Vibe Index
🎯

explore-run

🎯Skill

A skill that plans quick, small trial runs for deep learning research, such as testing on part of the data or trying many settings. It reports the results without claiming more than they show.

lllllllama/rigorpilot-skills356,208 Installs503Last Updated May 27, 2026

Installation

$npx skills add lllllllama/rigorpilot-skills --skill explore-run

Run it in a terminal; it asks which AI coding tools to install it for (Claude Code, Codex, Cursor and more).

Uses skills.sh · Node.js 22.20+

After installing

Ask for related work and the agent uses it on its own, or call it yourself.

Run it (Claude Code)/explore-run
Install by hand

Copy the whole skill folder from GitHub to the place below. Copying only SKILL.md can leave out files the skill uses.

Open the skill folder →
  • This project .claude/skills/explore-run/
  • All projects ~/.claude/skills/explore-run/

These paths are for Claude Code. For other tools, the command above puts it in the right place.

📦Same repositorylllllllama/rigorpilot-skills (14 items)

What this skill does

Overview

explore-run is the Rigor Improve / Rigor Explore run skill. With your clear permission, it plans short trial runs, ranks the ideas to try, and keeps them separate from your trusted baseline (the version you know works). It labels the results as limited evidence and explains when a comparison is not fully fair.

Key Features

  • Plan small-subset checks (tests on part of the data), short training runs, batch sweeps (many settings tried in a row), idle-GPU search (runs on GPUs that are not busy), and quick transfer-learning trials (reusing a trained model for a new task).
  • Rank candidates before running them by cost, success_rate, and expected_gain, and change the balance with selection_weights.
  • Keep the work within budget with max_variants and max_short_cycle_runs.
  • Describe what to try with variant_axes, subset_sizes, short_run_steps, primary_metric, and metric_goal.
  • Hand off the actual commands to minimal-run-and-audit or run-train, and read the summaries in explore_outputs/.

Who is this for?

Use it when you want to test many cheap ideas before you spend time on a long experiment. It needs your clear permission to explore, and it does not support claims of a new best result (SOTA).

Summarized by AI from this skill's SKILL.md. Suggest a better one

SKILL.md

View on GitHub →

Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with fair-comparison caveats and no-overclaim summaries in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline execution, conservative training verification, default routing, verified SOTA claims, or implicit experimentation.

explore-run

Use this as the Rigor Improve / Rigor Explore run leaf skill. The installed slug remains explore-run for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide candidate run planning while preserving model judgment about the active repo.

When to apply

  • When the researcher explicitly authorizes exploratory runs.
  • When the task is a small-subset validation, short-cycle training probe, batch sweep, idle-GPU search, or quick transfer-learning trial.
  • When the output should rank candidate runs rather than certify trusted success.

When not to apply

  • When the user wants trusted training execution or conservative verification.
  • When there is no explicit exploratory authorization.
  • When the task is repository setup, intake, or debugging.

Clear boundaries

  • This skill owns exploratory execution planning and summary only.
  • Use ai-research-explore instead when the task spans both current_research coordination and exploratory code changes.
  • It may hand off actual command execution to minimal-run-and-audit or run-train.
  • It should keep experiment state isolated from the trusted baseline.
  • It should prefer small-subset and short-cycle checks before heavier exploratory runs.
  • It should label run results as bounded evidence and explain when a comparison is not directly fair.

Ranking Semantics

  • Pre-execution candidate selection uses three factors: cost, success_rate, and expected_gain.
  • Default weights should stay conservative unless the researcher explicitly provides selection_weights.
  • Budget pruning still applies after scoring through max_variants and max_short_cycle_runs.
  • If runs are executed later, downstream ranking should switch to real execution evidence, not stay purely heuristic.

Variant Spec Hints

  • Use variant_axes to define the candidate dimension grid.
  • Use subset_sizes and short_run_steps to express exploratory run scale.
  • Use selection_weights to rebalance cost, success_rate, and expected_gain.
  • Use primary_metric and metric_goal so downstream ranking can order executed candidates consistently.

Output expectations

  • explore_outputs/CHANGESET.md
  • explore_outputs/SCIENTIFIC_CHANGELOG.md
  • explore_outputs/COMPARABILITY_REPORT.md
  • explore_outputs/TOP_RUNS.md
  • explore_outputs/status.json

Notes

Use references/execution-policy.md, ../ai-research-reproduction/references/explore-variant-spec.md, ../ai-research-reproduction/references/deep-learning-experiment-principles.md, scripts/plan_variants.py, and scripts/write_outputs.py.

More from this repository10

🎯
paper-context-resolver🎯Skill

A helper skill for rerunning a deep learning project from its README. When the README misses a key detail, it finds the answer in the original paper and notes where the two disagree.

🎯
repo-intake-and-plan🎯Skill

A skill that reads a deep learning project's README and main files before you run anything and lists the commands they describe. It then suggests the smallest run you can trust to check the results.

🎯
env-and-assets-bootstrap🎯Skill

A skill that plans the software setup and file locations you need before re-running a deep learning research project. It suggests install commands and where to put model and data files.

🎯
minimal-run-and-audit🎯Skill

A skill that runs one short check command when you re-run a deep learning research project and saves the results as standard report files. It also records any edits made to the project's files.

🎯
ai-research-explore🎯Skill

This skill helps deep learning researchers test new ideas on top of an existing project, with fair comparisons against a fixed benchmark. It marks each result as a candidate to check and saves the reports in `explore_outputs/`.

🎯
analyze-project🎯Skill

A skill that reads a deep learning research project and explains how it is built, without changing any code. It also points out code that looks suspicious so you can check it.

🎯
ai-research-reproduction🎯Skill

A skill that helps your agent rerun a deep learning research project and check whether it works as its README describes. It starts with the smallest test and records every step and change.

🎯
safe-debug🎯Skill

A skill that finds the cause of errors in deep learning research code, such as running out of GPU memory, before changing anything. It suggests the smallest fix and waits for your approval.

🎯
explore-code🎯Skill

A skill that helps you try small, low-risk code changes in a deep learning research project on a separate branch. It records why each change matters and how to undo it.

🎯
run-train🎯Skill

A skill that carefully runs a training command you already chose for a deep learning project. It saves the command, settings, logs, and results in one standard folder.