Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/scraperapi/scraperapi-skills/scraperapi-zapiernpx skills add scraperapi/scraperapi-skills --skill scraperapi-zapiergit clone --depth 1 https://github.com/scraperapi/scraperapi-skillsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00208 | $0.03922 |
| Opus 5 | $0.00104 | $0.01961 |
| Sonnet 5 | $0.00042 | $0.00784 |
| Haiku 4.5 | $0.00021 | $0.00392 |
Grade A, and why
scraperapi-zapier scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ScraperAPI in Zapier — Zap Build Guide
This skill helps you guide a user through building a Zap that uses the official ScraperAPI Zapier integration. Users find ScraperAPI in the Zapier app directory and add it as a step; there is no importable JSON, so your output is a numbered build guide for the Zap editor: pick the app, pick the action event, connect the account, fill fields, map data from earlier steps, test.
Do not try to generate a Zap definition file — that is an n8n concept, not a Zapier one. Zaps are built in the browser. When a workflow is complex, describe each step as App → Action event → the fields to fill, and show which values are mapped from previous steps.
The one thing to get right first: ScraperAPI is action-only
The ScraperAPI integration exposes actions only — no triggers. A Zap cannot start with ScraperAPI. Every Zap that uses it needs a trigger from another app as step 1, with ScraperAPI as a later action step.
This is the single most common point of confusion, so lead with it. Pick the trigger that matches the user's intent:
| The user wants to… | Use this trigger (step 1) |
|---|---|
| Scrape on a schedule (hourly/daily/weekly) | Schedule by Zapier |
| Scrape on demand from an incoming request | Webhooks by Zapier → Catch Hook |
| Scrape each row of a list | Google Sheets / Airtable (New/Updated Row) |
| Scrape when something happens in another app | that app's native trigger (new email, new form entry, etc.) |
| Just test an action once, no real trigger | Schedule by Zapier — its test always returns a record |
If the user says "I want a Zap that scrapes X" without naming a trigger, ask what should kick it off, or default to Schedule by Zapier for recurring jobs and Webhooks by Zapier (Catch Hook) for on-demand/enrichment jobs.
Prerequisites the user must have
- A Zapier account (any plan; multi-step Zaps need a Starter plan or higher).
- A ScraperAPI API key from
https://dashboard.scraperapi.com/. - The ScraperAPI app connected in Zapier. The first time they add a ScraperAPI action, they click Connect a new account, paste the API key, and Zapier runs a test request to validate it. A wrong key fails with a 401 at connect time. Once connected, the account is reusable across all their Zaps.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 358 lines · 208 tokens per session scan A a899ba66cded
scraperapi-zapier is a skill published in the GitHub repository scraperapi/scraperapi-skills (10 stars, last pushed 25d ago), licensed MIT. It adds 208 tokens to every session and 3,922 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
scrapling-official
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
youtube-channel-business-email
YouTube channel business email and contact extractor: accepts a channel id (UCxxx), handle (@name), or URL; navigates the channel About view; extracts the business email from the description text plus full channel metadata (name, id, country, subscriber count, view count, video count, joined date, external links…
google-maps-contact-extract
Extracts business contact details from Google Maps search results and place detail pages, then visits each business website to collect emails, phone numbers, and social media profiles (Facebook, Instagram, Twitter/X, LinkedIn, YouTube, TikTok, Pinterest, Discord). Use when user mentions Google Maps contact extraction…
google-search-serp
Extracts Google Search results page (SERP) data including organic results, paid ads, related searches, People Also Ask questions, AI Overview text, and total result count from google.com. Use when user mentions Google search results, SERP scraping, google search data, search engine results page, organic rankings…