← 返回 Skills 市场
200
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install openclaw-executing-plans
功能描述
Use when executing a written implementation plan in the current session with sequential task execution and review checkpoints - for when subagent-driven mode...
安全使用建议
This instruction-only skill appears coherent for executing written plans, but before installing you should: 1) confirm what 'read plan file' means in your environment (which files the agent may access); 2) review the referenced dependent skills (superpowers-isolated-workspace, verification, finishing-branch, etc.) to see what permissions or credentials they require; 3) avoid putting secrets or sensitive system paths into the plan content; and 4) test the skill in an isolated environment to observe what other skills it invokes and whether any unexpected file or network access occurs. If you need higher assurance, ask for the implementations or policies of the dependent skills before enabling this one.
功能分析
Type: OpenClaw Skill
Name: openclaw-executing-plans
Version: 1.0.0
The skill bundle provides a structured procedural framework for an AI agent to execute implementation plans sequentially. It includes safety-oriented instructions such as performing critical reviews, stopping on blockers to ask for clarification, and utilizing isolated workspaces (SKILL.md), with no evidence of malicious intent, data exfiltration, or unauthorized execution.
能力评估
Purpose & Capability
Name/description match the actual instructions: sequentially load/review/execute a plan and hand off to finishing/verification skills. It does not request unrelated credentials, binaries, or installs. Declaring dependent workflow skills (isolated workspace, verification, finishing-branch, etc.) is consistent with the stated goal.
Instruction Scope
The SKILL.md tells the agent to read a plan file, produce task lists, execute steps, run validations, and invoke other named skills. This is within scope, but the instructions are high-level and grant broad discretion (e.g., 'read plan file', '按指定运行验证', batch review cadence). That vagueness could let an agent access arbitrary session files or invoke other skills with different permissions — review how 'read plan file' is resolved and what the downstream skills do.
Install Mechanism
No install spec and no code files. Instruction-only skills carry minimal install risk because nothing is written to disk by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths. It does require other workflow skills, which themselves may request credentials; those should be evaluated separately.
Persistence & Privilege
always is false and the skill does not request persistent presence or to alter other skills' configs. It does rely on autonomous invocation (platform default) but that is normal and not by itself concerning.
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 openclaw-executing-plans - 安装完成后，直接呼叫该 Skill 的名称或使用
/openclaw-executing-plans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
OpenClaw-adapted skill for Superpowers development methodology.
元数据
常见问题
Executing Plans 是什么？
Use when executing a written implementation plan in the current session with sequential task execution and review checkpoints - for when subagent-driven mode... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 200 次。
如何安装 Executing Plans？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-executing-plans」即可一键安装，无需额外配置。
Executing Plans 是免费的吗？
是的，Executing Plans 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Executing Plans 支持哪些平台？
Executing Plans 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 Executing Plans？
由 AxelHu（@axelhu）开发并维护，当前版本 v1.0.0。
推荐 Skills