qiusuo0226/chrono-pm-skill / governance-shared/baselines/3.16.0/ChronoPM-Portfolio
chrono-pm-portfolio
Verified给项目集/组合经理用的只读 Skill。跨多个项目 ai 目录归集检索进度、风险、合同、周报。禁止写入成员项目事实源。触发:项目集、组合、跨项目、汇总周报、进度总览、人员排期、跨项目风险、门禁、P&L、合同去重、建议更新清单、共享文件拆分、术语索引、挂载、健康巡检、汇总计划、按时间归集计划、技能缺口、ChronoPM-Portfolio。
assets/templates/skill-gap-demand-template.md
View on GitHub---
doc_type: skill-gap-demand
sg_id: SG-YYYYMMDD-NNN
batch_id: YYYYMMDDHHMMSS
skill_name: chrono-pm-portfolio
skill_version_installed: x.y.z
workspace_skill_version: x.y.z
workspace_schema: 0.16.0
project: [项目集名]
created_at: YYYY-MM-DD
priority: 中
source_files: []
---
# Skill 升级需求:{一句话标题}
> 一句话痛点:**{加粗一句}**
- **所属 Skill**:chrono-pm-project / chrono-pm-portfolio
- **执行中的 Skill 版本**:{skill_version_installed}
- **工作空间实际版本**:{workspace_skill_version} / schema {workspace_schema}
- **所属项目**:{project}
- **日期**:YYYY-MM-DD
- **提出人**:{姓名或对话用户}
- **优先级**:高 / 中 / 低(AI 建议,不是发布决定)
版本两行不一致时,下一行写清差在哪。
---
## 〇、开场
{通俗场景,让没参加对话的人看懂发生了什么。}
---
## 一、问题描述
### 1.1 现象
| 维度 | 用户期望 | 技能实际 |
|---|---|---|
| {维度} | {期望} | {实际} |
单表 ≤6 列。
### 1.2 用户原话
> {原汁原味引用}
### 1.3 后果
1. {后果}
2. {后果}
---
## 二、为什么会这样
### 2.1 比喻(可选)
{一个贯穿的比喻。说不清则删本节。}
### 2.2 数据流:现状 vs 应有
```mermaid
flowchart LR
A[事实] --> B[现状断点]
```
### 2.3 设计是否仍对(可选)
仅当能说明「设计对、自动化不足」时写。禁止空发议论。
---
## 三、定位
### 3.1 一句话根因
> {根因}
### 3.2 分层
| 层级 | 结论 |
|---|---|
| 直接层 | |
| 机制层 | |
| 系统层 | |
### 3.3 已排除
| 嫌疑人 | 结论 | 为什么排除 |
|---|---|---|
| {至少一条} | 不是 | {证据} |
---
## 四、证据链(按时间)
| 时间 | 发生了什么 | 写进了哪 | 技能做了/没做 |
|---|---|---|---|
| | | | |
---
## 五、缺口全景(可选)
未核过的标「未核」。不要假装已经扫完全部联动。
---
## 六、建议 Skill 补什么(可选)
只列缺口条目。禁止在此写完整升级方案 / CR / AP。
---
## 七、如何复现
1. {口令或步骤}
2. {预期撞上的现象}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |