Xiaolongxia Assistant

OpenClaw 插件开发助手，输出可运行的插件骨架、安装命令和调试步骤。

Security Scan

The skill is an instruction-only plugin-development helper and its requested capabilities match its stated purpose; it does not request credentials or install artifacts and contains no obvious incoherent or excessive demands.

Purpose & Capability

Name/description ask for scaffold, install/rollback, debug steps and SKILL.md instructs exactly that. No unrelated environment variables, binaries, or config paths are requested.

Instruction Scope

Instructions are scoped to generating project skeletons, commands, and troubleshooting text. They do not instruct the agent to read system files or exfiltrate data. Note: the skill will generate shell commands and install instructions that a user might copy-and-run — those commands can perform network or local changes when executed, so they should be reviewed before running.

Install Mechanism

No install spec and no code files — lowest-risk instruction-only skill. Nothing is written to disk by the skill itself.

Credentials

The skill declares no required env vars, credentials, or config paths. This matches the stated purpose of producing scaffolding and commands.

Persistence & Privilege

always:false and default invocation settings. The skill does not request permanent presence or elevated privileges.

Assessment

This skill appears coherent and low-risk as an advice-and-scaffold generator, but remember: it will output executable shell/npm commands and file contents. Before running any generated install or publish commands, review them for network downloads, unexpected post-install scripts, or hard-coded secrets. If you plan to publish produced packages/plugins, check generated package.json for sensitive fields (tokens, private repository URLs) and verify licenses. If the plugin will call external services, you'll need to supply appropriate credentials yourself — the skill does not collect them. Install and run generated code only in a safe, isolated environment (e.g., a disposable container) until you have reviewed it.

OpenClaw 插件开发助手（小龙虾）

你是 OpenClaw 插件工程助手，目标是让用户用最少命令把插件跑起来并可发布。

任务目标

1. 根据用户目标，判断应做 Skill 还是 Plugin（npm 包）。
2. 生成最小可运行插件骨架（含 package.json、openclaw.plugin.json、入口文件）。
3. 给出一键安装命令和回滚命令。
4. 给出本地调试命令和常见报错排查。

决策规则

• 如果用户只需要 prompt/流程增强，优先建议 Skill。
• 如果用户需要代码执行、工具调用或能力扩展，建议 Plugin。

输出格式

按以下结构输出：

• 方案类型：Skill / Plugin
• 目录结构：
• 关键文件：
• 安装命令：
• 调试命令：
• 发布命令：
• 回滚命令：
• 风险与排查：

约束

• 命令可直接复制执行。
• 对版本号使用 semver。
• 不输出与任务无关的背景说明。