captcha-solver_skill

Overview

This skill provides CAPTCHA recognition and solving using local OCR plus optional third-party solving APIs. It supports simple text, numeric, math, and slide-gap CAPTCHAs locally, and integrates with paid services for complex challenges like reCAPTCHA, hCaptcha, and Cloudflare Turnstile. The design prioritizes local processing with API fallback to balance cost and success rate. It’s implemented in Python and configurable for Tesseract or external solver APIs.

How this skill works

The solver first attempts local OCR workflows: image preprocessing (grayscale, binarization, denoising, sharpening), character segmentation, and recognition via template matching or ML-based OCR. For slide CAPTCHAs it detects edges and gap locations, then generates a realistic movement trajectory to simulate human dragging. If local methods fail or the challenge requires it, the skill forwards the task to configured third-party services (2Captcha, Anti-Captcha) to retrieve tokens or answers.

When to use it

• Automating recognition of simple image or numeric CAPTCHAs where local OCR is sufficient.
• Solving slide-gap CAPTCHAs in automated testing or scraping with simulated human-like trajectories.
• Handling complex site CAPTCHAs (reCAPTCHA, hCaptcha, Turnstile) by using paid API providers.
• Balancing cost and reliability: try local OCR first and fall back to paid solvers on failure.
• Integrating CAPTCHA solving into headless browser workflows or testing pipelines.

Best practices

• Prefer local OCR for privacy and zero API cost; configure Tesseract path and language packs appropriately.
• Chain strategies: preprocess images, then segment and recognize; only call paid APIs when local attempts fail.
• Respect target sites’ terms of service and avoid using the tool for unlawful or abusive activities.
• Tune preprocessing parameters (thresholds, denoising strength) per target CAPTCHA style for best accuracy.
• Use realistic movement profiles for slide CAPTCHAs to reduce detection by anti-bot heuristics.

Example use cases

• Automated QA for web forms that include simple image CAPTCHAs during staging.
• Scraping public data where occasional CAPTCHAs appear and automated fallback is needed.
• Integrating slide-gap solving into end-to-end tests for interactive UI components.
• Using third-party solvers when encountering reCAPTCHA or hCaptcha during large-scale runs.
• Prototyping ML-based OCR improvements by swapping recognition backends in the solver.