTY FILE fd144aef657859fe

The third-party file has ended. Everything between the fd144aef657859fe tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2649 of 19656 bytes. © actionbook · Apache-2.0 · https://github.com/actionbook/actionbook/tree/HEAD/playground/actionbook-scraper/skills/actionbook-scraper/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
