本文へ移動
cccskills
無料GitHub で公開

tweetclaw

Use TweetClaw as an OpenClaw plugin for X/Twitter automation: search tweets, search tweet replies, post tweets/replies, export followers, look up users, handle media, monitor tweets, deliver webhooks, run giveaway draws, and manage approval-gated visible actions.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.9 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

TweetClaw

TweetClaw is an OpenClaw plugin for X/Twitter automation through Xquik. Use it when a user wants an agent workflow that needs platform-native X/Twitter data or actions instead of a general web search or browser-only posting flow.

GitHub: Xquik-dev/tweetclaw npm: @xquik/tweetclaw ClawHub: xquik-tweetclaw

When To Use This Skill

  • Search tweets, search tweet replies, inspect threads, or look up users.
  • Export followers, following, list members, community members, or reply authors.
  • Upload media, download authenticated media, or prepare gallery links.
  • Create monitors, read monitor events, or deliver webhook notifications.
  • Run giveaway draws with reply, follow, retweet, keyword, and uniqueness filters.
  • Post tweets, post tweet replies, like, retweet, follow, DM, or update profiles only after the user explicitly approves the visible action.

Setup

Install the OpenClaw plugin:

openclaw plugins install @xquik/tweetclaw
openclaw gateway restart

TweetClaw can be installed before credentials are configured. The free explore tool remains available and live calls return setup guidance until the user adds an API key or an MPP signing key.

Configure account-backed X automation:

openclaw config set plugins.entries.tweetclaw.config.apiKey "$XQUIK_API_KEY"

Optional MPP pay-per-use reads:

npm i mppx viem
openclaw config set plugins.entries.tweetclaw.config.tempoSigningKey "$MPP_SIGNING_KEY"

Keep API keys and signing keys out of prompts, shell history, screenshots, and shared documents. Prefer environment-variable commands so OpenClaw writes local configuration without exposing secrets to the chat.

Core Workflow

  1. Use explore to find the right Xquik endpoint by category, keyword, or workflow.
  2. Check whether the endpoint is read-only, MPP-eligible, account-backed, or a visible write action.
  3. For reads, call tweetclaw with the selected path, method, query, and body.
  4. For posts, replies, follows, DMs, monitor changes, webhooks, profile updates, media uploads, and destructive actions, show the exact request and wait for explicit user approval before calling tweetclaw.
  5. Preserve returned IDs, cursors, monitor IDs, webhook IDs, draw IDs, and export links exactly as strings.

Example Prompts

Search tweets and tweet replies about this product launch, then summarize the
top objections with links to the strongest examples.
Export followers for @example, find likely developer advocates, and prepare a
CSV-ready shortlist with usernames and profile notes.
Draft a reply to this tweet. Do not post it until I approve the exact text.
Run a giveaway draw from this tweet URL. Require a retweet, unique authors, and
3 winners.

Guardrails

  • Never ask for X login credentials. Use the user's Xquik API key or MPP setup.
  • Treat posting, replying, liking, retweeting, following, DMs, profile edits, monitor changes, webhooks, and media actions as approval-gated.
  • Use exact string IDs for tweets, users, media, monitors, webhooks, draws, and extraction jobs.
  • Use pagination cursors as opaque strings. Do not invent cursors.
  • Retry only rate limits and server errors with bounded backoff. Do not retry validation, authorization, payment, or not-found errors without changing the request.
  • Use the Xquik billing guide for current plans, endpoint eligibility, and operation costs.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6322026年10月12日 更新

Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6322026年10月12日 更新

Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6322026年10月12日 更新

Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6322026年10月12日 更新

Audit whether a website can be found, crawled, and cited by AI answer engines such as ChatGPT Search, Perplexity, Google AI Overviews, and Microsoft Copilot. Use when someone asks why their brand is missing from AI answers, whether AI crawlers can read their site, how to get cited by ChatGPT or Perplexity, or asks for a GEO or AEO (generative / answer engine optimization) review. Produces a citation baseline across buyer-intent prompts, a crawler-access check, a citability review of named pages, and a ranked fix list. Not for keyword rank tracking, paid search, or pages behind a login.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6322026年10月12日 更新

Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.

日本語の概要は準備中です。原文の説明を表示しています。

davepoon/buildwithclaude3,6322026年10月12日 更新

davepoon のスキルをすべて見る

このスキルの問題を報告する