Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Human-in-the-loop CAPTCHA solving with two modes: screenshot (default, zero infrastructure) and token relay (requires network access). Screenshot mode captur...
Human-in-the-loop CAPTCHA solving with two modes: screenshot (default, zero infrastructure) and token relay (requires network access). Screenshot mode captur...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
Solve CAPTCHAs by relaying them to a human. Two modes available.
Grid overlay screenshot β send image to human via Telegram β human replies with cell numbers β inject clicks. Zero setup beyond the skill itself. No Tailscale, no tunnels, no relay server. Works for any CAPTCHA type (reCAPTCHA, hCaptcha, sliders, text, etc.) Uses sharp for image processing + CDP for screenshots and click injection. node index.js # screenshot mode (default) node index.js --mode screenshot # explicit node index.js --screenshot # legacy alias const { solveCaptchaScreenshot } = require('./index'); const capture = await solveCaptchaScreenshot({ cdpPort: 18800 }); // capture.imagePath β annotated screenshot to send to human // capture.prompt β text prompt for the human
Detects CAPTCHA type + sitekey β serves real widget on relay page β human solves natively β token injected via CDP. Requires Tailscale or a tunnel (localtunnel/cloudflared) so the human's device can reach the relay server. Produces a proper CAPTCHA token β more reliable for reCAPTCHA v2, hCaptcha, Turnstile. Best when you have Tailscale already set up. node index.js --mode relay # with localtunnel node index.js --mode relay --no-tunnel # with Tailscale/LAN const { solveCaptcha } = require('./index'); const result = await solveCaptcha({ cdpPort: 18800, useTunnel: false }); // result.relayUrl β URL to send to human // result.token β solved CAPTCHA token
ScenarioModeQuick & easy, no setupscreenshotAny CAPTCHA type (sliders, text, etc.)screenshotKnown CAPTCHA with sitekey (reCAPTCHA, hCaptcha, Turnstile)relayTailscale already configuredrelayNo network access to hostscreenshot
FlagDefaultDescription--mode screenshot|relayscreenshotSelect solving mode--screenshotβAlias for --mode screenshot--no-injectinjectReturn token without injecting into browser--no-tunneltunnelSkip tunnel, use local/Tailscale IP (relay mode)--timeout N120Timeout in seconds--cdp-port N18800Chrome DevTools Protocol port
Call solveCaptchaScreenshot({ cdpPort }) Send capture.imagePath to human via message tool with capture.prompt Human replies with cell numbers (e.g. "1,3,5,7") Call injectGridClicks(cdpPort, capture, selectedCells) to click those cells
Call solveCaptcha({ useTunnel: false }) (Tailscale) or solveCaptcha() (tunnel) Send result.relayUrl to human via message tool Wait β resolves when human completes the CAPTCHA Token is auto-injected; continue automation
Chrome/Chromium with --remote-debugging-port=18800 Node.js 18+ and npm install (deps: ws, sharp) Relay mode only: Tailscale or internet for tunnel
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.