explore-code

github:lllllllama/RigorPilot-Skills · first committed 2026-04-01 · source · badge

Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together meaningful low-risk migration ideas with rollback-aware records in `explore_outp

Skill Health: not yet scored

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Version history

9 commits to this file on GitHub (newest first).

2026-09-06 · commit 0b3f4dd · fix: harden installed harness and add evidence-driven learning path
2026-05-18 · commit d4ce1a3 · Refine RigorPilot skill mode naming
2026-05-18 · commit d02df96 · Clean RigorPilot migration and evidence artifacts
2026-05-17 · commit c2969a6 · Align skills with RigorPilot modes
2026-05-09 · commit bb3b006 · Implement shared operating principles and enhance skill boundaries
2026-04-04 · commit 6b4c4c2 · Add comprehensive documentation and orchestration scripts for reproducible AI research
2026-04-02 · commit b3cd495 · feat: Enhance exploratory workflow with new scripts and specifications
2026-04-02 · commit 9244432 · feat: introduce research-explore orchestrator for exploratory iteration on current research
2026-04-01 · commit 2706b8e · feat: add explore-code and explore-run skeleton

Archived snapshots