tavily-key-generator-proxy

aradotso/trending-skills · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/aradotso/trending-skills --skill tavily-key-generator-proxy
0 commentsdiscussion
summary

Skill by ara.so — Daily 2026 Skills collection

skill.md

Tavily Key Generator + API Proxy

Skill by ara.so — Daily 2026 Skills collection

Automates bulk Tavily account registration using Playwright + CapSolver (Cloudflare Turnstile), then pools the resulting API keys behind a unified proxy gateway with round-robin rotation, usage tracking, token management, and a web console.


What It Does

Component Location Purpose
Key Generator root / Playwright-driven headless Firefox registers Tavily accounts, solves Turnstile CAPTCHAs, verifies email, extracts API key
API Proxy proxy/ FastAPI service that round-robins requests across pooled keys, exposes /api/search and /api/extract, serves web console at /console

Each free Tavily account yields 1,000 API calls/month. The proxy aggregates quota: 10 keys = 10,000 calls/month via one endpoint.


Installation

Key Generator

git clone https://github.com/skernelx/tavily-key-generator.git
cd tavily-key-generator
pip install -r requirements.txt
playwright install firefox
cp config.example.py config.py
# Edit config.py with your CapSolver key and email backend
python main.py

API Proxy (Docker — recommended)

cd proxy/
cp .env.example .env
# Set ADMIN_PASSWORD in .env
docker compose up -d
# Console at http://localhost:9874/console

Configuration (config.py)

CAPTCHA Solver (required)

# CapSolver — recommended (~$0.001/solve, high success rate)
CAPTCHA_SOLVER = "capsolver"
CAPSOLVER_API_KEY = "CAP-..."   # from capsolver.com

# Browser click fallback — free but low success rate
CAPTCHA_SOLVER = "browser"

Email Backend (required — pick one)

Option A: Cloudflare Email Worker (self-hosted, free)

EMAIL_BACKEND = "cloudflare"
EMAIL_DOMAIN = "mail.yourdomain.com"
EMAIL_API_URL = "https://mail.yourdomain.com"
EMAIL_API_TOKEN = "your-worker-token"

Option B: DuckMail (third-party temporary email)

EMAIL_BACKEND = "duckmail"
DUCKMAIL_API_BASE = "https://api.duckmail.sbs"
DUCKMAIL_BEARER = "dk_..."
DUCKMAIL_DOMAIN = "duckmail.sbs"

If both backends are configured, the CLI prompts you to choose at runtime.

Registration Throttle (anti-ban)

THREADS = 2                  # Max 3 — more = higher ban risk
COOLDOWN_BASE = 45           # Seconds between registrations
COOLDOWN_JITTER = 15         # Random additional seconds
BATCH_LIMIT = 20             # Pause after this many registrations

Auto-upload to Proxy (optional)

PROXY_AUTO_UPLOAD = True
PROXY_URL = "http://localhost:9874"
PROXY_ADMIN_PASSWORD = "your-admin-password"

Running the Key Generator

python main.py
# Prompts: how many keys to generate, which email backend
# Output: api_keys.md with all generated keys
# If PROXY_AUTO_UPLOAD=True, keys are pushed to proxy automatically

Generated api_keys.md format (used for bulk import into proxy):

tvly-abc123...
tvly-def456...
tvly-ghi789...

API Proxy Usage

Calling the Proxy (drop-in Tavily replacement)

# Search — replace base URL only
curl -X POST http://your-server:9874/api/search \
  -H "Authorization: Bearer tvly-YOUR_PROXY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"query": "latest AI news", "search_depth": "basic"}'

# Extract
curl -X POST http://your-server:9874/api/extract \
  -H "Authorization: Bearer tvly-YOUR_PROXY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"urls": ["https://example.com/article"]}'

Token can also be passed in the request body as api_key (Tavily SDK compatible):

import requests

response = requests.post(
    "http://your-server:9874/api/search",
    json={
        "query": "Python web scraping",
        "api_key": "tvly-YOUR_PROXY_TOKEN"
    }
)
print(response.json())

Python SDK Integration

from tavily import TavilyClient

# Point SDK at your proxy — no other changes needed
client = TavilyClient(
    api_key="tvly-YOUR_PROXY_TOKEN",
    base_url="http://your-server:9874"
)

results = client.search("machine learning trends 2025")

Admin API Reference

All admin endpoints require header: X-Admin-Password: your-password

Keys Management

# List all keys
curl http://localhost:9874/api/keys \
  -H "X-Admin-Password: secret"

# Add a single key
curl -X POST http://localhost:9874/api/keys \
  -H "X-Admin-Password: secret" \
  -H "Content-Type: application/json" \
  -d '{"key": "tvly-abc123..."}'

# Bulk import from api_keys.md text
curl -X POST http://localhost:9874/api/keys \
  -H "X-Admin-Password: secret" \
  -H "Content-Type: application/json" \
  -d '{"bulk": "tvly-abc...\ntvly-def...\ntvly-ghi..."}'

# Toggle key enabled/disabled
curl -X PUT http://localhost:9874/api/keys/{id}/toggle \
  -H "X-Admin-Password: secret"

# Delete key
curl -X DELETE http://localhost:9874/api/keys/{id} \
  -H "X-Admin-Password: secret"

Token Management

# Create access token
curl -X POST http://localhost:9874/api/tokens \
  -H "X-Admin-Password: secret" \
  -H "Content-Type: application/json" \
  -d '{"label": "my-app"}'
# Returns: {"token": "tvly-...", "id": "..."}

# List tokens
curl http://localhost:9874/api/tokens \
  -H "X-Admin-Password: secret"

# Delete token
curl -X DELETE http://localhost:9874/api/tokens/{id} \
  -H "X-Admin-Password: secret"

Stats

curl http://localhost:9874/api/stats \
  -H "X-Admin-Password: secret"
# Returns: total_quota, used, remaining, active_keys, disabled_keys

Change Admin Password

curl -X PUT http://localhost:9874/api/password \
  -H "X-Admin-Password: current-password" \
  -H "Content-Type: application/json" \
  -d '{"new_password": "new-secure-password"}'

Proxy Behavior

  • Round-robin: requests distributed evenly across active keys
  • Auto-disable: key disabled after 3 consecutive failures
  • Quota tracking: total = active_keys × 1,000/month; updates automatically on add/delete/toggle
  • Token format: proxy tokens use tvly- prefix, indistinguishable from real Tavily keys to clients

Proxy .env Configuration

ADMIN_PASSWORD=change-this-immediately
PORT=9874
# Optional: restrict CORS origins
CORS_ORIGINS=https://myapp.com,https://app2.com

Nginx Reverse Proxy + HTTPS

server {
    listen 443 ssl;
    server_name tavily-proxy.yourdomain.com;

    ssl_certificate /etc/letsencrypt/live/yourdomain.com/fullchain.pem;
    ssl_certificate_key /etc/letsencrypt/live/yourdomain.com/privkey.pem;

    location / {
        proxy_pass http://127.0.0.1:9874;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
    }
}

Integration Pattern: Auto-replenish Pool

# replenish.py — run on cron when quota runs low
import requests

PROXY_URL = "http://localhost:9874"
ADMIN_PASSWORD = "your-password"
MIN_ACTIVE_KEYS = 10

def get_stats():
    r = requests.get(f"{PROXY_URL}/api/stats",
                     headers={"X-Admin-Password": ADMIN_PASSWORD})
    return r.json()

def trigger_registration
how to use tavily-key-generator-proxy

How to use tavily-key-generator-proxy on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add tavily-key-generator-proxy
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/aradotso/trending-skills --skill tavily-key-generator-proxy

The skills CLI fetches tavily-key-generator-proxy from GitHub repository aradotso/trending-skills and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/tavily-key-generator-proxy

Reload or restart Cursor to activate tavily-key-generator-proxy. Access the skill through slash commands (e.g., /tavily-key-generator-proxy) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

Save 3-5 hours/week on communication overhead

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client
  • Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • Not validating competitive research—verify facts before sharing
  • Accepting user stories without involving engineering team
  • Over-relying on frameworks without qualitative judgment
  • Not customizing outputs to company culture and communication style
  • Skipping stakeholder validation of generated requirements

Best Practices

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • Don't publish competitive analysis without fact-checking
  • Don't finalize user stories without engineering review
  • Don't make prioritization decisions solely on AI scoring
  • Don't skip customer validation of generated requirements
  • Don't ignore company-specific context and culture

💡 Pro Tips

  • Provide context: company goals, constraints, customer feedback
  • Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • Use skill for 70% generation + 30% customization to company needs

When to Use This

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.546 reviews
  • Ishan Gonzalez· Dec 12, 2024

    tavily-key-generator-proxy fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Ganesh Mohane· Dec 4, 2024

    I recommend tavily-key-generator-proxy for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Ishan Ndlovu· Dec 4, 2024

    tavily-key-generator-proxy reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Daniel Farah· Dec 4, 2024

    I recommend tavily-key-generator-proxy for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Sakshi Patil· Nov 23, 2024

    Useful defaults in tavily-key-generator-proxy — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Anika Li· Nov 23, 2024

    Keeps context tight: tavily-key-generator-proxy is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Chen Mensah· Nov 23, 2024

    tavily-key-generator-proxy is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Chen Robinson· Nov 3, 2024

    We added tavily-key-generator-proxy from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Li Mensah· Oct 22, 2024

    Solid pick for teams standardizing on skills: tavily-key-generator-proxy is focused, and the summary matches what you get after install.

  • Chaitanya Patil· Oct 14, 2024

    tavily-key-generator-proxy is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

showing 1-10 of 46

1 / 5