agentleFS
MKAbuMattarMKAbuMattar/skills/xquik-x-data/SKILL.md

xquik-x-data

Skill1 starsChanged 4 months agoMITView on GitHub

Plan and run X/Twitter data workflows with Xquik using public REST API, webhooks, and MCP docs. Use this skill when the user needs post search, user lookup, timeline review, monitoring, webhook delivery, or agent access to X/Twitter data through Xquik.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 12 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Xquik for X/Twitter search, user lookup, timeline review, monitors, webhooks, and MCP-based agent workflows.

    line 25
  2. Distinctive:

    Use the public docs for endpoint names, parameters, and response shapes.

    line 44
  3. Distinctive:

    Keep examples scoped to public data and remove any sensitive user values before saving commands or logs.

    line 45
  4. Distinctive:

    Use MCP when an agent should call Xquik tools directly during a task.

    line 57
  5. Distinctive:

    Verify the configured server name, key handling, and available tools before assuming a tool exists.

    line 59
  6. Distinctive:

    Keep the agent prompt explicit about the target account, query, limit, and expected output.

    line 60
  7. Distinctive:

    Never paste or store API keys, cookies, or account sign-in material.

    line 64
  8. Distinctive:

    Do not claim access to private posts or private account data.

    line 65
  9. Distinctive:

    Do not describe private backend routing or infrastructure.

    line 66
  10. Distinctive:

    Do not fabricate pricing, endpoint names, response fields, or service limits.

    line 67
  11. Distinctive:

    If the docs do not cover a requested action, say it is not confirmed and propose the closest documented option.

    line 68
  12. Distinctive:

    When reporting a completed Xquik data task, include:

    line 72

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 X Data

Use Xquik for X/Twitter search, user lookup, timeline review, monitors, webhooks, and MCP-based agent workflows.

When To Use

  • The user asks for public X/Twitter posts, users, timelines, trends, or monitoring.
  • The workflow needs REST API calls, webhook delivery, or MCP access to Xquik.
  • The task needs a repeatable plan for collecting, filtering, or exporting X/Twitter data.

Public References

  • API docs: https://docs.xquik.com/api-reference/overview
  • MCP docs: https://docs.xquik.com/mcp/overview
  • Source repo: https://github.com/Xquik-dev/x-twitter-scraper

Workflow

  1. Clarify the data goal: search terms, account handles or IDs, time window, limits, and output format.
  2. Pick the smallest Xquik surface that fits: REST for direct calls, webhooks for delivery, MCP for agent tool access.
  3. Confirm the user has an Xquik API key or a configured MCP connection before writing runnable commands.
  4. Use the public docs for endpoint names, parameters, and response shapes. Do not invent fields.
  5. Keep examples scoped to public data and remove any sensitive user values before saving commands or logs.
  6. Summarize results with source URLs, request parameters, and any limits or filters applied.

REST Planning Pattern

  • For search tasks, map the user query to the documented search endpoint.
  • For user timelines, resolve the user identifier first, then fetch the documented timeline endpoint.
  • For repeated collection, define retry, rate limit, pagination, and export handling before running a batch.
  • For downstream automation, prefer webhooks when the user needs delivery into another system.

MCP Planning Pattern

  • Use MCP when an agent should call Xquik tools directly during a task.
  • Point setup work at https://docs.xquik.com/mcp/overview.
  • Verify the configured server name, key handling, and available tools before assuming a tool exists.
  • Keep the agent prompt explicit about the target account, query, limit, and expected output.

Safety Rules

  • Never paste or store API keys, cookies, or account sign-in material.
  • Do not claim access to private posts or private account data.
  • Do not describe private backend routing or infrastructure.
  • Do not fabricate pricing, endpoint names, response fields, or service limits.
  • If the docs do not cover a requested action, say it is not confirmed and propose the closest documented option.

Output Shape

When reporting a completed Xquik data task, include:

  • Goal and selected Xquik surface.
  • Query, account, endpoint family, and filters used.
  • Result count or delivery status.
  • Any pagination, retry, or export notes.
  • Links to the public docs used for setup or implementation.

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.