pillumina/ascend-sleuth / skills/diagnose
diagnose
Verified昇腾训练/推理问题的核心诊断循环:收集症状、按 triage-tree 路由、两阶段加载 并验证 Tier 2 case、命中给 fix(高危 root cause 改提示 halt)或转深度排查。 Tier-2 未命中但最终解决时起草候选 case。全程写 trace。 仅在能执行命令的 agent(Claude Code / Codex / pi)中可用。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 45.1 KB |
| references/collect-gates.yaml | config | 17.4 KB |
| references/diagnosis-procedure.md | markdown | 46.4 KB |
| references/diagnosis-trace.md | markdown | 46.2 KB |
| references/platform-dispatch.md | markdown | 1.6 KB |
| references/procedure-gates.yaml | config | 4.3 KB |
| references/report-template.md | markdown | 23.7 KB |
| references/script-integration.md | markdown | 2.2 KB |
| references/src-fetch.md | markdown | 9.2 KB |
references/platform-dispatch.md
View on GitHub# Platform Dispatch(case 的 platforms 字段分发机制)
平台差异是**字段级**,不是 case 级——大量共享规则加少量平台特定差异。一个 case 可有多组 `diagnosis`,按检测到的平台选分支。
> 本文档只描述 case schema 的 `platforms` 字段分发机制。平台背景知识文档(`knowledge/platforms/*.md`)已废弃(agent 生成、零外部源);平台事实的承载位置是 reference 层(`references/platform-facts/`,经 to-reference 从真实来源沉淀)。reference 层有内容之前,**诊断上下文不注入任何平台先验**——每个 case 携带自己的平台证据(`platforms` 键控的 `diagnosis` 分支)。
## 示例:同一 case 的平台分支(构造演示,只演示结构;完整 canonical sample 见 `examples/sample-case.yaml`)
```yaml
diagnosis:
- platforms: ["A5-950", "A3-910C"] # 该分支适用于这两个平台
steps:
- command_template: "env | grep HCCL_BUFFSIZE"
expected: ">= 4194304"
- platforms: ["A2-910B"] # 平台特定差异走独立分支
steps:
- command_template: "<该平台的等价检查>"
expected: "..."
```
分支内的检查内容由该 case 自己的证据决定(来自 issue 验证 / 官方文档),**不预设"某平台一定有/没有某参数"**——那是 reference 层(`platform-fact`)的职责,且必须带来源。
## 检测当前平台
```bash
npu-smi info | grep -i '910\|950' # 910B / 910C / 950
```
检测结果填入 case 的 `platforms` 匹配逻辑。无平台字段的 case 视为全平台通用。
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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |