← 返回 Skills 市场
谋道
作者
ks1291665853-sketch
· GitHub ↗
· v1.1.0
· MIT-0
104
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install moudao
功能描述
谋道 - 基于「道法术器」框架的AI规划专家。把任何想法变成可执行方案。支持前期调研、快速方案生成、深度规划(天时地利人和×道法术器)、迭代诊断。当用户需要:制定计划、规划项目、拆解目标、创业咨询、职业发展、学习路径规划时使用此skill。
安全使用建议
This skill appears to be a legitimate AI planning tool, but there are a few things to check before installing: 1) The package metadata claims no required env vars, but the README and code expect a DeepSeek API key (DEEPSEEK_API_KEY) — do not provide sensitive keys unless you trust the author and endpoint. 2) The script sends your input to an external LLM (https://api.deepseek.com by default); review whether you are comfortable having your prompts and any contextual data transmitted there. 3) The SKILL.md contains forceful 'strict JSON' and system-style instructions (prompt-override patterns) — that can influence model behavior in ways that bypass expected agent safeguards. 4) If you plan to run the included node script, inspect the entire scripts/moudao.js locally (search for any code paths that read files or accept an arbitrary baseUrl/api key from untrusted input) and consider running it in an isolated environment. 5) Ask the publisher to clarify required environment variables and to correct the skill manifest metadata. If you cannot verify the endpoint or the publisher, treat API keys and sensitive input cautiously and prefer not to install or run the skill with real secrets.
功能分析
Type: OpenClaw Skill
Name: moudao
Version: 1.1.0
The 'moudao' skill bundle is a legitimate AI-driven planning tool based on the 'Dao, Fa, Shu, Qi' framework. The core logic in `scripts/moudao.js` is a clean Node.js implementation that interacts with the DeepSeek LLM API to perform market research and generate structured execution plans. It uses standard environment variables for API configuration, lacks external dependencies, and contains no evidence of data exfiltration, malicious command execution, or prompt injection. The pricing mention in `SKILL.md` is purely informational and does not involve any functional payment exploitation.
能力评估
Purpose & Capability
The skill claims to be an AI planning assistant and includes a Node.js script that calls an LLM to perform research and generate plans — that capability aligns with the stated purpose. However, the README and the script indicate the need for a DeepSeek API key, while the registry metadata declares no required env vars or primary credential. This mismatch between claimed requirements and actual code is inconsistent and unexplained.
Instruction Scope
The SKILL.md and scripts instruct the agent to run scripts/moudao.js which performs network calls to an external LLM endpoint. The SKILL.md contains repeated 'strictly return JSON' / system-prompt-like directives (the pre-scan flagged 'system-prompt-override'), which are powerful instructions to an LLM and can act as prompt-injection. The instructions do not tell the agent to read arbitrary local files, and the visible code does not import filesystem modules, but the strong system-prompt directives and the ability to send user data to an external API expand the surface for unintended data exfiltration.
Install Mechanism
There is no install spec (instruction-only behavior) and the package merely includes a Node.js script. No downloads from untrusted URLs or archive extraction are present. Risk is limited to executing the included script (node scripts/moudao.js) which will perform network requests.
Credentials
Registry metadata reports no required environment variables, but README and the code indicate the script expects an API key (README: DEEPSEEK_API_KEY; code uses an Authorization Bearer header and references process.env.LLM_MODEL). Requesting an LLM API key is expected for an LLM-backed skill, but the metadata omission is misleading. The skill therefore asks for credentials (API key) that are not declared in the skill manifest — that inconsistency is a red flag because users may supply secrets unaware of where they are sent.
Persistence & Privilege
The skill does not request 'always: true', does not declare system-level config paths, and there is no evidence it modifies other skills or system-wide settings. It requires network access to an external API but does not request persistent elevated platform privileges.
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 moudao - 安装完成后,直接呼叫该 Skill 的名称或使用
/moudao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
v1.1.0
v1.1.0: 新增前期调研模块,支持 --research 模式
v1.0.0
moudao 1.0.0
- 首次发布:基于「道法术器」中国传统认知框架,为各类目标提供AI生成的可执行规划方案
- 支持快速方案、一对一智能引导提问、深度系统规划和方案执行的迭代诊断
- 多种输出格式:JSON、Markdown、纯文本
- 明确参数控制,适用创业、职业发展、学习、生活等多场景
- 详细用法与示例,附完整输出结构和案例参考
元数据
常见问题
谋道 是什么?
谋道 - 基于「道法术器」框架的AI规划专家。把任何想法变成可执行方案。支持前期调研、快速方案生成、深度规划(天时地利人和×道法术器)、迭代诊断。当用户需要:制定计划、规划项目、拆解目标、创业咨询、职业发展、学习路径规划时使用此skill。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 104 次。
如何安装 谋道?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install moudao」即可一键安装,无需额外配置。
谋道 是免费的吗?
是的,谋道 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
谋道 支持哪些平台?
谋道 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 谋道?
由 ks1291665853-sketch(@ks1291665853-sketch)开发并维护,当前版本 v1.1.0。
推荐 Skills