agentleFS
YangsonHungYangsonHung/awesome-agent-skills/skills/en/tweetclaw-twitter-automation/SKILL.md

tweetclaw-twitter-automation

Skill18 starsChanged 9 days agoMITView on GitHub

Guide agents through approved TweetClaw workflows for X/Twitter automation, including tweet scraping, reply search, follower export, user lookup, media, DMs, monitors, webhooks, giveaway draws, and confirmation-gated posts or replies.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    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 TweetClaw when a user asks an agent to work with X/Twitter through Xquik or the TweetClaw OpenClaw plugin.

    line 8
  2. Distinctive:

    Use this skill when the user asks for:

    line 12
  3. Distinctive:

    Do not use this skill for:

    line 23
  4. Distinctive:

    Check current docs before install, configuration, limits, or API details matter:

    line 34
  5. Distinctive:

    After install or update, verify the runtime before live work:

    line 44
  6. Distinctive:

    Keep credentials in the Xquik dashboard, OpenClaw plugin config, or environment-backed secret storage.

    line 51
  7. Distinctive:

    Use TweetClaw discovery or Xquik docs to choose the smallest endpoint and request limit that satisfies the user.

    line 52
  8. Distinctive:

    Before any visible, state-changing, private, paid, recurring, extraction, monitor, webhook, draw, or account-scoped action, summarize the …

    line 53
  9. Distinctive:

    Use TweetClaw when the user needs X/Twitter search from an agent.

    line 62
  10. Distinctive:

    Create a monitor only after the user confirms the account, keyword, or event target.

    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

TweetClaw Twitter Automation

Use TweetClaw when a user asks an agent to work with X/Twitter through Xquik or the TweetClaw OpenClaw plugin.

When to Use

Use this skill when the user asks for:

  • Scraping tweets, threads, replies, quotes, mentions, likes, or media
  • Searching tweets or tweet replies
  • Looking up users, followers, following, or verified followers
  • Posting tweets, replying to tweets, or uploading media after approval
  • Reading or sending direct messages after account authorization
  • Creating monitors, webhooks, or giveaway draws
  • Checking which TweetClaw or Xquik endpoint can perform a task

Do not use

Do not use this skill for:

  • Spam, harassment, deceptive engagement, impersonation, or platform evasion
  • Bulk unsolicited DMs, mass follows, mass likes, mass retweets, or engagement farming
  • X ads, analytics dashboards, or scheduling features that TweetClaw does not provide
  • Writing actions when only read-only access is configured
  • Accessing private or account-scoped data without clear user authorization
  • Asking users to paste API keys, signing keys, cookies, or tokens into chat

Instructions

  1. Restate the user job as one workflow: read, extraction, write, media, DM, monitor, webhook, draw, or discovery.
  2. Check current docs before install, configuration, limits, or API details matter:
  3. For OpenClaw installs, prefer the explicit npm selector:
openclaw plugins install npm:@xquik/tweetclaw
  1. After install or update, verify the runtime before live work:
openclaw plugins inspect tweetclaw --runtime --json
openclaw skills info tweetclaw
  1. Keep credentials in the Xquik dashboard, OpenClaw plugin config, or environment-backed secret storage. Never print or echo credential values.
  2. Use TweetClaw discovery or Xquik docs to choose the smallest endpoint and request limit that satisfies the user.
  3. Before any visible, state-changing, private, paid, recurring, extraction, monitor, webhook, draw, or account-scoped action, summarize the target, account, action, limits, data handling, and usage impact if available. Wait for explicit confirmation.
  4. For posting or replying, show the final text and media list before sending. Do not add links, mentions, hashtags, or claims the user did not request.
  5. For monitors and webhooks, state the target, event types, delivery behavior, and how the user can stop the resource.
  6. Return concise results with IDs, URLs, counts, and any partial failures.

Common Workflows

Search Tweets

Use TweetClaw when the user needs X/Twitter search from an agent. Keep the query narrow, choose a result limit, and summarize returned tweet IDs, URLs, authors, timestamps, and matched text.

Export Followers

Confirm the account or profile, the requested limit, and whether the user needs raw rows or a summary. Keep private account data scoped to the user's authorization.

Post a Tweet

Show the exact tweet text and attached media. Ask for confirmation before sending. Report the created tweet URL after the action succeeds.

Monitor Activity

Create a monitor only after the user confirms the account, keyword, or event target. Explain what will be watched and how results will be delivered.

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.