---
id: gh-explore-run
name: "explore-run"
url: https://skills.yangsir.net/skill/gh-explore-run
author: lllllllama
domain: data-ai
tags: ["deep-learning", "exploratory-research", "machine-learning", "experimentation", "research-automation"]
install_count: 329900
rating: 4.90 (120 reviews)
github: https://github.com/lllllllama/rigorpilot-skills/tree/main/skills/explore-run
---

# explore-run

> 此技能用于在深度学习研究中执行有界探索性运行，如小样本验证、短周期试错、批次扫描或快速迁移学习。它能帮助研究人员系统地规划和总结实验，从而高效地评估候选模型和方法，加速研究进程。

**Stats**: 329,900 installs · 4.9/5 (120 reviews)

## Before / After 对比

### 加速深度学习探索性实验

**Before**:

在没有此技能之前，研究人员需要手动规划、执行和总结深度学习的探索性实验，这通常耗费大量时间，且容易遗漏关键配置或分析不彻底，导致研究迭代周期漫长。

**After**:

此技能能够自动化探索性实验的规划与总结，系统地评估多种候选方案，显著减少手动操作时间，使研究人员能更快地获得实验洞察，加速研究进程。

| Metric | Before | After | Change |
|---|---|---|---|
| 实验规划与总结时间 | 240分钟 | 30分钟 | -87% |

## Readme

# 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
`../../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`, `../../references/explore-variant-spec.md`, `../../references/deep-learning-experiment-principles.md`, `scripts/plan_variants.py`, and `scripts/write_outputs.py`.



---
*Source: https://skills.yangsir.net/skill/gh-explore-run*
*Markdown mirror: https://skills.yangsir.net/api/skill/gh-explore-run/markdown*