← 返回 Skills 市场
1431
总下载
0
收藏
9
当前安装
1
版本数
在 OpenClaw 中安装
/install x-monitor
功能描述
Monitor specific X/Twitter accounts and surface noteworthy tweets on a configurable schedule. Filters for high-value content about technology and trends, excluding political rage bait. Use when user wants to manage their X account list, run a manual check, or update filtering criteria.
安全使用建议
This skill appears to implement X monitoring but has a few issues you should resolve before installing: (1) Fix the path inconsistency — SKILL.md and scripts use two different base paths (~/.openclaw/workspace/x-monitor vs ~/.openclaw/workspace/skills/x-monitor). Confirm where credentials, handles, schedule, and last-check files will live. (2) The skill stores your X bearer token in plaintext under your home directory; restrict file permissions (chmod 600), consider using a secrets manager or environment-secret instead, and rotate the token if shared. (3) The agent will create cron jobs that schedule future agentTurn runs — review exactly what the scheduled payloads do and ensure you want recurring autonomous checks. (4) Test a manual run ('check x now') and inspect outputs and logs before enabling the schedule. If you want higher assurance, ask the author to correct the path inconsistencies and to document where scheduled jobs will run and which account identity they use.
功能分析
Type: OpenClaw Skill
Name: x-monitor
Version: 1.0.0
The OpenClaw AgentSkills bundle 'x-monitor' is classified as benign. All files (SKILL.md, scripts/setup-crons.sh, scripts/fetch-tweets.py, config/schedule.json, _meta.json) align with the stated purpose of monitoring X/Twitter accounts. The `SKILL.md` instructions for setting up cron jobs specify using an `agentTurn` payload, which is a message for the agent to interpret, rather than a direct shell command, mitigating prompt injection risks. The Python script (`fetch-tweets.py`) correctly uses the X API, reads credentials from a designated workspace file, and stores data within the skill's workspace, showing no signs of unauthorized data exfiltration, malicious execution, or persistence mechanisms.
能力评估
Purpose & Capability
The code and SKILL.md implement the described purpose (fetching tweets, filtering, scheduling). However there's a clear path inconsistency: fetch-tweets.py reads credentials/handles from ~/.openclaw/workspace/x-monitor/, while the cron setup and schedule.json locations in SKILL.md use ~/.openclaw/workspace/skills/x-monitor/config/schedule.json. This mismatch means scheduled jobs may not find credentials/handles or the script may not read the intended schedule, which is an incoherent design choice.
Instruction Scope
Instructions are generally scoped to the skill's purpose (store bearer token, list handles, configure schedule, create cron jobs). But the SKILL.md asks the agent to create cron jobs that post 'agentTurn' payloads (i.e., schedule future autonomous agent actions). That grants the skill recurring autonomous execution via the platform scheduler — expected for a monitor but worth noting. Also several paths in the docs differ (see purpose_capability), which could cause the agent to read/write unexpected locations or fail silently.
Install Mechanism
No install spec; the skill is instruction + scripts. There are no remote downloads or obscure installers. The Python script uses requests and local JSON files; the bash script only prints cron expressions. This is low risk from an install mechanism perspective.
Credentials
The only credential the skill needs is the X bearer token, which the SKILL.md asks you to store in a local credentials.json. The registry metadata lists no required env vars — consistent with file-based credentials. Storing a bearer token in plaintext under your home directory is functional but a security/privacy risk (consider file permissions or using a secrets store). There are no other unrelated credentials requested.
Persistence & Privilege
always:false and normal autonomous invocation are set. The skill instructs creating cron jobs that schedule agentTurn payloads, giving it persistent, recurring execution capability. This is reasonable for a monitor but increases the blast radius if the skill behaved unexpectedly; ensure you understand/approve the scheduled payloads before enabling them.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install x-monitor - 安装完成后，直接呼叫该 Skill 的名称或使用
/x-monitor触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of x-monitor: an automated tool for tracking high-value technology and trend tweets from selected X/Twitter accounts.
- Monitors specific X/Twitter handles and filters for noteworthy, non-political content.
- Configurable schedules via JSON (timezone, check times, enable/disable).
- Supports up to 10–20 handles; easy add/remove/list commands.
- Scheduled and manual reports include executive summaries and filtered tweet details.
- Criteria for noteworthy content customizable via markdown file.
- Cron jobs set up and updated based on schedule configuration.
- Handles API errors, rate limits, and invalid accounts gracefully.
元数据
常见问题
Monitor X posts 是什么？
Monitor specific X/Twitter accounts and surface noteworthy tweets on a configurable schedule. Filters for high-value content about technology and trends, excluding political rage bait. Use when user wants to manage their X account list, run a manual check, or update filtering criteria. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1431 次。
如何安装 Monitor X posts？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install x-monitor」即可一键安装，无需额外配置。
Monitor X posts 是免费的吗？
是的，Monitor X posts 完全免费（开源免费），可自由下载、安装和使用。
Monitor X posts 支持哪些平台？
Monitor X posts 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Monitor X posts？
由 vmathur（@vmathur）开发并维护，当前版本 v1.0.0。
推荐 Skills