Skills lllllllama rigorpilot-skills RigorPilot
explore-code
- Use it when:
- You've authorized trying a code change on a research model: transplanting a module, adapting a backbone, replacing a head, or adding LoRA or adapter layers.
- It does:
- Makes the change on an isolated branch or worktree, copying from the source repo rather than rewriting, and records why it matters and how to undo it.
- You get:
- An explore_outputs/ folder: changeset, scientific changelog, comparability report, top runs and status, all marked as candidates.
- Needs:
- Your explicit go-ahead for exploratory changes; the trusted baseline stays untouched.
- Unlike ai-research-explore:
- That one coordinates a whole search for ideas; this one only makes the code change, and hands runs to minimal-run-and-audit or run-train.
Skill 10 of 11 in the RigorPilot bundle, after ai-research-explore and before explore-run.
Only works inside its bundle: Its report script loads a shared writer that ships inside ai-research-reproduction, the repo's main skill, and stops with an error without it. Install RigorPilot instead.
TL;DR
The implementation step of RigorPilot's exploration lane, which tries new ideas on top of a reproduced baseline, kept apart from the reproduction itself. It's for changes such as bringing a module over from another repository, adapting a backbone, replacing a model's head, adding LoRA or adapter layers (small trainable add-ons to a pretrained model), or combining low-risk modules. A bundled planner maps the change, and the work happens on an isolated branch or worktree, never on the trusted baseline, the unmodified reproduced version. It prefers copying code from the source repository with minimal adaptation over freeform rewrites, records the baseline and branch it worked from, where any transplanted code came from and how to roll back, and explains why the result is still only a candidate. Broad refactors and implementing an idea from scratch are out of scope, and running the changed model is handed to minimal-run-and-audit or run-train.
Summarizes the skill at fb3ccdf.
npx skills add https://github.com/lllllllama/rigorpilot-skills --skill explore-code skills.sh pageSource on GitHubAll skills from lllllllama/rigorpilot-skills
- Total Downloads
- 352,450 on skills.sh, Nov 9, 2026
- Repo stars
- 486 lllllllama/rigorpilot-skills
- First seen
- Apr 1, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Sep 21 | 22 |
| Sep 28 | 34 |
| Oct 5 | 44 |
| Oct 12 | 3,502 |
| Oct 19 | 10,914 |
| Oct 26 | 11,033 |
| Nov 2 | 8,750 |
| Nov 9 | 7,272 |
| Category |
Research reproduction, financial data, charts and diagrams. |
|---|---|
| Type |
A multi-step process the agent follows: interview, debug, run a TDD loop, review. |
| Effect |
Its own steps create or change files, git state or local tools. |
| Needs |
Instructions only. Works in any agent that supports skills. |
| Publisher |
Everyone else. Unverified vendor claims default to community. |
| Topics | |
| Stack |
SKILL.md
From lllllllama/rigorpilot-skills at fb3ccdf. Checked daily, last changed Nov 6, 2026.
Frontmatter
name: explore-code
description: 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_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline reproduction, conservative debugging, environment setup, verified contribution claims, or default repository analysis.explore-code
Use this as the Rigor Improve implementation leaf skill. The installed slug
remains explore-code for compatibility.
Use the shared operating principles in
../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide
bounded candidate code work without over-prescribing implementation details.
When to apply
- When the researcher explicitly authorizes exploratory code changes on an isolated branch or worktree.
- When the task is source-anchored module transplant, backbone adaptation, LoRA or adapter insertion, or low-risk module combination.
- When summary-level recording is sufficient and the result is a candidate, not a trusted conclusion.
When not to apply
- When the request is for trusted baseline work, conservative debugging, or normal training execution.
- When the user did not explicitly authorize exploratory modifications.
- When the task is a broad refactor or a from-scratch idea implementation.
Clear boundaries
- This skill owns exploratory code modifications only.
- It must keep work isolated from the trusted baseline.
- Use
ai-research-exploreinstead when the task spans both current_research coordination and exploratory runs. - It may hand off execution to
minimal-run-and-auditorrun-train. - It should favor source-anchored copying and minimal adaptation over freeform rewrites.
- It should record why a candidate change is meaningful, how to roll it back, and why it remains a candidate rather than a verified contribution.
Output expectations
explore_outputs/CHANGESET.mdexplore_outputs/SCIENTIFIC_CHANGELOG.mdexplore_outputs/COMPARABILITY_REPORT.mdexplore_outputs/TOP_RUNS.mdexplore_outputs/status.json
Notes
Use references/explore-policy.md, ../ai-research-reproduction/references/research-rigor-principles.md, scripts/plan_code_changes.py, and scripts/write_outputs.py.