← 返回 Skills 市场
249
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install yes-md-ja
功能描述
ファイル・設定・データベース・デプロイの変更を伴うタスクで発動。デバッグが2回以上連続で失敗した時に発動。証拠なしに推測・仮定しようとした時に発動（「おそらく」「多分」「〜だと思う」「〜のはず」）。ユーザーに丸投げしようとした時に発動（「ご確認ください」「手動で対応してください」「〜が必要かもしれません」）。修正...
安全使用建议
This skill is a conservative, evidence-first checklist for debugging and making safe changes and appears internally consistent. It will expect the agent to be able to run shell commands, read files, and perform WebSearches — capabilities that can expose sensitive local data if the agent is allowed full filesystem or network access. If you plan to enable it, ensure the agent runs in an environment where those actions are appropriate (sandboxed or limited access) and that you trust the agent's execution context; otherwise the skill is safe but may be unable to perform all checks.
功能分析
Type: OpenClaw Skill
Name: yes-md-ja
Version: 1.1.0
The skill bundle 'yes-md-ja' is a set of engineering guidelines and behavioral constraints designed to improve the reliability and thoroughness of an AI agent. It enforces best practices such as mandatory backups before file edits, evidence-based debugging using standard tools (bash, grep, curl), and post-fix verification, with no evidence of malicious intent or data exfiltration logic in SKILL.md or _meta.json.
能力评估
Purpose & Capability
The skill is a rules-and-checklist engine for safe debugging, edits, and deployments; the commands and checks it describes (cp for backups, grep/lsof/env/node -v/curl for verification, WebSearch for research) are appropriate and proportional to that purpose.
Instruction Scope
SKILL.md instructs the agent to run shell commands and read configuration/log files and to use WebSearch. This is expected for a change-safety governance skill, but it assumes the agent has filesystem and network tooling available — if the agent environment lacks or restricts these capabilities, the skill cannot fully operate.
Install Mechanism
No install spec and no code files — the skill is instruction-only, which minimizes installation risk (nothing is downloaded or written to disk by the skill itself).
Credentials
The skill declares no required environment variables, credentials, or config paths. While it suggests using env/cat/grep/etc. to gather evidence, it does not demand secrets or unrelated credentials, so requested access is proportional to its stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges or modify other skills; autonomous invocation is allowed by default but not elevated 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 yes-md-ja - 安装完成后，直接呼叫该 Skill 的名称或使用
/yes-md-ja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
YES.md 日本語版：6層AIガバナンス、機械強制フック付き
元数据
常见问题
YES.md 日本語版 是什么？
ファイル・設定・データベース・デプロイの変更を伴うタスクで発動。デバッグが2回以上連続で失敗した時に発動。証拠なしに推測・仮定しようとした時に発動（「おそらく」「多分」「〜だと思う」「〜のはず」）。ユーザーに丸投げしようとした時に発動（「ご確認ください」「手動で対応してください」「〜が必要かもしれません」）。修正... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 249 次。
如何安装 YES.md 日本語版？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install yes-md-ja」即可一键安装，无需额外配置。
YES.md 日本語版 是免费的吗？
是的，YES.md 日本語版 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
YES.md 日本語版 支持哪些平台？
YES.md 日本語版 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 YES.md 日本語版？
由 tkman（@sstklen）开发并维护，当前版本 v1.1.0。
推荐 Skills