Model Handoff Skill
Enables seamless context continuity when switching between LLM models mid-session. Maintains a HANDOFF.md file that any model can read to instantly understand the current project state, active tasks, and behavioral expectations.
Core Concept
Every model starts a session cold. HANDOFF.md is a dense, always-current fast-boot file that eliminates the ramp-up. It is the single source of truth for model-to-model context transfer.
HANDOFF.md Structure
Write HANDOFF.md to the workspace root with these sections:
CODEBLOCK0
When to Create/Update
Create HANDOFF.md when:
- - User asks about switching models
- User asks how to preserve context
- INLINECODE4 does not yet exist
Update HANDOFF.md when:
- - User says "switching to [model]" — update immediately before they go
- User says "update HANDOFF" or "log everything"
- A significant project milestone is reached (new project started, major decision made, new agent added)
- The session has been running for several hours with significant new context
Keep current proactively — do not wait to be asked. Update during long sessions when meaningful things happen.
Wiring HANDOFF.md into the Workspace
After creating HANDOFF.md, add a reference in AGENTS.md so every model is instructed to read it on a model switch:
CODEBLOCK1
What to Say When Switching
Tell the user to open with this when switching to a new model:
"Read HANDOFF.md. You are [agent name]."
That single line forces the new model to self-load before responding.
Writing Guidelines
- - Dense, not verbose — every line earns its place
- File paths, not descriptions — "see
azure-config.json" not "credentials are stored somewhere" - Never inline secrets — point to credential files only
- No personal/private data — HANDOFF.md may be shared; keep sensitive context in MEMORY.md
- Remove stale content — delete completed projects and outdated context on each update
- Last updated timestamp — always include so the receiving model knows how fresh it is
References
- - See
references/template.md for a copy-paste HANDOFF.md starter template
模型交接技能
在会话过程中切换LLM模型时，实现无缝的上下文连续性。维护一个HANDOFF.md文件，任何模型均可读取该文件，以即时了解当前项目状态、活跃任务及行为预期。
核心概念
每个模型启动会话时都是冷启动。HANDOFF.md是一个紧凑且始终最新的快速启动文件，消除了预热过程。它是模型间上下文传递的唯一真实来源。
HANDOFF.md结构
将HANDOFF.md写入工作区根目录，包含以下章节：
markdown
HANDOFF.md — 模型切换上下文
你是谁
[代理名称、角色、语气、关键行为规则。如存在SOUL.md，请引用。]
你在帮助谁
[用户名称、角色、位置、偏好。如存在USER.md和MEMORY.md，请引用。]
活跃项目
[每个项目：名称、状态、关键文件、后续步骤。请具体说明——包含文件路径。]
代理名册
[如为多代理：列出代理ID、模型、角色。]
关键凭证与工具
[指向凭证文件——切勿内联机密。例如：Azure SP凭据：azure-config.json]
行为规则
[新模型必须遵循的关键规则。仅保留必要内容。]
如何保持此文件最新
[关于何时更新的简要说明。]
最后更新时间
[时间戳 + 1行会话摘要]
何时创建/更新
创建 HANDOFF.md 当：
- - 用户询问切换模型
- 用户询问如何保留上下文
- HANDOFF.md 尚不存在
更新 HANDOFF.md 当：
- - 用户说切换到[模型]——在他们离开前立即更新
- 用户说更新HANDOFF或记录所有内容
- 达到重要项目里程碑（新项目启动、重大决策做出、新代理加入）
- 会话已运行数小时且积累了大量新上下文
主动保持最新——不要等待被要求。在长时间会话中，当有重要事件发生时进行更新。
将HANDOFF.md接入工作区
创建HANDOFF.md后，在AGENTS.md中添加引用，以便每个模型在模型切换时被指示读取该文件：
markdown
每次会话
...
- - 如果你是接替的新模型（模型切换）：首先读取HANDOFF.md——它是所有活跃内容的快速启动摘要
切换时该说什么
告知用户在切换到新模型时使用以下开场：
读取HANDOFF.md。你是[代理名称]。
这一行指令强制新模型在响应前自行加载。
编写指南
- - 紧凑而非冗长——每一行都应有其价值
- 文件路径而非描述——使用参见azure-config.json而非凭证存储在某个地方
- 切勿内联机密——仅指向凭证文件
- 不包含个人/隐私数据——HANDOFF.md可能被共享；敏感上下文保留在MEMORY.md中
- 删除过时内容——每次更新时删除已完成的项目和过时的上下文
- 最后更新时间戳——始终包含，以便接收模型了解其新鲜程度
参考
- - 参见references/template.md获取可复制粘贴的HANDOFF.md起始模板
