← 返回 Skills 市场
100
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install nm-conserve-decisive-action
功能描述
Guidance on when to ask clarifying questions vs proceed with standard approaches. Reduces unnecessary interaction rounds
安全使用建议
This is a low-risk, instruction-only skill that provides heuristics for asking vs acting. Before enabling it for autonomous agents, confirm the agent's execution permissions (so it cannot perform destructive git/file operations without your consent), ensure backups/repos exist for reversibility, and verify agent policies for confirmations on irreversible actions. If you want extra safety, require manual approval for actions that the skill would classify as 'irreversible' or 'security-critical.'
功能分析
Type: OpenClaw Skill
Name: nm-conserve-decisive-action
Version: 1.0.0
The skill bundle contains only metadata and markdown instructions (SKILL.md) designed to guide an AI agent's decision-making process regarding when to ask for clarification versus proceeding autonomously. It includes explicit safety guidelines that mandate user confirmation for destructive, security-critical, or irreversible operations, and contains no executable code or malicious patterns.
能力评估
Purpose & Capability
The name/description match the SKILL.md content: the document provides heuristics and examples for asking vs acting. It does not request unrelated credentials, binaries, or system access.
Instruction Scope
SKILL.md stays within scope: it is text guidance and examples about decision thresholds, previews, dry-runs, and safe use of git/backups. References to git stash, branches, copying files, and previews are appropriate given the goal of safe autonomous action and are phrased as recommended safety mechanisms, not as hidden steps to exfiltrate data.
Install Mechanism
No install spec and no code files are present, so nothing will be written to disk or fetched at install time.
Credentials
The skill declares no environment variables, credentials, or config paths. The SKILL.md does not ask for secrets or unrelated service keys.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request permanent presence or 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 nm-conserve-decisive-action - 安装完成后，直接呼叫该 Skill 的名称或使用
/nm-conserve-decisive-action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 the decisive-action skill, providing clear guidance on when to ask clarifying questions versus when to proceed autonomously.
- Outlines checklists and decision matrices for balancing efficiency with risk in workflows.
- Includes practical examples, anti-patterns, and safety mechanisms to encourage confident, streamlined operation.
- Aims to reduce unnecessary interaction rounds and improve decision-making in routine and ambiguous scenarios.
元数据
常见问题
Nm Conserve Decisive Action 是什么？
Guidance on when to ask clarifying questions vs proceed with standard approaches. Reduces unnecessary interaction rounds. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 100 次。
如何安装 Nm Conserve Decisive Action？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nm-conserve-decisive-action」即可一键安装，无需额外配置。
Nm Conserve Decisive Action 是免费的吗？
是的，Nm Conserve Decisive Action 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Nm Conserve Decisive Action 支持哪些平台？
Nm Conserve Decisive Action 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 Conserve Decisive Action？
由 athola（@athola）开发并维护，当前版本 v1.0.0。
推荐 Skills