explore-run
๐ฏSkillfrom lllllllama/rigorpilot-skills
|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.
Overview
explore-run is a RigorPilot explore-lane skill for running small-subset probes, short-cycle trials, and ranked exploratory experiments. Unlike trusted-lane skills, explore-run only activates when the researcher explicitly authorizes candidate-only exploration on top of a defined current_research reference point. All outputs are treated as candidates, not verified results.
Key Features
- Small-subset probes: Runs experiments on reduced data subsets to quickly validate whether an exploratory idea shows promise before committing to full-scale runs.
- Short-cycle trials: Executes bounded, time-limited experimental cycles that generate preliminary evidence without consuming excessive compute resources.
- Ranked experiment outputs: Produces results in
explore_outputs/with structured ranking information so researchers can compare candidate approaches. - Explicit authorization required: Will not execute unless the researcher has explicitly requested candidate-only exploratory work, preventing accidental drift from the trusted lane.
- current_research anchoring: All exploration branches from a defined reference point (branch, commit, checkpoint, or run record), maintaining traceability back to the baseline.
- Idea score breakdowns: Integrates with the Rigor Explore chain to provide atomic idea decomposition and implementation-fidelity evidence layers.
Who is this for?
- Deep learning researchers who want to safely explore new ideas with bounded experiments while maintaining a clear separation between exploratory candidates and verified results.
- Teams running systematic hyperparameter searches or architectural explorations who need structured, ranked output from multiple trial runs.
- Users of the full RigorPilot suite who have a frozen baseline and want to run exploratory experiments within the explore lane's guardrails.
Same repository
lllllllama/rigorpilot-skills(14 items)
Installation
npx vibeindex add lllllllama/rigorpilot-skills --skill explore-runnpx skills add lllllllama/rigorpilot-skills --skill explore-run~/.claude/skills/explore-run/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 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.
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 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 starting or verifying deep learning training runs, including resume handling, bounded monitoring, and generating durable training records.
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 trusted-lane skill for conservatively running documented evaluation, inference, smoke tests, and sanity checks in deep learning repositories without introducing unaudited changes.