explore-code
๐ฏSkillfrom lllllllama/rigorpilot-skills
|A RigorPilot explore-lane skill for candidate implementation, code transplanting, and stitching on isolated branches when the researcher has explicitly authorized exploratory work on top of current research.
Overview
Explore Code is an explore-lane skill in the RigorPilot suite for candidate implementation, code transplanting, and stitching on isolated branches. Unlike the trusted-lane skills that default to safe, non-destructive operations, this skill activates only when the researcher has explicitly authorized exploratory work on top of the current research baseline. All exploratory changes happen on separate branches to preserve the original state.
Key Features
- Explicit-only activation - Never runs exploratory modifications unless the researcher explicitly requests it, preventing accidental scientific drift
- Isolated branch work - All candidate implementations happen on separate branches, keeping the main research baseline clean and comparable
- Code transplanting and stitching - Supports taking components from other repositories or papers and integrating them into the current codebase with proper tracking
- Durable explore bundles - Saves all exploratory outputs to
explore_outputs/with full provenance so results can be audited later - Cross-platform support - Works on Windows and Linux with Claude Code, Codex, and standard Agent Skills installations
Who is this for?
- Deep learning researchers who want to experiment with alternative architectures or techniques while maintaining a clean, reproducible baseline
- ML engineers integrating components from published papers into existing research codebases with proper version tracking
- Research teams that need auditable exploration workflows where every change is traceable and reversible
Same repository
lllllllama/rigorpilot-skills(14 items)
Installation
npx vibeindex add lllllllama/rigorpilot-skills --skill explore-codenpx skills add lllllllama/rigorpilot-skills --skill explore-code~/.claude/skills/explore-code/SKILL.mdSKILL.md
More from this repository10
The primary explore-lane orchestrator in the RigorPilot suite that enables meaningful and potentially novel exploration on top of current deep learning research, with idea gating, bounded experiments, and candidate ranking.
The primary end-to-end orchestrator in the RigorPilot suite that guides AI agents through README-first reproduction of deep learning repositories, ensuring scientific rigor, comparability, and auditable outputs.
A helper skill in the RigorPilot suite that resolves gaps between a deep learning repository's README and its associated research paper, helping agents understand the paper context needed for faithful reproduction.
A RigorPilot trusted-lane skill for research-safe debugging of deep learning experiments that analyzes failures first and applies patches only after explicit approval, preserving scientific comparability.
A RigorPilot trusted-lane skill that performs read-only project analysis on deep learning repositories, including model mapping, structure inspection, and risk surfacing, without making any edits.
A RigorPilot trusted-lane skill for conservatively starting or verifying deep learning training runs, including resume handling, bounded monitoring, and generating durable training records.
A RigorPilot helper skill that scans deep learning repositories and extracts README commands to build an initial reproduction plan, typically invoked by the main reproduction orchestrator.
A RigorPilot trusted-lane skill for conservatively setting up deep learning environments, including datasets, pretrained weights, checkpoints, and cache assumptions required for research reproduction.
A RigorPilot explore-lane skill for running small-subset probes, short-cycle trials, and ranked exploratory experiments when the researcher explicitly authorizes candidate-only exploration.
A RigorPilot trusted-lane skill for conservatively running documented evaluation, inference, smoke tests, and sanity checks in deep learning repositories without introducing unaudited changes.