← 返回 Skills 市场
Knowledge To Playbook
作者
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
153
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install knowledge-to-playbook
功能描述
把 FAQ、聊天、零散笔记整理成 SOP / Playbook，补齐异常分支和回滚步骤。；use for playbook, sop, knowledge-base workflows；do not use for 直接执行危险操作, 跳过人工审批节点.
使用说明 (SKILL.md)
知识到手册转换器
你是什么
你是“知识到手册转换器”这个独立 Skill，负责：把 FAQ、聊天、零散笔记整理成 SOP / Playbook，补齐异常分支和回滚步骤。
Routing
适合使用的情况
- 把聊天记录整理成 SOP
- 补齐回滚和异常处理
- 输入通常包含：FAQ、聊天记录、操作步骤
- 优先产出：适用场景、标准步骤、常见坑位
不适合使用的情况
- 不要直接执行危险操作
- 不要跳过人工审批节点
- 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
- 先把用户提供的信息重组成任务书，再输出结构化结果。
- 缺信息时，优先显式列出“待确认项”，而不是直接编造。
- 默认先给“可审阅草案”，再给“可执行清单”。
- 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
- 如运行环境允许 shell / exec，可使用：
python3 "{baseDir}/scripts/run.py" --input \x3C输入文件> --output \x3C输出文件>
- 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：
- 适用场景
- 标准步骤
- 异常分支
- 回滚方案
- 升级路径
- 常见坑位
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
- 适合作为操作手册草案，正式上线前需评审。
- 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。
安全使用建议
This skill appears coherent and offline: it expects python3 and processes local input files to produce reviewable SOP/playbook drafts. Before installing or running it: (1) run the included script locally (use --dry-run) to verify behavior; (2) avoid pointing the script at system/root directories — only supply intended input directories/files; (3) don't feed sensitive secrets into the inputs (the script will read files you point it to); (4) review generated output before using it to perform any real-world changes; and (5) confirm you have python3 and are comfortable running a small local script. If you need the agent to run this autonomously, be aware autonomous invocation is allowed by default — enable it only if you trust the skill and its inputs.
功能分析
Type: OpenClaw Skill
Name: knowledge-to-playbook
Version: 1.0.0
The skill bundle is a documentation utility designed to convert unstructured notes, FAQs, and chat logs into structured SOPs and playbooks. The core logic in `scripts/run.py` is limited to file reading, text processing, and basic pattern matching (including a defensive scanner for secrets and dangerous shell commands) without any network access, obfuscation, or unauthorized execution capabilities. The instructions in `SKILL.md` and `README.md` explicitly define safety boundaries, emphasizing manual review and prohibiting the execution of high-risk operations.
能力评估
Purpose & Capability
Name/description (SOP/playbook generation) match the included files and scripts. Declared requirement (python3) is appropriate; resources/spec.json and template.md drive output structure as described.
Instruction Scope
SKILL.md confines runtime actions to reading provided input, using local resources, and optionally running scripts. It explicitly warns not to perform dangerous operations and instructs to produce reviewable drafts. The script reads files the user points it at (expected for this use).
Install Mechanism
No install spec — instruction-only plus a local Python script. No network downloads or package installs are requested; the README and SELF_CHECK state only Python standard library is used.
Credentials
The skill requests no environment variables, credentials, or config paths. The script works with local files supplied as input; that local file access is proportional to the stated purpose.
Persistence & Privilege
Skill is not always-enabled and does not request autonomous elevated privileges or modify other skills. It writes output only when given an output path (or not when --dry-run is used).
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 knowledge-to-playbook - 安装完成后，直接呼叫该 Skill 的名称或使用
/knowledge-to-playbook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 – knowledge-to-playbook skill version 1.0.0:
- Converts FAQ, chat logs, and scattered notes into SOPs or playbooks.
- Automatically supplements exception branches and rollback procedures.
- Includes clear rules and boundaries for safe usage: forbids direct execution of dangerous operations and bypassing manual approvals.
- Provides structured outputs: scenarios, steps, exceptions, rollback, upgrades, and pitfalls.
- Highlights missing information for user confirmation instead of making assumptions.
- Generates reviewable drafts and checklists before any execution recommendation.
元数据
常见问题
Knowledge To Playbook 是什么？
把 FAQ、聊天、零散笔记整理成 SOP / Playbook，补齐异常分支和回滚步骤。；use for playbook, sop, knowledge-base workflows；do not use for 直接执行危险操作, 跳过人工审批节点. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 153 次。
如何安装 Knowledge To Playbook？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install knowledge-to-playbook」即可一键安装，无需额外配置。
Knowledge To Playbook 是免费的吗？
是的，Knowledge To Playbook 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Knowledge To Playbook 支持哪些平台？
Knowledge To Playbook 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux, win32）。
谁开发了 Knowledge To Playbook？
由 vx：17605205782（@52yuanchangxing）开发并维护，当前版本 v1.0.0。
推荐 Skills