Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →AI-driven data extraction from 55+ Actors across all major platforms. This skill automatically selects the best Actor for your task.
.claude/skills/apify-ultimate-scraper/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 8 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 139% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 103% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 110% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 163% | 0% |
AI-driven data extraction from 55+ Actors across all major platforms. This skill automatically selects the best Actor for your task.
(No need to check it upfront)
.env file with APIFY_TOKEN--env-file support)mcpc CLI tool: npm install -g @apify/mcpcCopy this checklist and track progress:
Task Progress:
- [ ] Step 1: Understand user goal and select Actor
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the scraper script
- [ ] Step 5: Summarize results and offer follow-upsFirst, understand what the user wants to achieve. Then select the best Actor from the options below.
| Actor ID | Best For | |----------|----------| | apify/instagram-profile-scraper | Profile data, follower counts, bio info | | apify/instagram-post-scraper | Individual post details, engagement metrics | | apify/instagram-comment-scraper | Comment extraction, sentiment analysis | | apify/instagram-hashtag-scraper | Hashtag content, trending topics | | apify/instagram-hashtag-stats | Hashtag performance metrics | | apify/instagram-reel-scraper | Reels content and metrics | | apify/instagram-search-scraper | Search users, places, hashtags | | apify/instagram-tagged-scraper | Posts tagged with specific accounts | | apify/instagram-followers-count-scraper | Follower count tracking | | apify/instagram-scraper | Comprehensive Instagram data | | apify/instagram-api-scraper | API-based Instagram access | | apify/export-instagram-comments-posts | Bulk comment/post export |
| Actor ID | Best For | |----------|----------| | apify/facebook-pages-scraper | Page data, metrics, contact info | | apify/facebook-page-contact-information | Emails, phones, addresses from pages | | apify/facebook-posts-scraper | Post content and engagement | | apify/facebook-comments-scraper | Comment extraction | | apify/facebook-likes-scraper | Reaction analysis | | apify/facebook-reviews-scraper | Page reviews | | apify/facebook-groups-scraper | Group content and members | | apify/facebook-events-scraper | Event data | | apify/facebook-ads-scraper | Ad creative and targeting | | apify/facebook-search-scraper | Search results | | apify/facebook-reels-scraper | Reels content | | apify/facebook-photos-scraper | Photo extraction | | apify/facebook-marketplace-scraper | Marketplace listings | | apify/facebook-followers-following-scraper | Follower/following lists |
| Actor ID | Best For | |----------|----------| | clockworks/tiktok-scraper | Comprehensive TikTok data | | clockworks/free-tiktok-scraper | Free TikTok extraction | | clockworks/tiktok-profile-scraper | Profile data | | clockworks/tiktok-video-scraper | Video details and metrics | | clockworks/tiktok-comments-scraper | Comment extraction | | clockworks/tiktok-followers-scraper | Follower lists | | clockworks/tiktok-user-search-scraper | Find users by keywords | | clockworks/tiktok-hashtag-scraper | Hashtag content | | clockworks/tiktok-sound-scraper | Trending sounds | | clockworks/tiktok-ads-scraper | Ad content | | clockworks/tiktok-discover-scraper | Discover page content | | clockworks/tiktok-explore-scraper | Explore content | | clockworks/tiktok-trends-scraper | Trending content | | clockworks/tiktok-live-scraper | Live stream data |
| Actor ID | Best For | |----------|----------| | streamers/youtube-scraper | Video data and metrics | | streamers/youtube-channel-scraper | Channel information | | streamers/youtube-comments-scraper | Comment extraction | | streamers/youtube-shorts-scraper | Shorts content | | streamers/youtube-video-scraper-by-hashtag | Videos by hashtag |
| Actor ID | Best For | |----------|----------| | compass/crawler-google-places | Business listings, ratings, contact info | | compass/google-maps-extractor | Detailed business data | | compass/Google-Maps-Reviews-Scraper | Review extraction | | poidata/google-maps-email-extractor | Email discovery from listings |
| Actor ID | Best For | |----------|----------| | xquik/x-tweet-scraper | Tweet lookup, search, timelines, lists, threads, replies, quotes, and engagement | | xquik/x-follower-scraper | Followers, following, verified followers, lists, communities, and audience overlap |
Check each Actor's live Apify pricing box before starting a paid run. Show the Actor, targets, result cap, and maximum charge. Get explicit approval. Set a conservative result cap. maxItems applies across the whole run.
Xquik is an independent third-party service. Not affiliated with X Corp. "Twitter" and "X" are trademarks of X Corp.
| Actor ID | Best For | |----------|----------| | apify/google-search-scraper | Google search results | | apify/google-trends-scraper | Google Trends data | | voyager/booking-scraper | Booking.com hotel data | | voyager/booking-reviews-scraper | Booking.com reviews | | maxcopell/tripadvisor-reviews | TripAdvisor reviews | | vdrmota/contact-info-scraper | Contact enrichment from URLs |
| Use Case | Primary Actors | |----------|---------------| | Lead Generation | compass/crawler-google-places, poidata/google-maps-email-extractor, vdrmota/contact-info-scraper | | Influencer Discovery | apify/instagram-profile-scraper, clockworks/tiktok-profile-scraper, streamers/youtube-channel-scraper | | Brand Monitoring | xquik/x-tweet-scraper, apify/instagram-tagged-scraper, apify/instagram-hashtag-scraper, compass/Google-Maps-Reviews-Scraper | | Competitor Analysis | apify/facebook-pages-scraper, apify/facebook-ads-scraper, apify/instagram-profile-scraper | | Content Analytics | apify/instagram-post-scraper, clockworks/tiktok-scraper, streamers/youtube-scraper | | Trend Research | apify/google-trends-scraper, clockworks/tiktok-trends-scraper, apify/instagram-hashtag-stats | | Review Analysis | compass/Google-Maps-Reviews-Scraper, voyager/booking-reviews-scraper, maxcopell/tripadvisor-reviews | | Audience Analysis | xquik/x-follower-scraper, apify/instagram-followers-count-scraper, clockworks/tiktok-followers-scraper, apify/facebook-followers-following-scraper |
For complex tasks, chain multiple Actors:
| Workflow | Step 1 | Step 2 | |----------|--------|--------| | Lead enrichment | compass/crawler-google-places → | vdrmota/contact-info-scraper | | Influencer vetting | apify/instagram-profile-scraper → | apify/instagram-comment-scraper | | Competitor deep-dive | apify/facebook-pages-scraper → | apify/facebook-posts-scraper | | Local business analysis | compass/crawler-google-places → | compass/Google-Maps-Reviews-Scraper | | X audience context | xquik/x-follower-scraper → | xquik/x-tweet-scraper |
If none of the Actors above match the user's request, search the Apify Store directly:
bashexport $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call search-actors keywords:="SEARCH_KEYWORDS" limit:=10 offset:=0 category:="" | jq -r '.content[0].text'
Replace SEARCH_KEYWORDS with 1-3 simple terms (e.g., "LinkedIn profiles", "Amazon products", "Twitter").
Fetch the Actor's input schema and details dynamically using mcpc:
bashexport $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"
Replace ACTOR_ID with the selected Actor (e.g., compass/crawler-google-places).
This returns:
Before running, ask:
Quick answer (display in chat, no file):
bashnode --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \ --actor "ACTOR_ID" \ --input 'JSON_INPUT'
CSV:
bashnode --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \ --actor "ACTOR_ID" \ --input 'JSON_INPUT' \ --output YYYY-MM-DD_OUTPUT_FILE.csv \ --format csv
JSON:
bashnode --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \ --actor "ACTOR_ID" \ --input 'JSON_INPUT' \ --output YYYY-MM-DD_OUTPUT_FILE.json \ --format json
After completion, report:
| If User Got | Suggest Next | |-------------|--------------| | Business listings | Enrich with vdrmota/contact-info-scraper or get reviews | | Influencer profiles | Analyze engagement with comment scrapers | | Competitor pages | Deep-dive with post/ad scrapers | | Trend data | Validate with platform-specific hashtag scrapers |
APIFY_TOKEN not found - Ask user to create .env with APIFY_TOKEN=your_token mcpc not found - Ask user to install npm install -g @apify/mcpc Actor not found - Check Actor ID spelling Run FAILED - Ask user to check Apify console link in error output Timeout - Reduce input size or increase --timeout
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→pass | 15,524 | 8,208 | -47% | 1 | 1 | 0% | 3,075 | 4,758 | +55% | 0 | 0 | — |
case-07 | fail→pass | 13,134 | 5,700 | -57% | 1 | 1 | 0% | 2,378 | 4,081 | +72% | 0 | 0 | — |
case-08 | fail→fail | 11,606 | 6,344 | -45% | 1 | 1 | 0% | 1,931 | 4,212 | +118% | 0 | 0 | — |
case-01 | fail→fail | 3,382 | 7,984 | +136% | 1 | 1 | 0% | 453 | 3,633 | +702% | 0 | 0 | — |
case-02 | fail→fail | 10,283 | 2,232 | -78% | 1 | 1 | 0% | 1,909 | 3,438 | +80% | 0 | 0 | — |
case-03 | fail→fail | 9,437 | 8,527 | -10% | 1 | 1 | 0% | 1,693 | 3,781 | +123% | 0 | 0 | — |
case-04 | pass→pass | 9,376 | 8,902 | -5% | 1 | 1 | 0% | 1,917 | 4,758 | +148% | 0 | 0 | — |
case-05 | pass→pass | 9,751 | 7,010 | -28% | 1 | 1 | 0% | 1,686 | 4,331 | +157% | 0 | 0 | — |
case-09 | fail→pass | 9,410 | 3,893 | -59% | 1 | 1 | 0% | 1,558 | 3,726 | +139% | 0 | 0 | — |
case-10 | fail→pass | 11,569 | 5,317 | -54% | 1 | 1 | 0% | 1,959 | 3,980 | +103% | 0 | 0 | — |
case-11 | fail→pass | 10,776 | 15,225 | +41% | 1 | 1 | 0% | 1,836 | 3,847 | +110% | 0 | 0 | — |
case-12 | fail→fail | 10,502 | 7,734 | -26% | 1 | 1 | 0% | 1,747 | 3,504 | +101% | 0 | 0 | — |
case-13 | fail→pass | 8,555 | 5,263 | -38% | 1 | 1 | 0% | 1,519 | 3,989 | +163% | 0 | 0 | — |
case-14 | fail→pass | 12,427 | 4,463 | -64% | 1 | 1 | 0% | 1,919 | 3,802 | +98% | 0 | 0 | — |
case-15 | pass→fail | 12,581 | 9,667 | -23% | 1 | 1 | 0% | 1,993 | 3,698 | +86% | 0 | 0 | — |
case-16 | fail→pass | 10,164 | 2,981 | -71% | 1 | 1 | 0% | 2,035 | 3,704 | +82% | 0 | 0 | — |
case-17 | fail→pass | 9,281 | 3,667 | -60% | 1 | 1 | 0% | 1,756 | 3,761 | +114% | 0 | 0 | — |
case-18 | fail→fail | 12,983 | 7,167 | -45% | 1 | 1 | 0% | 2,213 | 3,528 | +59% | 0 | 0 | — |
case-19 | fail→pass | 11,136 | 6,872 | -38% | 1 | 1 | 0% | 1,777 | 4,009 | +126% | 0 | 0 | — |
case-20 | fail→fail | 12,619 | 9,473 | -25% | 1 | 1 | 0% | 1,969 | 3,660 | +86% | 0 | 0 | — |
case-21 | fail→pass | 4,640 | 4,440 | -4% | 1 | 1 | 0% | 731 | 3,903 | +434% | 0 | 0 | — |
case-22 | pass→pass | 7,993 | 3,395 | -58% | 1 | 1 | 0% | 1,555 | 3,664 | +136% | 0 | 0 | — |
case-23 | fail→pass | 12,256 | 3,611 | -71% | 1 | 1 | 0% | 2,036 | 3,677 | +81% | 0 | 0 | — |
case-24 | fail→pass | 12,407 | 4,500 | -64% | 1 | 1 | 0% | 2,059 | 3,419 | +66% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted, and 18 counted toward the lift figure. The other 6 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +46 percentage points is the difference between those two pass rates over the 18 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/28/2026 | +50% |
Other measured skills in the registry, with their headline benchmark lift.