Turn scattered responsibilities and undocumented operational knowledge into a clear, actionable work handover pack.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ym-work-handover-pack
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install ym-work-handover-pack using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Work Handover Pack is an Openclaw Skills workflow for transforming fragmented duties, active projects, recurring tasks, system access details, contacts, risks, and operational tips into a structured Markdown handover document. It is designed for role changes, resignations, extended leave, project transfers, and any situation where another person must take over work quickly.
Its core value is capturing hidden knowledge: practical details that may not exist in formal documentation but are essential for successful execution. The skill does not invent missing facts; it identifies information gaps, asks targeted follow-up questions, preserves placeholders, avoids writing passwords, and flags sensitive content for desensitization before generation.
[To complete: Which report requires manual filtering?].No third-party dependencies are required. The skill performs text-only processing, does not access local files unless the user provides a path, does not connect to the internet, and does not upload content.
ym-work-handover-pack skill available in the configured Openclaw Skills directory.references/信息缺口八维度清单.md for gap discoveryreferences/隐性知识提问库.md for hidden-knowledge promptstemplates/交接包模板.md for the fixed nine-section outputhandover/ within the skill directory. Cross-session storage is not enabled by default.The skill must not receive raw passwords or other secrets. For sensitive material, provide a desensitized version before requesting document generation.
The generated deliverable is Markdown with a fixed nine-section taxonomy:
| Section | Required content |
|---|---|
| 1. Information gaps | Missing details across eight dimensions, with follow-up questions |
| 2. Responsibility checklist | Trigger, operating steps, and completion standard; ordered by frequency × importance |
| 3. Active items | Item, current status, next step, milestone, related person, and deadline |
| 4. Recurring tasks | Task, cadence, previous execution time, next execution time, and dependencies |
| 5. Assets and permissions | System or platform, account type, transfer requirement, and request owner or path; no passwords |
| 6. Key contacts | Role, name or alias, communication topic, and contact method |
| 7. Hidden knowledge | Undocumented but necessary operational details, with explicit placeholders when unknown |
| 8. Risks and pending decisions | Unresolved approvals, budget issues, process uncertainties, and handover risks |
| 9. 30-day transition timeline | Week-one shadowing, week-two practice, week-three independent execution, and week-four review, adjusted to the supplied deadline |
Input metadata includes the work description as required data, while the handover recipient, deadline, permission-transfer scope, and sensitivity flag are optional. Missing recipients default to a “new colleague” perspective without omitting necessary context. Missing deadlines use a clearly labeled two-week assumption. Sensitive content must be desensitized before processing. Account credentials are represented only by transfer status and an approval route, such as “requires transfer,” never by secret values.
Package resources are organized under references/ and templates/; an optional handover/ directory may hold incremental working material when explicitly enabled.
[To complete: ...] placeholders rather than inventing factshandover/ for follow-up completion across sessionsLoading
Convert client meeting notes, chat excerpts, and visit records into a structured, evidence-based follow-up plan with owners, deadlines, risks, and completion criteria.

Zhongkui Guard scans AI-related content for suspicious commands, redacts sensitive data, and evaluates configured model APIs with evidence-based reports.

AI Web Check performs an evidence-first, non-mutating assessment of website usability and agent readiness.

A practical troubleshooting and configuration skill that makes Hermes browser automation reliable on Fedora Atomic and bootc systems.

A reliable preflight and dependency installer for PDF OCR, summarization, translation, and rendering pipelines.

Grilling relentlessly stress-tests a plan, decision, or idea through structured, round-based questioning until every assumption is resolved.








































