← Back to Skills Marketplace
Handover Memory Pack
by
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
164
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install handover-memory-pack
Description
为人员离岗或项目交接整理显性与隐性知识，减少信息流失。；use for handover, knowledge-transfer, memory workflows；do not use for 泄露不该交接的密钥, 省略高风险事项.
README (SKILL.md)
交接记忆包封装器
你是什么
你是“交接记忆包封装器”这个独立 Skill，负责：为人员离岗或项目交接整理显性与隐性知识，减少信息流失。
Routing
适合使用的情况
- 帮我整理一份交接记忆包
- 把隐性知识显式化
- 输入通常包含：职责范围、关键联系人、未决事项
- 优先产出：职责概览、关键联系人、接手建议
不适合使用的情况
- 不要泄露不该交接的密钥
- 不要省略高风险事项
- 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：
- 职责概览
- 关键联系人
- 隐性知识
- 未决事项
- 风险提醒
- 接手建议
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
- 建议把敏感信息改为引用位置而不是明文。
- 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。
Usage Guidance
This skill appears to do what it claims, but take normal precautions: (1) review the included scripts before running; (2) run the script in a sandboxed environment if you plan to point it at directories (do not pass /, your home, or other sensitive paths); (3) avoid giving it files containing secrets or credentials — the tool will scan for "secret-like" patterns and could include masked findings in outputs; (4) prefer using the template/spec-driven mode (passing sanitized text) rather than directory scans when handling sensitive handovers; and (5) use --dry-run and inspect outputs before any automated write/send actions.
Capability Analysis
Type: OpenClaw Skill
Name: handover-memory-pack
Version: 1.0.0
The skill bundle is a utility designed to assist in project handovers and knowledge transfer. The core logic in `scripts/run.py` focuses on reading local text files, CSVs, and directories to generate structured Markdown reports. Notably, it includes a 'pattern_audit' mode that uses regular expressions to identify (rather than execute) potentially dangerous patterns like hardcoded secrets or 'curl|bash' commands in the source material. The instructions in `SKILL.md` are aligned with the stated purpose and include explicit safety constraints against leaking sensitive keys.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, README, resources, and the included Python script all align: the skill organizes handover material, produces structured Markdown, and optionally audits directories or CSVs. Declared requirement (python3) is appropriate and minimal.
Instruction Scope
SKILL.md stays on-topic and warns about not including secrets and not performing high-risk actions. The included script can read arbitrary files and directories (many text file extensions) when invoked with a directory or file path, and it will scan contents for patterns (including secret-like patterns). This is expected for an audit/reporting tool but means users must avoid pointing it at sensitive directories or untrusted paths.
Install Mechanism
No install spec; this is an instruction-only skill with an included Python script. No external downloads, package installs, or obscure installers are present.
Credentials
No environment variables or credentials are requested. The skill operates on user-provided inputs and local resources only, which is proportionate to its purpose.
Persistence & Privilege
always is false and the skill does not request persistent elevated privileges or modify other skills. Model invocation is allowed (platform default); nothing in the skill implies it requires forced inclusion or system-wide changes.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install handover-memory-pack - After installation, invoke the skill by name or use
/handover-memory-pack - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of handover-memory-pack.
- Provides structured knowledge packaging for personnel or project handover.
- Helps organize both explicit and implicit information to reduce data loss during transitions.
- Outputs customizable, reviewable drafts and actionable checklists, prioritizing role overview, key contacts, tacit knowledge, unresolved matters, and risk notes.
- Incorporates security boundaries: avoids sharing untransferable secrets, flags high-risk/privileged items, and prefers references to sensitive info.
- Usable via Python script or direct text generation based on included templates/specs.
- Supports Darwin, Linux, and Win32 environments.
Metadata
Frequently Asked Questions
What is Handover Memory Pack?
为人员离岗或项目交接整理显性与隐性知识，减少信息流失。；use for handover, knowledge-transfer, memory workflows；do not use for 泄露不该交接的密钥, 省略高风险事项. It is an AI Agent Skill for Claude Code / OpenClaw, with 164 downloads so far.
How do I install Handover Memory Pack?
Run "/install handover-memory-pack" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Handover Memory Pack free?
Yes, Handover Memory Pack is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Handover Memory Pack support?
Handover Memory Pack is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Handover Memory Pack?
It is built and maintained by vx：17605205782 (@52yuanchangxing); the current version is v1.0.0.
More Skills