“debugging”

Use for any bug, test failure or unexpected behavior, before proposing a fix - reproduce, find the root cause, one hypothesis at a time.

Systematic debugging with diagnostic paths covering data processing, rendering, state machine, asset loading, form/input, and build issues

When there is a bug, error, failed test, regression, performance drop, unexpected result, or anomalous data, establish a tight feedback loop and find the root…

Find the root cause of a defect or a symptom by first building a feedback loop that shows the failure on demand, recording the behaviour that must not change…

Use when diagnosing a bug, error, crash, or unexpected behavior.

Diagnose failures from evidence and make the smallest safe correction.

Use when diagnosing a failure, crash, regression, or wrong result before fixing.

Diagnose failures from evidence before changing code.

Systematically track down a bug.

Investiga bugs e falhas por evidência, reproduzindo o problema, isolando causa raiz e validando a correção sem empilhar patches sobre estado incerto.

Reproduce a failure, isolate the cause, and keep the fix bounded.

Use when encountering test failures, bugs, or unexpected behavior - requires root cause investigation before any fix attempt

Diagnose defects systematically by reproducing the issue, isolating the failing layer, testing hypotheses, fixing root cause, and adding regression protection.

Methods for recovering EVM stack traces and inspecting transaction statuses on BOT Chain.

Trace a software failure from its first divergence to an evidence-backed causal chain.

系统调试：遇到 bug、报错、测试失败、性能退化、意外实验结果或异常数据时，先于任何修复动作使用；仅背景不清而无故障信号时用 grounding，正常执行既定计划时用 executing-plans。

Diagnose reproducible backend bugs, failing tests, and regressions.

调试与故障排查技能：复现问题、定位根因、修复验证

Diagnose unexplained reproducible failures via competing hypotheses and focused experiments.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern…

Use when the user reports a bug, regression, crash, or unexpected behavior.

Use when diagnosing failing behavior, errors, regressions, or unexpected output.

Deep static analysis and bug hunting for any codebase.

Diagnose failures by narrowing the symptom, reproducing the issue, and applying a targeted fix.