explore-code
This skill serves as a rigorous improvement implementation leaf skill for deep learning research, enabling researchers to perform exploratory code modifications on isolated branches, such as transplanting modules, adapting backbones, or adding adapter layers. It ensures all changes are auditable and rollback-aware, helping researchers conduct low-risk experiments efficiently and systematically record processes and outcomes, thereby enhancing research rigor and traceability.
npx skills add https://github.com/lllllllama/rigorpilot-skills --skill explore-codeBefore / After Comparison
1 组Before this skill, researchers manually managed experimental branches and meticulously documented exploratory code changes in deep learning projects. This process was time-consuming, prone to errors, and often resulted in difficulties tracking or reverting changes, significantly hindering research agility and reproducibility.
This skill automates the management of exploratory code modifications, ensuring changes are isolated, auditable, and easily reversible. It drastically reduces the time researchers spend on managing experimental branches and tracking changes, allowing them to focus more on scientific discovery and ensuring the reproducibility of their experiments.
explore-code
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.
When to apply
- 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 not to apply
- 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.
Clear boundaries
- This skill owns exploratory code modifications only.
- It must keep work isolated from the trusted baseline.
- Use
ai-research-exploreinstead when the task spans both current_research coordination and exploratory runs. - It may hand off execution to
minimal-run-and-auditorrun-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.
Output expectations
explore_outputs/CHANGESET.mdexplore_outputs/SCIENTIFIC_CHANGELOG.mdexplore_outputs/COMPARABILITY_REPORT.mdexplore_outputs/TOP_RUNS.mdexplore_outputs/status.json
Notes
Use references/explore-policy.md, ../../references/research-rigor-principles.md, scripts/plan_code_changes.py, and scripts/write_outputs.py.
User Reviews (0)
Write a Review
No reviews yet
Statistics
User Rating
Rate this Skill