菜单
Use when updating ai-skill-hub handoff as a system document and the merge must stay section-aware instead of becoming a full rewrite.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | system-handoff |
| description | Use when updating ai-skill-hub handoff as a system document and the merge must stay section-aware instead of becoming a full rewrite. |
| metadata | {"triggers":["update ai-skill-hub system handoff","maintain skill-hub handoff sections","refresh system boundaries in docs HANDOFF md","capture next phase direction for ai capability system","merge system-level handoff updates without full rewrite"],"side_effects":["read_only","write_files"]} |
This execution-focused skill definition keeps the behavior, invocation shape, and adapter-facing contract unchanged while moving explanation-oriented content into supporting assets.
这个 pattern 的核心是：
chatgpt-handoff-pilot 的 bounded execution 与 section-aware mergeInput:
docs/HANDOFF.mdProcess:
readlocate sectionsmerge incrementallyreportOutput:
maturity_score这样组织的原因是，handoff 在 system repo 中的作用是保持长期边界清晰，而不是每轮都重新生成一份说明文档。底层 merge 方法继续来自 canonical skill chatgpt-handoff-pilot，这个 wrapper 只负责 system-oriented 收口。
先复用 canonical handoff flow，再施加 system constraints。
Reuse the canonical handoff flow before adding system constraints.
只做 section-aware merge，不做全文重写。
Use section-aware merge and avoid full rewrites.
章节内容必须服务系统边界与阶段表达。
Keep sections focused on system boundaries and phase expression.
Next Phase Direction 只写方向，不写任务清单。
Keep next-phase content directional, not task-list oriented.
handoff 不得退化为 diff 摘要。
Do not degrade handoff into a diff summary.
读取 system handoff context。
先读取 docs/HANDOFF.md、当前 system status、phase 和相关 system docs，确认本轮更新对象是 ai-skill-hub 自身；若存在 docs/status/skill-hub-status.md，同步记录其 Updated at 作为本次 handoff 的 status baseline。
对齐 canonical handoff method。
复用 chatgpt-handoff-pilot 的 read input -> restate boundaries -> bounded execution -> execution report 方法，不新增第二套 handoff 机制。
定位必需 sections。
优先定位并增量更新 Current Status、Hard Boundaries、Key Design Decisions、Intentional Gaps、Next Phase Direction，必要时补 Update Log。
执行 section-aware merge。
只把新的 system facts 合并到相关 section，保留既有结构和人工内容；不得整体重排或全文重写 docs/HANDOFF.md。
输出简短回执。
回执应说明哪些 system sections 被更新、哪些 hard boundaries 保持不变、哪些 intentional gaps 继续保留，以及当前 next-phase direction。Next Phase Direction 必须保持方向级表达，不得写成任务清单、逐项施工 next steps 或 implementation backlog。handoff 回执可引用 shared assessment output protocol 的 evidence、open_questions、risk_priority 口径，并保留 phase / freshness risk awareness；不要强制使用 maturity_score。
执行 phase consistency check。
若本轮同时刷新了 docs/status/skill-hub-status.md，则 docs/HANDOFF.md 中的 phase 表达必须与最新 status 一致；若不一致，应先修正再落盘。
chatgpt-handoff-pilot 作为 canonical dependency，不得分叉 handoff flowdocs/HANDOFF.md 时必须坚持 section-aware merge，不得全文重写Current Status 必须按 system phase 和 capabilities 表达，而不是施工进度表达Next Phase Direction 只能写方向级演进，不得退化成任务清单、逐项施工 next steps 或实现待办列表docs/status/skill-hub-status.md，本轮 handoff 更新日志应记录 status baseline 日期system-status-update 联动执行，handoff 落盘前必须完成 phase consistency 检查ai-skill-hub 的 handoff 主文档，并保持 system-oriented section 输出时使用。Adapter entry for bootstrapping agent rules, contracts, validation, task packages, reports, and handoff boundaries for financial data engineering or operations projects. Canonical source is in skills/financial-data-agent-bootstrap.
Use when bootstrapping agent rules, contracts, validation, task packages, reports, and handoff boundaries for financial data engineering or operations projects.
Use when evaluating, scoring, diagnosing, or explicitly refactoring a single skill under controlled governance.
Use when onboarding a new maintainer or AI agent, scanning an unfamiliar repository, or generating a takeover packet.
Use when preparing a handoff task package, bounded execution, or execution report across AI agents.
Use when assessing migration readiness for a financial-data Python project with script sprawl, Excel assets, or Wind/Desktop coupling.