insight-orchestrator — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited insight-orchestrator (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
本编排器当前 Pipeline 仅包含 1 个子 Skill(insight-analysis),属于合并简化后的退化编排器。保留本编排器的理由:
若未来该子模块需要扩展为多阶段 Pipeline,本编排器可直接增加阶段,无需修改上层编排器的调用方式。
编排协议遵循 orchestrator-protocol.md 统一标准。
本编排器为透传编排器,职责是提供统一入口、阶段总结和异常处理。上层编排器(如product-launch-orchestrator)可直接调用insight-analysis子Skill,无需经过本编排器。
pipeline: insight-orchestrator
version: 9.0
post_pipeline:
- action: stage-summary
output: output/phase-reports/pm-discovery/insight-orchestrator.md
stages:
- id: phase-1
name: "需求洞察分析"
skills: [insight-analysis]
gate:
condition: "insight-analysis输出文件已生成"
fail_action: "按子Skill失败原因处理,必要时升级人类"#### 调用 insight-analysis
Skill: insight-analysis
输入:
voice_analysis: output/pm-discovery/user-research-voice-analysis/voice-analysis.json
behavior_analysis: output/pm-discovery/user-research-behavior-analysis/behavior-analysis.json
requirements: 用户提供 或 output/pm-discovery/user-research-voice-analysis/voice-analysis.json(可选)
输出: output/pm-discovery/insight-analysis/insight-analysis.json
验证:
- 输出文件已生成且内容完整
模式: 🤖→👤(优先级权重需人类确认)所有业务阶段执行完成后,必须立即生成阶段总结文档:
动作: 生成阶段总结
输入:
所有子Skill输出: output/pm-discovery/insight-analysis/
人类决策记录: 本轮执行中的人类决策点及结果
输出: output/phase-reports/pm-discovery/insight-orchestrator.md
验证: 阶段总结文档已生成,6项结构(执行概览/关键发现/决策记录/产出清单/风险与待办/下游衔接)均非空
下游衔接:
primary:
target: opportunity-orchestrator
reason: 洞察分析完成,将洞察转化为可执行的机会
input_mapping:
insight_analysis_output: "output/pm-discovery/insight-analysis/ → opportunity-definition输入"
alternatives:
- target: market-orchestrator
reason: 洞察结论缺乏市场数据验证,需补充市场分析
condition: 洞察中市场数据引用率<30%或关键假设缺乏市场验证时
- target: user-research-orchestrator
reason: 洞察深度不足,需更多用户研究支撑
condition: 洞察样本量不足或用户画像不清晰时
special_cases:
- target: insight-analysis
reason: 仅需补充特定维度的需求洞察,无需完整编排流
condition: 已有洞察基础,仅需增量更新时
模式: 🤖⏸ 阶段卡口:阶段总结文档已生成且6项结构均非空 → 未通过:补充缺失结构项后重新生成
| 卡口 | 条件 | 未通过处理 |
|---|---|---|
| 输出文件已生成 | insight-analysis.json 已生成 | 按子Skill失败原因处理,必要时升级人类 |
| 阶段总结已生成 | output/phase-reports/pm-discovery/insight-orchestrator.md 已生成且6项结构均非空 | 补充缺失结构项后重新生成 |
| 决策点 | 触发条件 | 决策内容 |
|---|---|---|
| KANO边界判定 | insight-analysis KANO分类完成 | 确认边界情况的分类归属 |
| 优先级权重确认 | insight-analysis 优先级评分完成 | 确认评分权重和最终优先级排序 |
| 异常类型 | 处理策略 |
|---|---|
| 子Skill执行失败 | 按子Skill内部降级策略处理,编排器层面暂停并上报人类 |
| 上游数据全部缺失 | 降级为轻量版流程:用户口述需求 → 调用insight-analysis拆解 → 基于描述评分 |
| 阶段总结生成失败 | 基于已完成的子Skill输出生成部分总结,缺失项标注"数据缺失",不阻塞编排完成 |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.