Flaresolverr

A collection of agent skills. Mostly vibe coded.

Install

npx -y skills add whtsky/skills --skill flaresolverr

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Bypass Cloudflare anti-bot protection and 403 challenges using a FlareSolverr proxy to scrape blocked websites.

SKILL.md

1.7 KB, 415 tokens by cl100k_base, as published. Nobody here has run it

FlareSolverr

Bypass Cloudflare protection using FlareSolverr proxy. Default endpoint can be overridden with FLARESOLVERR_URL environment variable (default: http://localhost:8191).

When to Use

web_fetch returns Cloudflare challenge page
curl gets 403 or "Just a moment" / "Checking your browser"

Usage

# Using default URL
FLARESOLVERR_URL="${FLARESOLVERR_URL:-http://localhost:8191}"

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.get",
    "url": "https://example.com/page",
    "maxTimeout": 120000
  }'

Response

{
  "status": "ok",
  "message": "Challenge solved!" or "Challenge not detected!",
  "solution": {
    "url": "final URL after redirects",
    "status": 200,
    "response": "<html>...</html>",
    "cookies": [...],
    "userAgent": "..."
  }
}

Extract content from solution.response.

POST Requests

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.post",
    "url": "https://example.com/api",
    "postData": "key=value&foo=bar",
    "maxTimeout": 120000
  }'

Tips

maxTimeout is in milliseconds; recommend 120000 (120s) for complex challenges
Simple pages typically return in 2-5 seconds; timeout is just the upper limit
Response is full HTML; parse as needed
If status is "error", check message for details

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.