opportunity-orchestrator — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited opportunity-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(opportunity-definition),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。
pipeline: opportunity-orchestrator
version: 8.0
post_pipeline:
- action: stage-summary
output: output/phase-reports/pm-discovery/opportunity-orchestrator.md
stages:
- id: phase-1
name: "机会识别与定义"
skills: [opportunity-definition]
gate:
condition: "opportunity-definition.json已生成,评分完整,Problem Statement质量检查通过,HMW 4维度覆盖,Brief证据摘要完整"
fail_action: "按子步骤失败原因分别处理:评分缺失等人类判定、Problem Statement质量不通过自动重试3次后升级人类、HMW维度不完整补充数据、Brief缺失补充上游数据"#### 调用 opportunity-definition
Skill: opportunity-definition
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
tam_som: output/pm-discovery/market-tam-som/tam-som.json
competitor_analysis: output/pm-discovery/market-competitor-analysis/competitor-analysis.json
persona: output/pm-discovery/user-research-user-modeling/persona.json(可选)
insight_analysis: output/pm-discovery/insight-analysis/insight-analysis.json(可选)
tech_assessment: 用户提供(可选,技术团队评估)
输出: output/pm-discovery/opportunity-definition/opportunity-definition.json
验证:
- scoring: 5个维度均已评分,战略契合度标记为needs_human=true,评分依据完整
- problem_statement: 5项质量检查全部通过(quality_check.all_passed=true),数据支撑完整
- hmw: 4个维度均已覆盖,总计8-12个HMW陈述
- brief: 证据摘要3个子字段均有内容,关键假设已列出可验证性,人类决策项非空,机会评分完整
模式: 🤖→👤(战略契合度维度👤由人类判定,Brief最终决策👤人类审批)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/opportunity-definition/
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/opportunity-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: business-orchestrator
reason: 机会定义完成,将机会转化为可持续的商业模式
input_mapping:
opportunity_output: "output/pm-discovery/opportunity-definition/ → business-model-canvas输入"
alternatives:
- target: design-orchestrator
reason: 商业模式已确定,直接进入产品设计
condition: 商业模式已在前序阶段确定,无需重新设计时
- target: validation-orchestrator
reason: 机会假设风险较高,需先验证再投入
condition: 机会简报中关键假设风险等级≥高时
special_cases: []
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 |
|---|---|---|
| 阶段1完成 | opportunity-definition.json 已生成且非空 | 按子步骤失败原因分别处理 |
| 战略契合度人类已确认 | 人类已确认战略契合度评分 | 等待人类判定战略契合度 |
| Opportunity Brief人类已确认 | 人类已审批Opportunity Brief | 等待人类审批决策项 |
| 阶段总结已生成 | output/phase-reports/pm-discovery/opportunity-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 |
|---|---|---|
| 战略契合度判定 | opportunity-definition Step 1 机会评分完成 | 确认每个机会的战略契合度评分(AI仅提供分析建议,最终得分必须由人类判定) |
| Problem Statement质量检查 | opportunity-definition Step 2 质量检查3次不通过 | 人工审核所有尝试版本并决定最终Problem Statement |
| Opportunity Brief最终决策 | opportunity-definition Step 4 机会简报完成 | 审批机会简报的结论、关键假设验证优先级和推荐下一步方案 |
| 异常类型 | 处理策略 |
|---|---|
| 机会评分战略契合度未判定 | 暂停Brief生成,等待人类判定战略契合度评分,其余4个维度评分结果可先输出 |
| Problem Statement质量检查3次不通过 | 升级人类仲裁,输出3次尝试版本及未通过项对比,由人类决定最终Problem Statement |
| HMW某维度未覆盖 | 标注"维度覆盖不完整",基于已有Problem Statement补充生成该维度HMW,标注"推断补充" |
| Brief上游数据大量缺失 | 基于已有数据生成Brief,缺失字段标注"数据缺失",证据摘要和关键假设置信度降级,建议人类补充数据后重新生成 |
| 所有上游数据全部缺失 | 降级为轻量版流程:用户口述问题 → 基于描述生成Problem Statement → 基于Problem Statement生成HMW → 输出轻量版Brief,全流程标注"数据缺失" |
| 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.