kali20gakki/msAgent / skills/host-cpu/msagent-perf-cpu-perf-triage
msagent-perf-cpu-perf-triage
Verified昇腾 Host 侧性能异常归因编排:训练/推理出现症状(变慢、抖动、利用率低)且原因 不明时,按「配置复核 → 归因量化」编排 config-audit 完成配置判型,并输出按 代价×收益排序的 Action。触发:训练变慢、step 抖动、性能下降、利用率低、查根因、 瓶颈在哪。 不用于:只要配置检查(→ perf-cpu-config-audit)、只要绑核方案 (→ perf-cpu-bind-tune)——窄诉求直接用对应技能更快;本技能用于症状不明、 需多源归因的场景。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.7 KB |
| references/degradation.md | markdown | 2.2 KB |
| references/quant-rules.md | markdown | 3.7 KB |
| references/triage-playbook.md | markdown | 4.0 KB |
| resources/action-templates.json | config | 3.8 KB |
| resources/triage-report.template.html | other | 7.9 KB |
| scripts/action_build.py | script | 9.9 KB |
| scripts/audit_or_reuse.py | script | 8.5 KB |
| scripts/quantify.py | script | 8.1 KB |
| scripts/report.py | script | 9.6 KB |
| scripts/workspace.py | script | 4.4 KB |
references/degradation.md
View on GitHub# 降级矩阵
每个依赖点缺失时的表现、降级行为与标注。降级不中断主流程,但**必须在报告与
`manifest.json` 中显式标注**,不允许静默留空。
## 配置维(本期可用)
| 依赖点 | 缺位表现 | 降级行为 | 标注 |
| ---- | ---- | ---- | ---- |
| config-audit skill | 找不到 `audit.py` | 配置维缺失,本期无运行时归因 → 结论「无法归因」 | `config_triage.status = UNAVAILABLE` |
| config-audit 执行失败 | 子进程非 0 退出 | 同上;保留 stderr 末 300 字符供排查 | `status = FAILED` |
| findings 过期(> 30min) | 时效校验失败 | 自动重跑快检;新旧差异标注 | `degradation` 记录 age |
| 显式 `--skip-audit` | 用户要求跳过 | 不审计,仅用现有 findings(可为空) | `status = SKIPPED` |
## 运行时维(后续 tracing 接入后启用)
| 依赖点 | 缺位表现 | 降级行为 | 标注 |
| ---- | ---- | ---- | ---- |
| 运行时数据缺失(本期默认) | 会话内无 `01-trace/phase_verdict_1.json` | 打扰 / 等待两维为 `null`,结论降级为「仅完成配置判型」 | `attribution.disturb_pct / wait_pct = null` |
| 运行时产物缺 `accounting` | 旧版本产物无该字段 | 两维按不可观测处理(`null`) | `degradation` 提示版本不匹配 |
| 多卡仅部分成功 | 部分卡 UNOBSERVED | 主结论取成功的卡;未成功卡列明细并标原因 | `basis = card<N>` |
## 其他维
| 依赖点 | 缺位表现 | 降级行为 | 标注 |
| ---- | ---- | ---- | ---- |
| perf-collect 缺位(第一期) | 阶段2 空 | 效率维 `not_observable`,其时间计入残余 | 报告显式标注「第二期」 |
| step 周期缺失 | 无 step 对齐 | 按观测窗分析,不声称与 step 对齐 | `未与 step 对齐` |
| os-observe 缺位(第一期) | 无 `anomaly_window` | 用户口述窗 / 运行时自定全窗 | `window = derived` |
## 降级与结论的关系
- 降级**降低置信度、不改变结论结构**:`AttributionResult` 字段不变,缺项为 `null`;
- 配置维缺失 + 运行时不可观测 → 结论只能是「无法归因」,需补齐依赖后重跑;
- 任一维降级都必须出现在 `index.html` 的「降级与口径说明」区块,供用户判断可信度。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |