Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, MCP tools, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.
.claude/skills/x-twitter-scraper/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 127% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 13% | 0% |
Use this skill when a user wants to integrate Xquik into an app, script, data pipeline, or AI agent workflow for X API and Twitter scraper tasks.
Before writing code, inspect the current Xquik source material:
Do not invent endpoint names, request fields, response fields, scopes, pricing, limits, or package names. Read the relevant SDK README and API reference page first.
When application code is involved, match the SDK to the user's project language:
Use project-native typed request and response models. Keep network calls in server-side code unless the SDK docs explicitly support browser use.
Use extraction jobs for complete or large follower, following, reply, quote, repost, like, list, community, article, media, and search exports.
POST /extractions/estimate with the intended target and filters.Do not treat an extraction-backed follower export as a free public read. Direct, bounded public pagination remains read-only.
Use the Apify path when a workflow needs hosted runs, datasets, schedules, or Apify-native orchestration.
| Need | Actor | REST ID | |---|---|---| | Tweets, search, timelines, lists, articles, replies, quotes, threads, retweeters, or best-effort favoriters | xquik/x-tweet-scraper | xquik~x-tweet-scraper | | Followers, following, verified followers, list members, list subscribers, or community members | xquik/x-follower-scraper | xquik~x-follower-scraper |
Authenticate with an Apify API token. Keep it in APIFY_API_TOKEN. Fetch the current input schema from the relevant Actor page before selecting fields.
Start a bounded tweet run:
bashcurl --fail --silent --show-error --request POST \ "https://api.apify.com/v2/actors/xquik~x-tweet-scraper/runs" \ --header "Authorization: Bearer ${APIFY_API_TOKEN}" \ --header "Content-Type: application/json" \ --data '{"twitterHandles":["apify"],"outputVariant":"rich","maxItems":25}'
Start a bounded follower run:
bashcurl --fail --silent --show-error --request POST \ "https://api.apify.com/v2/actors/xquik~x-follower-scraper/runs" \ --header "Authorization: Bearer ${APIFY_API_TOKEN}" \ --header "Content-Type: application/json" \ --data '{"twitterHandles":["apify"],"relation":"followers","outputMode":"compact","maxItems":50}'
Record the returned run ID. Poll the Actor run with a bounded retry loop. Stop on SUCCEEDED, FAILED, ABORTED, or TIMED-OUT. On success, read defaultDatasetId, then fetch its dataset items.
Treat maxItems as the cap for the entire tweet run, including runs with several search terms. Keep follower target metadata when attribution matters. Treat rows with resultType: "diagnostic" as status information, not scraped records. Inspect any run-report row before trusting an incomplete result.
Review each Actor's live Apify pricing box before every paid run. Apify platform usage may apply separately. Start with a small maxItems value and ask before raising the cap.
When adding webhook handlers:
Use the MCP server when the user wants an agent to explore or call Xquik tools directly. Connect to https://xquik.com/mcp and prefer OAuth 2.1. Use an environment-backed API key only when the client cannot complete OAuth securely.
Call explore to inspect current operation IDs and schemas. Then call xquik with the narrowest matching operation. Keep application code on REST or SDK clients when the app needs stable typed contracts, tests, or internal abstractions.
Use TweetClaw when the user is working in OpenClaw, wants installable plugin metadata, or needs an approval-reviewed path for private, paid, recurring, or account-changing X operations. Keep application services on REST or SDK clients when the project needs typed contracts, server-side abstractions, or long-lived backend jobs outside OpenClaw.
Before suggesting install commands or tool names, read the TweetClaw README and package metadata. Do not assume the published npm version matches source HEAD.
Keep bounded public tweet search, reply search, profile lookup, and evidence collection low risk. Require approval for private reads, paid calls, extraction-backed exports, draws, writes, monitors, webhooks, and recurring work. Review the exact tool payload before approval.
Xquik is an independent third-party service. Not affiliated with X Corp. "Twitter" and "X" are trademarks of X Corp.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 20,129 | 16,893 | -16% | 1 | 1 | 0% | 3,269 | 4,753 | +45% | 0 | 0 | — |
case-02 | fail→pass | 27,421 | 24,035 | -12% | 1 | 1 | 0% | 4,457 | 6,013 | +35% | 0 | 0 | — |
case-03 | fail→fail | 24,998 | 18,299 | -27% | 1 | 1 | 0% | 3,491 | 4,807 | +38% | 0 | 0 | — |
case-04 | fail→pass | 31,263 | 10,952 | -65% | 1 | 1 | 0% | 1,470 | 3,341 | +127% | 0 | 0 | — |
case-05 | fail→pass | 18,841 | 12,364 | -34% | 1 | 1 | 0% | 2,476 | 3,376 | +36% | 0 | 0 | — |
case-06 | fail→pass | 17,611 | 10,589 | -40% | 1 | 1 | 0% | 2,415 | 2,725 | +13% | 0 | 0 | — |
case-07 | fail→pass | 16,956 | 11,449 | -32% | 1 | 1 | 0% | 1,989 | 3,991 | +101% | 0 | 0 | — |
case-08 | fail→pass | 22,068 | 16,219 | -27% | 1 | 1 | 0% | 2,915 | 4,221 | +45% | 0 | 0 | — |
case-09 | fail→pass | 21,026 | 15,839 | -25% | 1 | 1 | 0% | 2,597 | 3,803 | +46% | 0 | 0 | — |
case-10 | pass→pass | 18,129 | 18,902 | +4% | 1 | 1 | 0% | 3,529 | 4,723 | +34% | 0 | 0 | — |
case-11 | pass→pass | 10,759 | 13,296 | +24% | 1 | 1 | 0% | 1,690 | 3,355 | +99% | 0 | 0 | — |
case-12 | fail→pass | 21,716 | 15,590 | -28% | 1 | 1 | 0% | 2,986 | 3,934 | +32% | 0 | 0 | — |
case-13 | fail→pass | 16,072 | 4,040 | -75% | 1 | 1 | 0% | 1,813 | 2,648 | +46% | 0 | 0 | — |
case-14 | fail→pass | 18,504 | 5,108 | -72% | 1 | 1 | 0% | 2,174 | 2,952 | +36% | 0 | 0 | — |
case-15 | fail→pass | 17,083 | 10,663 | -38% | 1 | 1 | 0% | 2,923 | 3,978 | +36% | 0 | 0 | — |
case-16 | fail→pass | 11,338 | 12,594 | +11% | 1 | 1 | 0% | 1,817 | 3,410 | +88% | 0 | 0 | — |
case-17 | fail→pass | 18,980 | 15,632 | -18% | 1 | 1 | 0% | 3,330 | 5,102 | +53% | 0 | 0 | — |
case-18 | pass→pass | 23,500 | 10,860 | -54% | 1 | 1 | 0% | 3,183 | 3,797 | +19% | 0 | 0 | — |
case-19 | pass→pass | 17,064 | 14,676 | -14% | 1 | 1 | 0% | 1,947 | 3,722 | +91% | 0 | 0 | — |
case-20 | pass→fail | 21,308 | 19,106 | -10% | 1 | 1 | 0% | 3,582 | 5,058 | +41% | 0 | 0 | — |
case-21 | fail→fail | 22,481 | 9,695 | -57% | 1 | 1 | 0% | 3,313 | 3,798 | +15% | 0 | 0 | — |
case-22 | pass→pass | 11,748 | 17,146 | +46% | 1 | 1 | 0% | 2,528 | 4,607 | +82% | 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. 22 cases were attempted, and 21 counted toward the lift figure. The other 1 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 +59 percentage points is the difference between those two pass rates over the 21 comparable cases. 2 cases got worse with the skill loaded, and they are 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 | 8/3/2026 | +18% |
| gemini-3.6-flash | verified | 7/27/2026 | +33% |
Other measured skills in the registry, with their headline benchmark lift.