← 返回 Skills 市场

X Alive

Name: X Alive
Author: kitakitsune0x

作者 kitakitsune0x · GitHub ↗ · v0.1.0

cross-platform ⚠ suspicious

524

总下载

当前安装

版本数

在 OpenClaw 中安装

/install x-alive

功能描述

Bring your AI agent to life on X/Twitter. Complete toolkit for launching, growing, and maintaining an authentic AI presence — organic replies, trend awarenes...

安全使用建议

This skill is a playbook for running an AI persona on X and is generally coherent with that goal, but it has two red flags you should address before installing: (1) the registry metadata lists no credentials or config paths, while the SKILL.md requires X API keys (OAuth 1.0a credentials and a Bearer token) and instructs putting a Bearer token into ~/.config/env/global.env — verify and prefer a scoped, agent-specific secret store rather than a global file; (2) the skill depends on third‑party tools (xurl, x-research) and links to external repos — review those projects' source and permissions before installing. Also review any local agent files the skill will read (SOUL.md, IDENTITY.md, AGENTS.md) so they don't contain unrelated secrets. If you can't verify xurl/x-research or confirm where tokens will be stored and who can access them, treat this as potentially risky and consider sandbox testing or requiring the skill's manifest to declare required env vars and config paths before use.

功能分析

Type: OpenClaw Skill Name: x-alive Version: 0.1.0 The skill instructs the AI agent to perform network calls to `api.x.com` (via `curl` and implicitly `xurl`/`x-research`) and to read local files such as `SOUL.md`, `IDENTITY.md`, `AGENTS.md`, and `~/.config/env/global.env` for sensitive tokens. It also relies on external CLI tools and other skills, implying execution of external processes. While these capabilities are necessary for its stated purpose of managing an X/Twitter presence, they introduce potential attack surfaces (e.g., prompt injection to bypass safety instructions or vulnerabilities in dependencies). However, both `SKILL.md` and `README.md` contain explicit and strong safety instructions forbidding data exfiltration, financial scams, and sharing of sensitive information, indicating a clear intent against malicious behavior.

能力评估

✓ Purpose & Capability

The skill's name and description match the runtime instructions: it is a playbook for operating an AI identity on X/Twitter and therefore legitimately needs X API access and tools for reading timelines and posting. The overall capability is coherent with the stated purpose.

⚠ Instruction Scope

The SKILL.md explicitly instructs the agent/human to install and use xurl and x-research, to configure OAuth 1.0a and a Bearer token, and to read agent config files (SOUL.md, IDENTITY.md, AGENTS.md, etc.). It also instructs storing a Bearer token in ~/.config/env/global.env and fetching user tweets for dedup checks. Reading agent config files and a global env file may expose unrelated secrets; the skill gives broad discretion to read local identity files rather than listing exactly which files/keys are required.

ℹ Install Mechanism

There is no install spec or code — low disk/write risk. However the skill prescribes third-party tools (xurl and x-research) and linking to external repos. Those dependencies are out-of-band and should be reviewed separately before use.

⚠ Credentials

Registry metadata declares no required env vars or config paths, but the documentation asks for OAuth 1.0a credentials and a Bearer token (X_BEARER_TOKEN) and instructs placing it in ~/.config/env/global.env. This mismatch (undisclosed credentials required) is a proportionality/visibility problem. The skill also tells the agent to read agent-local identity files that may contain secrets—reasonable for identity but not documented in the metadata.

✓ Persistence & Privilege

The skill is instruction-only and does not request always:true or other elevated persistence. It does not claim to modify other skills or global agent settings. Autonomous invocation is allowed by default but not unusual.

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-alive
安装完成后，直接呼叫该 Skill 的名称或使用 /x-alive 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

v0.1.0

x-alive 0.1.0 – Initial Release - Launches a toolkit for AI agents to build and maintain authentic presence on X/Twitter. - Provides setup instructions for API access, agent identity configuration, and regular engagement loops. - Introduces principles for organic replies, trend awareness, and strict deduplication to ensure authentic interactions. - Outlines strategies for content sourcing, engagement, and following growth through genuine participation. - Prioritizes safety and human oversight for sensitive interactions, mentions, and DMs. - Emphasizes real-time, non-scheduled posting and replying based on relevance, not timers.

元数据

Slug x-alive

版本 0.1.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题

X Alive 是什么？

Bring your AI agent to life on X/Twitter. Complete toolkit for launching, growing, and maintaining an authentic AI presence — organic replies, trend awarenes... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 524 次。

如何安装 X Alive？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install x-alive」即可一键安装，无需额外配置。

X Alive 是免费的吗？

是的，X Alive 完全免费（开源免费），可自由下载、安装和使用。

X Alive 支持哪些平台？

X Alive 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 X Alive？

由 kitakitsune0x（@kitakitsune0x）开发并维护，当前版本 v0.1.0。