iteration-orchestrator — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited iteration-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.
数据驱动的优先级决策,平衡短期修复与长期价值
迭代不是简单的需求排队,而是在有限资源下做出最优取舍。每一次优先级调整都是在短期修复和长期价值之间寻找平衡点,数据是决策的依据而非决策本身。
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。上层编排器可直接调用iteration-decision子Skill,无需经过本编排器。
pipeline: iteration-orchestrator
version: 10.0
post_pipeline:
- action: stage-summary
output: output/phase-reports/pm-monitoring/iteration-orchestrator.md
stages:
- id: phase-1
name: "迭代决策"
depends_on: []
skills: [iteration-decision]
gate:
condition: "iteration-decision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 iteration-decision
Skill: iteration-decision
输入:
requirement_pool: 项目管理系统(需求池)
tech_debt: 代码质量平台(技术债务)
monitoring_alerts: monitoring-pipeline → 告警数据(可选)
user_feedback: 反馈系统(可选)
current_sprint_plan: agile-sprint-planning → sprint_plan
trigger_event: 监控系统/反馈系统
resource_constraints: planning-resource → resource_plan
change_request: 用户提供
iteration_completion: agile-daily-sync → daily_sync
quality_metrics: 测试平台/CI/CD
team_feedback: Retro工具(可选)
monitoring_data: monitoring-pipeline(可选)
输出: output/pm-monitoring/iteration-decision/
验证: 输出文件已生成且内容完整
模式: 🤖→👤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-monitoring/
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-monitoring/iteration-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: design-orchestrator
reason: 迭代决策完成,实现迭代需求变更
input_mapping:
iteration_output: "output/pm-monitoring/iteration-decision/ → change-impact-analysis输入"
alternatives:
- target: release-orchestrator
reason: 迭代决策为直接发布
condition: 迭代决策为紧急修复或小版本发布时
- target: monitoring-orchestrator
reason: 迭代后需加强监控
condition: 迭代涉及核心功能变更,需加强上线后监控时
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 |
|---|---|---|
| 输出文件已生成 | iteration-decision输出已生成 | 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-monitoring/iteration-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 |
|---|---|---|
| 迭代计划调整确认 | iteration-decision 优先级调整方案生成完成 | 确认调整方案、资源重新分配和风险接受 |
| 异常类型 | 处理策略 |
|---|---|
| 子Skill执行失败 | 回退至当前阶段重新执行,最多重试1次;仍失败则标记异常并上报人类 |
| 上游数据缺失 | 标注缺失数据项,使用合理假设填充,继续执行并在输出中高亮标注 |
| 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.