x5-model-diagnostics
Skill1 starsChanged 3 months agoApache-2.0View on GitHub
只读分诊 X5 环境、checker、PTQ、QAT、Runtime、精度、性能和日志问题；当已有 failure receipt、environment.json、日志或中间产物，需要定位首次失败阶段和下一 Skill 时使用。默认不重跑训练、编译、安装或上传。
In this repository59 other files it gives its agents.
- bsp-bootloader-buildSkill
- bsp-deb-buildSkill
- bsp-env-setupSkill
- bsp-image-buildSkill
- bsp-kernel-buildSkill
- bsp-rootfs-customSkill
- bsp-source-syncSkill
- bsp-s-seriesSkill
- hmct-workflowSkill
- horizon-routerSkill
- ucpSkill
- x5-accuracy-diagnosticsSkill
- x5-board-monitorSkill
- x5-bpu-python-apiSkill
- x5-calibration-data-prepareSkill
- x5-consistency-diagnosticsSkill
- x5-environment-installSkill
- x5-environment-probeSkill
- x5-environment-setupSkill
- x5-model-preflightSkill
- x5-performance-diagnosticsSkill
- x5-ptq-compileSkill
- x5-ptq-config-authoringSkill
- x5-ptq-deploySkill
- x5-qat-adaptationSkill
- x5-qat-compileSkill
- x5-qat-deploySkill
- x5-qat-trainingSkill
- x5-routerSkill
- x5-runtime-cpp-inferSkill
- x5-runtime-deploySkill
- x5-runtime-perf-evalSkill
- rdk-accessoriesSkill
- rdk-board-delegateSkill
- rdk-board-knowledgeSkill
- rdk-camera-setupSkill
- rdk-command-manualSkill
- rdk-diagnosticSkill
- rdk-docs-referenceSkill
- rdk-ecosystemSkill
- rdk-embodied-lerobotSkill
- rdk-gpio-40pinSkill
- rdk-hardwareSkill
- rdk-headless-modeSkill
- rdk-llm-deploymentSkill
- rdk-log-forensicsSkill
- rdk-memory-auditSkill
- rdk-model-benchmarkSkill
- rdk-model-deploySkill
- rdk-model-zooSkill
- rdk-multimediaSkill
- rdk-network-remoteSkill
- rdk-peripheral-cookbookSkill
- rdk-source-mapSkill
- rdk-system-configSkill
- rdk-system-maintainSkill
- rdk-tros-setupSkill
- rdk-vision-pipelineSkill
- d-robotics-pack-installerSkill
The file
Files
X5 模型诊断路由
目标与边界
从失败收据和证据确定首次失败阶段，输出可证伪的根因假设和最小恢复实验。诊断不是“换参数再跑一次”的别名。
输入合同
receipt.json、environment.json、run-state.json、相关日志和配置。- 模型/数据/源码哈希、已验证中间产物和可复现输入。
- 用户观察到的期望与实际结果。
前置检查
- 检查证据是否来自同一 run/attempt、模型哈希和环境。
- 先区分环境、模型支持、校准/训练、编译、Runtime I/O、精度或性能。
- 诊断期间不修改原始模型、配置、环境或板端状态。
执行步骤
- 建立阶段时间线并找到第一个从 pass 变 fail 的边界。
- 提取错误码、首个异常节点、输入合同差异和环境变化。
- 选择专项 Skill：
- 精度/量化掉点 →
x5-accuracy-diagnostics - 阶段输出不一致 →
x5-consistency-diagnostics - 延时/吞吐/资源 →
x5-performance-diagnostics - 工具/版本/板端 →
x5-environment-probe
- 精度/量化掉点 →
- 输出一个最小实验，只改变一个主变量，并说明成功/失败如何更新假设。
产物与完成标准
diagnosis-report.json/md包含首次失败阶段、证据、假设、反证、恢复路径和下一 Skill。- 结论区分“已证明”“高概率”“缺证据”。
- 不以日志关键词或命令返回码单独认定根因。
风险与确认
默认只读，低风险。任何重跑、安装、覆盖、上传或设备修改都必须形成新计划并重新确认。
失败与交接
证据不足时列出最小补充项并保持 blocked；不得从不完整日志猜配置。专项诊断同一假设最多验证两次。
按需参考
.drobotics/platforms/x5/references/manual-map.md.drobotics/platforms/x5/references/run-contract.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.