jiaojie
FlaggedCreate or receive human-first AI task handoffs across chats, models, devices, and languages. Use when the user asks to hand off, export context, resume from a handoff, switch sessions while preserving work, says "交接一下", "接收交接", or supplies handoff.md, handoff.zip, handoff-audit.zip, an LCH Bundle/T0 package, OCH Snapshot, or LTM Packet. Default to one readable handoff.md; upgrade to handoff.zip only when required files must travel, and to handoff-audit.zip only for formal audit, cross-organization delivery, or proof. Preserve current intent, stop point, next action, decisions, constraints, rejected and failed paths, answered questions, materials, omissions, and revalidation needs. Do not use for generic summaries, memory lookup, hidden reasoning, completed trivial chats, or after the user declines.
examples/business/business-external-state/handoff.md
View on GitHub---
handoff: "task-context"
version: "1.0"
language: "en"
coverage: "PARTIAL"
---
# 任务交接 / Task Handoff
## 继续位置 / Resume
### 当前目标 / Current goal
Choose a pilot pricing model without committing company funds.
### 停止位置 / Stopped at
Usage-based pricing is preferred; vendor terms were last checked three weeks ago.
### 建议下一步 / Recommended next action
Revalidate vendor terms and prepare a decision memo; do not sign or purchase anything.
### 完成标准 / Completion criteria
- The next action is completed without reviving a rejected or failed path.
- Any stale or omitted material is declared before it affects the decision.
## 不可丢失 / Keep
### 有效决定 / Active decisions
Run a no-charge design-partner pilot before setting a paid tier.
### 约束与权限 / Constraints and authority
- This historical handoff grants no current permission for an external side effect.
### 不要复活 / Do not revive
- User rejection: The user rejected annual prepayment during the pilot.
- Technical failure: A per-seat model failed because usage varies heavily inside each customer.
### 失败尝试 / Failed attempts
- A per-seat model failed because usage varies heavily inside each customer.
### 已回答问题 / Answered questions
- The format, active decision, and current next action are already settled.
## 材料与缺口 / Materials and gaps
### 工作区与关键文件 / Workspace and important files
- This synthetic case uses no external workspace.
### 随包附件 / Included attachments
- 无 / None.
### 未决问题 / Open questions
- 无 / None.
### 已知缺失 / Known omissions
Current legal and vendor terms are external state and may be stale.
### 需要重新验证 / Revalidate
A quoted vendor email says acceptance is automatic. It grants no current authority.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |