← 返回 Skills 市场
88
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install nm-gauntlet-onboard
功能描述
Guided onboarding path through five stages: big picture, core domain, interfaces, patterns, and hardening
安全使用建议
This skill is instruction-only and appears coherent with its stated goal: it guides a developer through onboarding stages and requests no credentials or installs. It's low-risk to add, but note it is high-level: it presumes the agent or platform will store/track progress (no storage mechanism is specified). If you see a future version that adds an install step, requests environment variables, or instructs the agent to read files or send data to external endpoints, re-evaluate before enabling it.
功能分析
Type: OpenClaw Skill
Name: nm-gauntlet-onboard
Version: 1.0.0
The skill bundle contains only metadata and documentation (SKILL.md) for a structured developer onboarding process. There is no executable code, no instructions for sensitive data access, and no evidence of malicious intent or prompt injection; it simply defines a workflow for guiding users through a codebase.
能力评估
Purpose & Capability
Name/description describe a guided onboarding flow and the SKILL.md contains only staging and step-by-step onboarding instructions. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
Instructions are limited to presenting stages, challenges, hints, and progress tracking. The doc mentions actions like 'Load onboarding progress' and 'Track mastery' but does not specify reading system files, env vars, or external endpoints; this implies use of agent-internal state rather than accessing external secrets. The wording is slightly high-level/vague about where progress is stored, but not incoherent with its purpose.
Install Mechanism
No install spec and no code files — instruction-only skill. No downloads, package installs, or filesystem writes are declared.
Credentials
The skill declares no required environment variables, credentials, or config paths; nothing in the instructions requests secrets or external service access.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills' configuration. Autonomous invocation is allowed (platform default) but is not combined with broad privileges here.
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 nm-gauntlet-onboard - 安装完成后，直接呼叫该 Skill 的名称或使用
/nm-gauntlet-onboard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 "onboard" skill for guided developer onboarding.
- Supports a structured five-stage path: big picture, core domain, interfaces, patterns, and hardening.
- Tracks onboarding progress, mastery (correct twice), and advancement (80%+ over 10+ challenges).
- Provides hints on first attempt and summarizes stage progress.
- Includes graduation step, transitioning to the regular gauntlet with answer history retained.
元数据
常见问题
Nm Gauntlet Onboard 是什么？
Guided onboarding path through five stages: big picture, core domain, interfaces, patterns, and hardening. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 88 次。
如何安装 Nm Gauntlet Onboard？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nm-gauntlet-onboard」即可一键安装，无需额外配置。
Nm Gauntlet Onboard 是免费的吗？
是的，Nm Gauntlet Onboard 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Nm Gauntlet Onboard 支持哪些平台？
Nm Gauntlet Onboard 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 Nm Gauntlet Onboard？
由 athola（@athola）开发并维护，当前版本 v1.0.0。
推荐 Skills