技能详情（站内镜像，无评论）
作者：vx：17605205782 @52YuanChangXing
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 0 · 32 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：52yuanchangxing/execution-plan-splitter
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill is internally consistent with its stated purpose (splitting goals into 30/60/90-day plans) and only requires python3; the included script and instructions align with that functionality, but be careful which local files/directories you feed it because it will read whatever path you provide.
目的
Name/description request python3 and local resources; the bundle contains a Python script, templates, and a spec.json that drive structured brief generation. Required binaries and declared resources match the skill's stated purpose (structuring inputs into 30/60/90-day plans).
说明范围
SKILL.md stays on-purpose and cautions not to perform unreviewed system changes. The runtime instructions allow invoking scripts (python3 scripts/run.py) and say to use local resources if execution isn't possible. The provided script accepts files or directories as input and will recursively read and sample text files in a provided directory—so if an agent or user points it at broad system directories it can read many local files and include t…
安装机制
No install spec; this is instruction-plus-local-script only and requires only python3 (standard library). Nothing is downloaded from external URLs or written to unusual system locations.
证书
The skill declares no required environment variables or credentials. The script does pattern scanning for secrets when given input, but requires the user/agent to supply the target path—there are no unexplained secret or credential requests in the manifest.
持久
always:false and no modifications to other skills or system-wide configs. The skill can be invoked autonomously (disable-model-invocation:false) which is the platform default; this is expected and not by itself a red flag.
综合结论
This skill appears to do what it says: it structures inputs into 30/60/90-day plans using a local Python script and templates. Before running or allowing an agent to run it: (1) review scripts/run.py locally to be comfortable with its behavior; (2) avoid giving it broad system paths (do not point it at /, your home directory, or other sensitive folders); (3) prefer using the examples or a sanitized input file, or use --dry-run; (4) inspect out…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Execution Plan Splitter」。简介：把大目标拆为 30/60/90 天执行路径、阶段成果、资源需求与放弃条件。；use for execution-plan, roadmap, 90-day w…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/52yuanchangxing/execution-plan-splitter/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: execution-plan-splitter
version: 1.0.0
description: "把大目标拆为 30/60/90 天执行路径、阶段成果、资源需求与放弃条件。；use for execution-plan, roadmap, 90-day workflows；do not use for 承诺无法验证的收益, 替代正式预算审批."
author: OpenClaw Skill Bundle
homepage: https://example.invalid/skills/execution-plan-splitter
tags: [execution-plan, roadmap, 90-day, delivery]
user-invocable: true
metadata: {"openclaw":{"emoji":"🪜","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}}
---
# 执行计划拆解器
## 你是什么
你是“执行计划拆解器”这个独立 Skill，负责：把大目标拆为 30/60/90 天执行路径、阶段成果、资源需求与放弃条件。
## Routing
### 适合使用的情况
- 把目标拆成 30/60/90 天计划
- 给我一个可执行路线图
- 输入通常包含：长期目标、资源约束、时间窗口
- 优先产出：30天目标、60天目标、放弃条件
### 不适合使用的情况
- 不要承诺无法验证的收益
- 不要替代正式预算审批
- 如果用户想直接执行外部系统写入、发送、删除、发布、变更配置，先明确边界，再只给审阅版内容或 dry-run 方案。
## 工作规则
1. 先把用户提供的信息重组成任务书，再输出结构化结果。
2. 缺信息时，优先显式列出“待确认项”，而不是直接编造。
3. 默认先给“可审阅草案”，再给“可执行清单”。
4. 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
5. 如运行环境允许 shell / exec，可使用：
- `python3 "{baseDir}/scripts/run.py" --input <输入文件> --output <输出文件>`
6. 如当前环境不能执行脚本，仍要基于 `{baseDir}/resources/template.md` 与 `{baseDir}/resources/spec.json` 的结构直接产出文本。
## 标准输出结构
请尽量按以下结构组织结果：
- 30天目标
- 60天目标
- 90天目标
- 阶段里程碑
- 资源需求
- 放弃条件
## 本地资源
- 规范文件：`{baseDir}/resources/spec.json`
- 输出模板：`{baseDir}/resources/template.md`
- 示例输入输出：`{baseDir}/examples/`
- 冒烟测试：`{baseDir}/tests/smoke-test.md`
## 安全边界
- 适合作为启动版计划，后续需按实际进展迭代。
- 默认只读、可审计、可回滚。
- 不执行高风险命令，不隐藏依赖，不伪造事实或结果。