Review lessons from difficult tasks, debugging, and failed attempts, then turn them into reusable guidance. Update relevant skill instructions or shared memory so future tasks can benefit from what was learned.
任务完成后的反思与经验沉淀。仅在任务非平凡且出现调试、失败修复、反复试错、明显误判或可复用教训时使用；简单执行、查询、常规 CI 通过等无新增经验的任务可跳过。
Review the instructions the agent will receive before you install.
触发条件：非平凡任务完成后，且存在可沉淀经验：debug、失败修复、反复试错、明显误判、流程缺口，或用户显式要求。
跳过条件：简单执行、查询、格式调整、常规 CI 通过等没有新增教训的任务，无需执行此 skill。
服务对象：所有 skill。本 skill 的产出是对其他 skill 文件的更新，不产生代码。
最大的风险是"觉得差不多了"的幻觉——结果不达标时，找外部原因搪塞然后降低要求宣布完成。
常见的自我欺骗模式：
正确做法：
每个子任务开始前明确三件事：
| 教训类型 | 更新位置 |
|---|---|
| 某个 skill 流程中的陷阱 | 该 skill 的 common-pitfalls 或步骤文件 |
| 通用工作方法论 | 该 skill 的 SKILL.md 顶层注意事项 |
| 跨 skill 通用经验 | memory 系统 |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Add new operators to MNN through a staged workflow covering data definitions, output shapes, computation, and tests. It prioritizes combining existing operators, with CPU implementations and additional hardware backends used when needed.
Triage incorrect MNN outputs and regressions by matching symptoms to focused debugging guides. Use backend comparisons, minimal reproductions, and controlled experiments to investigate memory issues, quantization, concurrency, numeric limits, caches, and inconsistent results across runs.
Find the right workflow for MNN CPU work, from investigating slow execution to implementing calculation routines and planning tests. Compare ARM, x86_64, and RISC-V backend structures before choosing the relevant guidance.
Develop or port CPU kernels, the low-level calculation routines used by MNN. Follow staged implementation guidance, check data layout agreements, register functions, and verify correctness across processor instruction sets and numerical precision settings.
Find why MNN CPU inference is slow by examining threads, scheduling, memory layout, and the processor instruction path actually used. Operator-level measurements and comparisons with other inference frameworks help identify which layer needs improvement across ARM, x86_64, and RISC-V.
Optimize and troubleshoot MNN's Hexagon DSP backend, which runs computation on a dedicated processor. The workflow uses device measurements to identify bottlenecks, compare v79 and v81 architectures, verify correctness, and investigate crashes or memory usage.