explore-code

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Chinese

Use this as the Rigor Improve implementation leaf skill. The installed slug remains

explore-code

for compatibility.

Use the shared operating principles in

../../references/agent-operating-principles.md

; this skill should guide bounded candidate code work without over-prescribing implementation details.

这是Rigor Improve的执行叶技能。为保证兼容性，安装后的标识仍为

explore-code

。

请遵循

../../references/agent-operating-principles.md

中的共享操作原则；本技能应指导有边界的候选代码工作，不过度规定执行细节。

When the researcher explicitly authorizes exploratory code changes on an isolated branch or worktree.
When the task is source-anchored module transplant, backbone adaptation, LoRA or adapter insertion, or low-risk module combination.
When summary-level recording is sufficient and the result is a candidate, not a trusted conclusion.

When the request is for trusted baseline work, conservative debugging, or normal training execution.
When the user did not explicitly authorize exploratory modifications.
When the task is a broad refactor or a from-scratch idea implementation.

This skill owns exploratory code modifications only.
It must keep work isolated from the trusted baseline.
Use
```
ai-research-explore
```
instead when the task spans both current_research coordination and exploratory runs.
It may hand off execution to
```
minimal-run-and-audit
```
or
```
run-train
```
.
It should favor source-anchored copying and minimal adaptation over freeform rewrites.
It should record why a candidate change is meaningful, how to roll it back, and why it remains a candidate rather than a verified contribution.

Use

references/explore-policy.md

../../references/research-rigor-principles.md

scripts/plan_code_changes.py

, and

scripts/write_outputs.py

请使用

references/explore-policy.md

、

../../references/research-rigor-principles.md

、

scripts/plan_code_changes.py

和

scripts/write_outputs.py

。