Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
DeepSeek
Muse+22 moreClaude CodeCursorCodex CLIDeepSeekMuse
Dots
Manus
Grok
Grok Bot+18 agentsTwitter/X Scraper
Automated Twitter/X profile discovery and browser-based scraping with anti-detection and proxy support.
$8
Twitter/X Scraper
Example session with this skill installed
Find 10 tech influencers in Miami and scrape their profile stats and recent tweets. Save the results as a CSV.
- Read your context and instructions
- Compiled the twitter x scraper
- Generated the data export
I have initiated the discovery and scraping process for tech influencers in Miami. Using the DuckDuckGo fallback for discovery, I identified 10 relevant profiles and performed stealth browser scraping to extract their metrics.
Miami Tech Influencer Report
| Username | Display Name | Followers | Verified | Top Tweet Engagement | Media Saved |
|---|---|---|---|---|---|
| miamitechguy | Alex Rivera | 45,200 | Yes | 1.2k Likes, 340 RTs | 3 images |
| 305dev | Sofia Chen | 12,800 | No | 450 Likes, 89 RTs | 1 image |
| venturemiami | Miami VC | 89,500 | Yes | 2.1k Likes, 600 RTs | 5 images |
| cryptobeach | Julian Voss | 5,400 | No | 120 Likes, 15 RTs | 2 images |
| sunshinecode | Elena Rodriguez | 22,100 | Yes | 890 Likes, 210 RTs | 4 images |
| techeventsmia | MIA Tech Hub | 31,000 | Yes | 560 Likes, 150 RTs | 2 images |
| startuphialeah | Marcus Thorne | 2,900 | No | 95 Likes, 12 RTs | 1 image |
| brickellfintech | David Bloom | 15,300 | No | 310 Likes, 45 RTs | 3 images |
| magiccityai | Sarah J. | 7,800 | No | 205 Likes, 33 RTs | 1 image |
| siliconbeach305 | Tech Watch | 110,000 | Yes | 4.5k Likes, 1.1k RTs | 6 images |
Next steps
- Access the full dataset in
data/export_20260220_1430.csv. - Review the downloaded media files in the
thumbnails/directory. - Configure a residential proxy in
config/scraper_config.jsonbefore running larger batches.
export_20260220_1430.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Manually collecting Twitter/X profile data for lead generation or influencer research is slow and prone to immediate IP bans. Developers face constant challenges with login walls, sophisticated bot detection, and unstable DOM selectors.
What it does
- Discovers niche-specific profiles by location and category using Google Custom Search or DuckDuckGo.
- Extracts full profile metadata including follower counts, verified status, and engagement metrics without requiring a login.
- Simulates human behavior using Playwright with stealth scripts, canvas noise, and randomized mouse movements.
- Automates media archival by downloading profile pictures and tweet media to local storage.
- Manages long-running sessions with built-in checkpointing, auto-resume, and residential proxy rotation.
Frameworks & tools
Python 3, Playwright, Chromium, and Google Custom Search API.
Why this beats prompting it yourself
Vanilla LLM prompts cannot bypass Twitter's aggressive anti-bot measures or handle dynamic browser rendering. This skill integrates specific fingerprinting evasion and residential proxy logic that a standard agentic script lacks, ensuring reliable data extraction at scale.
Use cases
- Building verified lead lists for local businesses based on geographic metadata.
- Conducting competitive analysis by monitoring engagement trends across industry influencers.
- Archiving social media presence for brand sentiment analysis and sentiment tracking.
- Automating the discovery of niche micro-influencers for targeted marketing campaigns.
Known limitations
Does not scrape private (protected) accounts. Requires a residential proxy for high-volume operations to avoid rate limits.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills to Reverse Engineer and Scrape Websites.
Only scrapes public profiles. High-volume scraping requires residential proxies. Discovery limited by Google API quotas if not using DuckDuckGo fallback.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
- Accounts
Duckduckgo
- Software
Python
Permissions
Allowed Hosts