agentleFS
frankxaifrankxai/starlight-automation-agent-skills/skills/xquik-public-x-data/SKILL.md

xquik-public-x-data

Skill0 starsChanged 3 months agoMITView on GitHub

Route public X data automation work through Xquik REST, MCP, webhooks, exports, monitors, and SDK or skill handoffs. Use when a user asks for X or Twitter search, profile lookup, followers, trends, monitor events, webhook delivery, MCP agent access, no-code workflow handoff, or recurring public-source social data collection with Xquik.

The file

Show its rules and text

We split this skill into the rules it gives an agent

17 rules. About 0 are common, 17 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Use this skill when public X data belongs in an automation plan and Xquik is an available source.

    line 8
  2. Distinctive:

    Keep the plan public-safe, opt-in, and scoped to the documented Xquik surfaces.

    line 9
  3. Distinctive:

    Check current public docs before giving endpoint-specific instructions:

    line 13
  4. Distinctive:

    Do not guess endpoint names, request fields, pricing, limits, or authentication details.

    line 21
  5. Distinctive:

    If the docs do not confirm a capability, mark it as unavailable or ask for a source-backed check.

    line 22
  6. Distinctive:

    Use REST when an app needs direct reads such as tweet search, profile lookup, timelines, followers, trends, or extraction status.

    line 28
  7. Distinctive:

    Use MCP when an AI agent needs to explore the API catalog or run authenticated Xquik operations from an agent session.

    line 29
  8. Distinctive:

    Use webhooks when a downstream system needs event delivery from monitors or workflow notifications.

    line 30
  9. Distinctive:

    Use exports when a workflow needs CSV, JSON, Markdown, PDF, TXT, or spreadsheet handoff from extraction or giveaway draw results.

    line 31
  10. Distinctive:

    Use monitors when the job needs recurring account or keyword event capture instead of repeated manual polling.

    line 32
  11. Distinctive:

    Use the Xquik skill or SDK route when an agent or codebase needs reusable implementation guidance.

    line 33
  12. Distinctive:

    Prefer a native connector first when the target automation platform already has one.

    line 35
  13. Distinctive:

    Before proposing a workflow, collect:

    line 39
  14. Distinctive:

    Do not print or commit API keys, bearer tokens, webhook secrets, cookies, customer data, private memory, or live webhook URLs.

    line 68
  15. Distinctive:

    Use placeholders for public examples.

    line 70
  16. Distinctive:

    Do not help evade platform rules, rate limits, access controls, or account restrictions.

    line 72
  17. Distinctive:

    Keep unsupported operations on the documented fallback route rather than inventing a hidden capability.

    line 74

≈ “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 Public X Data

Use this skill when public X data belongs in an automation plan and Xquik is an available source. Keep the plan public-safe, opt-in, and scoped to the documented Xquik surfaces.

Source Truth

Check current public docs before giving endpoint-specific instructions:

  • https://docs.xquik.com/llms.txt
  • https://docs.xquik.com/api-reference/overview
  • https://docs.xquik.com/mcp/overview
  • https://docs.xquik.com/guides/workflows
  • https://github.com/Xquik-dev/x-twitter-scraper

Do not guess endpoint names, request fields, pricing, limits, or authentication details. If the docs do not confirm a capability, mark it as unavailable or ask for a source-backed check.

Route Selection

Choose the narrowest useful route:

  1. Use REST when an app needs direct reads such as tweet search, profile lookup, timelines, followers, trends, or extraction status.
  2. Use MCP when an AI agent needs to explore the API catalog or run authenticated Xquik operations from an agent session.
  3. Use webhooks when a downstream system needs event delivery from monitors or workflow notifications.
  4. Use exports when a workflow needs CSV, JSON, Markdown, PDF, TXT, or spreadsheet handoff from extraction or giveaway draw results.
  5. Use monitors when the job needs recurring account or keyword event capture instead of repeated manual polling.
  6. Use the Xquik skill or SDK route when an agent or codebase needs reusable implementation guidance.

Prefer a native connector first when the target automation platform already has one. Use generic HTTP only when no native connector exists or the native route cannot express the documented operation.

Intake Checklist

Before proposing a workflow, collect:

  • objective and audience
  • public source target, such as query, username, tweet URL, list, community, or region
  • freshness requirement
  • output format and destination
  • authentication owner
  • retry, pagination, and cursor handling needs
  • approval gate for posting, deletion, spending, account changes, or production activation
  • validation method using mock inputs or a small public-safe sample

Output Shape

Return:

  • selected Xquik route
  • why that route wins
  • fallback route
  • required public docs to verify
  • inputs
  • output contract
  • auth and secret-handling note
  • pagination or replay plan
  • approval gate
  • validation command or manual check
  • durable state location

Safety

  • Do not print or commit API keys, bearer tokens, webhook secrets, cookies, customer data, private memory, or live webhook URLs.
  • Store webhook secrets in a secret manager. Verify X-Xquik-Signature against the raw request body before processing each webhook.
  • Use placeholders for public examples.
  • Share documented public pricing and usage limits when needed for approval. Do not disclose private provider names, source details, non-public cost mechanics, or internal routing.
  • Do not help evade platform rules, rate limits, access controls, or account restrictions.
  • Require human approval before posting, deleting, sending DMs, changing accounts, spending, creating or reactivating metered monitors, or enabling production monitors and webhooks.
  • Keep unsupported operations on the documented fallback route rather than inventing a hidden capability.

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.