一键导入
system-takeover
Use when analyzing system-level architecture, capability hubs, multi-agent systems, or orchestration stacks rather than ordinary business projects.
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。
菜单
Use when analyzing system-level architecture, capability hubs, multi-agent systems, or orchestration stacks rather than ordinary business projects.
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-takeover |
| description | Use when analyzing system-level architecture, capability hubs, multi-agent systems, or orchestration stacks rather than ordinary business projects. |
| metadata | {"triggers":["analyze system architecture","analyze skill hub","analyze ai capability system","multi agent system analysis","analyze orchestration system","capability os assessment"],"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 的核心是把能力系统接管组织成六个分析维度,并把维度结论汇总为系统成熟度判断:
Capability Map:识别 skills、能力域、重叠与空洞Invocation Readiness:检查 protocol、invocation completeness 和 readinessRouting Layer:评估 router、scoring、top-k 和稳定性Pipeline Layer:评估 subtask splitting、ordering 和 orchestration depthAdapter Layer:评估 .agents、.github 和 multi-AI discoverabilityTooling / Governance:评估 automation、lifecycle、status 和 enforcementInput:
Process:
scanmapassesssynthesizeoutputOutput:
skill_assessment_output where applicable: maturity_score, evidence, inference, open_questions, risk_priority, impact_scope, next_action这样组织的原因是,能力系统接管的难点不在于单点扫描,而在于把多个层的事实组织成可决策的系统视图。只有把 capability、invocation、routing、pipeline、adapter、tooling 和 governance 作为一个整体来分析,输出才真正服务后续系统演进。
先识别系统层,再下结论。
Map system layers before making maturity judgments.
不要把能力系统误判为普通业务项目。
Do not reduce a capability system to a normal product repository.
区分结构存在、调用就绪和治理闭环。
Separate structural existence from invocation readiness and governance enforcement.
优先输出分层判断,而不是零散观察。
Prefer layered assessment over disconnected observations.
演进建议必须对齐系统瓶颈,而不是泛化优化。
Tie evolution plans to actual bottlenecks instead of generic improvements.
scan:识别系统边界。
读取仓库结构、skills/、tools/、docs/、adapter 目录和测试文件,判断该对象是否属于 capability system,并区分 canonical source、discovery layer、tooling layer 和 governance layer。
map:建立能力地图。
盘点现有 skills、能力域、职责边界、重叠区与空洞区;确认哪些能力已经成为 canonical skill,哪些仍停留在隐式流程或缺失状态。
assess:分层评估 readiness 与 maturity。
按 Capability Map、Invocation Readiness、Routing Layer、Pipeline Layer、Adapter Layer、Tooling & Automation、Governance 七个维度检查系统现状,明确哪些层只是“存在”,哪些层已经“可用”,哪些层还没有形成 enforceable mechanism。
synthesize:形成系统级判断。
将分层发现组织成系统结构图、成熟度评估、Top 3 bottlenecks 和下一阶段演进建议;显式区分“已确认事实”“基于代码和文档的推断”“需要后续验证的点”。
output:输出 system takeover 结果。
使用结构化格式回传 System Structure、Capability Map、Maturity Assessment、Top Bottlenecks 和 Evolution Plan;在 assessment / takeover 输出中按 shared assessment output protocol 标注 maturity_score、evidence、inference、open_questions、risk_priority、impact_scope 和 next_action;如果用户允许写文件,再把分析结果写入 takeover 文档或 status 文档。
protocol、adapter、router、pipeline、tooling 和 governance 这些系统层材料skill-hub、AI capability system、multi-agent system 或 orchestration system 的整体结构与成熟度,而不是普通项目状态时使用。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.