agentleFS
JayRHaJayRHa/AgentSkills/skills/xquik-social-data/SKILL.md

xquik-social-data

Skill12 starsChanged 5 months agoMITView on GitHub

Use this skill when the user needs X or Twitter social data extraction, tweet search, profile and follower lookup, media download, webhook monitoring, MCP setup, or REST API integration with Xquik and the x-developer skill package.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. About 0 are common, 17 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈17

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when an agent needs to plan, implement, or verify Xquik social-data workflows.

    line 11
  2. Distinctive:

    Prefer the published skill package so agents load the full Xquik reference material only when needed.

    line 17
  3. Distinctive:

    Use the public docs for API and MCP details:

    line 23
  4. Very specific:

    Use the installed x-twitter-scraper skill for agent-guided endpoint selection.

    line 33
  5. Distinctive:

    Use the MCP server when the host supports remote MCP tools.

    line 34
  6. Distinctive:

    Use the REST API when building an application, workflow, or backend integration.

    line 35
  7. Distinctive:

    Read the relevant Xquik reference before naming endpoints or request fields.

    line 44
  8. Distinctive:

    Verify the result with the response contract, returned identifiers, webhook signature checks, or a follow-up read where appropriate.

    line 47
  9. Distinctive:

    Keep Xquik optional in host integrations.

    line 63
  10. Distinctive:

    Treat connected-account reads and all write actions as approval-gated workflows.

    line 64
  11. Distinctive:

    Use documented pagination cursors instead of one-shot assumptions for list endpoints.

    line 65
  12. Distinctive:

    Verify webhook signatures with HMAC-SHA256 before trusting event payloads.

    line 67
  13. Distinctive:

    Prefer task-specific endpoint references over broad summaries when implementing code.

    line 68
  14. Distinctive:

    Do not scrape public docs into hardcoded endpoint tables.

    line 72
  15. Distinctive:

    Do not retry validation errors unchanged.

    line 73
  16. Distinctive:

    Do not treat an accepted bulk extraction job as completed.

    line 74
  17. Distinctive:

    Do not expose private account content, API keys, webhook secrets, or connected-account identifiers in public issues or examples.

    line 75
  18. Distinctive:

    Do not claim official X platform affiliation.

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Xquik Social Data

Overview

Use this skill when an agent needs to plan, implement, or verify Xquik social-data workflows. Xquik provides an installable agent skill, REST API, MCP server, webhooks, bulk extraction jobs, and confirmation-gated X actions for developer workflows.

Keywords: Xquik, x-developer, x-twitter-scraper, X API, Twitter API, tweet search, followers, following, media download, webhooks, MCP, social data extraction, giveaway draw, account monitoring.

Setup

Prefer the published skill package so agents load the full Xquik reference material only when needed.

npx skills@1.5.3 add Xquik-dev/x-twitter-scraper

Use the public docs for API and MCP details:

  • https://docs.xquik.com
  • https://docs.xquik.com/api-reference/overview
  • https://docs.xquik.com/mcp/overview

Workflow

  1. Confirm the task needs X social data or X account automation. If it is only general web research, use the user's normal research tools instead.
  2. Choose the narrowest integration path:
    • Use the installed x-twitter-scraper skill for agent-guided endpoint selection.
    • Use the MCP server when the host supports remote MCP tools.
    • Use the REST API when building an application, workflow, or backend integration.
  3. Map the user's goal to a public capability:
    • Tweet search and lookup for keywords, URLs, IDs, hashtags, and advanced search operators.
    • User profile lookup, recent posts, likes, media, followers, following, and verified followers.
    • Bulk extraction for replies, quotes, reposts, favoriters, communities, lists, Spaces, mentions, articles, and people search.
    • Media download for tweet images, GIFs, and videos.
    • Monitors and HMAC webhooks for account or keyword activity.
    • Giveaway draws from tweet replies with configurable filters.
    • Confirmation-gated posting and account actions when the user explicitly requests them.
  4. Read the relevant Xquik reference before naming endpoints or request fields. Do not invent parameters, response shapes, limits, or pricing.
  5. For large reads, use the documented estimate and pagination flow before launching jobs. Continue with cursors until the response reports completion.
  6. For write actions, require explicit user approval in the calling product or agent flow before sending the request.
  7. Verify the result with the response contract, returned identifiers, webhook signature checks, or a follow-up read where appropriate.

Decision Guide

User asks forUse
"Find tweets about..."Tweet search
"Get this user's followers"Follower extraction
"Download media from this tweet"Media download
"Track new posts from this account"Account monitor plus webhook
"Build an agent tool for X data"MCP server or REST API
"Post this tweet"Confirmation-gated write action
"Run a reply giveaway"Giveaway draw

Best Practices

  • Keep Xquik optional in host integrations. Do not replace an existing provider unless the user asks.
  • Treat connected-account reads and all write actions as approval-gated workflows.
  • Use documented pagination cursors instead of one-shot assumptions for list endpoints.
  • Store API keys and webhook secrets in the host secret manager. Never paste them into examples, logs, or pull requests.
  • Verify webhook signatures with HMAC-SHA256 before trusting event payloads.
  • Prefer task-specific endpoint references over broad summaries when implementing code.

Common Pitfalls

  • Do not scrape public docs into hardcoded endpoint tables. Link to the source docs or install the skill package.
  • Do not retry validation errors unchanged. Fix the request shape first.
  • Do not treat an accepted bulk extraction job as completed. Poll the documented job status endpoint.
  • Do not expose private account content, API keys, webhook secrets, or connected-account identifiers in public issues or examples.
  • Do not claim official X platform affiliation. Describe Xquik as a developer platform for X workflows.

Supporting Resources

  • Published package: x-developer@2.4.16
  • Source repository: https://github.com/Xquik-dev/x-twitter-scraper
  • Product docs: https://docs.xquik.com
  • API reference: https://docs.xquik.com/api-reference/overview
  • MCP guide: https://docs.xquik.com/mcp/overview

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.