← 返回 Skills 市场
251
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install yes-md
功能描述
Use when any task involves modifying files, configs, databases, or deployments. Use when debugging hits 2+ failures. Use when about to guess or assume withou...
安全使用建议
This skill is a governance checklist: coherent and focused on safe, evidence-backed changes. It does instruct the agent to run local shell commands and read files when used, so only enable or invoke it where the agent is allowed to access the target environment (preferably a staging sandbox). Because it's instruction-only and has no installs or credential requests, the main risk is operational — an agent with direct access to production could follow its commands and make changes. Review invocation policies and sandboxing, and try the skill in a controlled test environment before using it on production systems. Also note the skill has no homepage or publisher reputation metadata; if provenance matters, consider verifying the source or recreating the checklist internally.
功能分析
Type: OpenClaw Skill
Name: yes-md
Version: 1.1.1
The 'yes-md' skill is a governance framework designed to improve AI agent reliability and technical rigor. It enforces safety protocols such as mandatory file backups (e.g., using `cp` in SKILL.md), evidence-based diagnosis using standard tools (Bash, grep, curl), and post-fix verification. The instructions are aimed at reducing AI hallucinations and 'lazy' behaviors rather than executing unauthorized or harmful actions.
能力评估
Purpose & Capability
Name/description describe a guardrail/checklist for making safe changes. The SKILL.md contains exactly those procedures (backup, verification, blast-radius checks) and does not request unrelated resources, binaries, or credentials.
Instruction Scope
The instructions tell the agent to run local verification commands (cp, grep, lsof, curl, docker-compose checks, etc.) and to produce evidence before acting. Those actions are consistent with a 'safety/guidance' skill. It does ask the agent to read local files and run commands, but only in the context of verifying changes, which aligns with the stated purpose.
Install Mechanism
No install spec or code files are present. This is instruction-only, so nothing will be downloaded or written to disk by an installer.
Credentials
The skill does not request environment variables, credentials, or config paths. The actions it describes (reading local files, running shell checks) are proportional to its safety/verification purpose.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request permanent presence, nor does it instruct modification of other skills or global agent config.
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 - 安装完成后，直接呼叫该 Skill 的名称或使用
/yes-md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
v1.1.1
fix: quote name field to prevent YAML boolean parsing
v1.1.0
6-layer AI governance: format, trigger, hooks, anti-slack, gates, memory. Machine-enforced hooks that AI cannot bypass.
元数据
常见问题
YES.md 是什么？
Use when any task involves modifying files, configs, databases, or deployments. Use when debugging hits 2+ failures. Use when about to guess or assume withou... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 251 次。
如何安装 YES.md？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install yes-md」即可一键安装，无需额外配置。
YES.md 是免费的吗？
是的，YES.md 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
YES.md 支持哪些平台？
YES.md 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？
由 tkman（@sstklen）开发并维护，当前版本 v1.1.1。
推荐 Skills