Twitter Monitor
Apps & Automationtwitter-monitorTwitter Monitor is an Agent Skill for apps & automation published in the kangarooking/kangarooking-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Fetch recent posts from one or more X/Twitter accounts through twitterapi.io, output structured JSON/CSV records, optionally sync records to Feishu/Lark Bitable through feishu-cli, and optionally guide recurring execution through OpenClaw, Codex automations, cron, or launchd. Use when the user wants to monitor X bloggers, collect recent tweets, export tweet metrics, append tweets to Feishu Bitable, or set up a scheduled Twitter/X account tracking workflow.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/kangarooking/kangarooking-skills/blob/HEAD/twitter-monitor/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/twitter-monitor, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Twitter Monitor
Workflow
Use this skill as an execution workflow, not as a long-running daemon. First complete a one-shot fetch, then offer optional Feishu sync and scheduling only when useful.
- Ask for X/Twitter account ids when missing. Accept handles such as
sama,@sama, profile URLs, or multiple comma-separated ids. - Ask the user to provide or configure a
twitterapi.ioAPI key whenTWITTER_API_KEYis unavailable. Do not write API keys into files committed to a repository. - Confirm pagination depth. Default to
--pages 1; use a larger number only when the user asks for more history or accepts higher API usage. - Run
scripts/twitter_monitor.pyand generate JSON or CSV output. - If the user wants Feishu/Lark Bitable output, follow
references/feishu-output.md. - After the one-shot command works, ask whether they want recurring execution. If yes, follow
references/scheduling.md, including OpenClaw when appropriate.
Quick Start
From this skill directory:
export TWITTER_API_KEY="..."
python scripts/twitter_monitor.py --accounts sama --pages 1 --format json
For multiple accounts:
python scripts/twitter_monitor.py --accounts sama,elonmusk,OpenAI --pages 1 --format csv
For a JSON account list:
python scripts/twitter_monitor.py --accounts-file assets/accounts.example.json --pages 1
Read references/twitterapi-setup.md when the user needs API key setup, account input examples, or command variants.
Output Schema
The script writes one record per tweet with these fields:
推文内容日期推文链接推文ID作者作者ID阅读量点赞数转发数评论数收藏数是否回复抓取时间
Deduplicate by 推文ID before appending to any durable destination.
Feishu
Do not require Feishu configuration for normal fetches. Only enter the Feishu workflow when the user asks to write, append, or sync records to Feishu/Lark Bitable.
Prefer feishu-cli over hard-coded Feishu app credentials. If feishu-cli is missing, ask whether to install and configure it. See references/feishu-output.md for the field mapping and sync rules.
Scheduling
Offer scheduling only after a successful one-shot fetch or when the user explicitly asks for ongoing monitoring.
Prefer OpenClaw when the user wants an agent-managed recurring job or already uses OpenClaw. Otherwise choose Codex automations, cron, or launchd based on the runtime environment. See references/scheduling.md.
Safety
Never commit real API keys, Feishu tokens, output files containing private monitoring data, or local status caches. Keep secrets in environment variables, secret managers, or the user's existing CLI auth.