Skills lllllllama/rigorpilot-skills RigorPilot

ai-research-explore

Use it when: you have a working baseline and want to try new research ideas on top of it, with the benchmark and evaluation fixed in advance
It does: ranks candidate ideas, tests them one at a time on an isolated branch, and compares each with the baseline
You get: results in explore_outputs, marked as candidates and never as reproduced results, with notes on what changed and how comparable they are
Needs: you to ask for exploration explicitly, and a saved baseline: a branch, commit, checkpoint or run record
Unlike RigorPilot's reproduction skills: it tries new ideas instead of rerunning what the README documents

Skill 5 of 5 in the RigorPilot bundle · Before it: minimal-run-and-audit

Only works inside its bundle: Loads its required research loop and shared runtime from ai-research-reproduction, the repo's main skill, and hands code changes and trial runs to the repo's explore-code and explore-run skills. Install RigorPilot instead.

TLDR

The exploration side of RigorPilot, a set of skills that reproduces deep-learning research code by following its README, kept separate from its reproduction work. You fix the ground rules first: task, dataset, benchmark, how results are evaluated, the state-of-the-art results you compare against, and a compute budget. The agent then alternates between planning and trying. While planning, it studies the repo, keeps your own ideas, adds a few single-change ideas of its own, looks up supporting papers (in a local reference manager such as Zotero first, the web optionally) and ranks ideas by expected gain, cost, risk and ease of rollback. While trying, it makes one bounded change or run, checks it quickly, collects evidence and ranks it against the baseline; measured results outrank predictions. It stops for you at blockers, unclear scientific meaning, an exhausted budget or ideas too close to call. It won't call a gain new or state-of-the-art without a literature comparison, ablations and a fair comparison.

Summarizes the skill at fb3ccdf.

npx skills add https://github.com/lllllllama/rigorpilot-skills --skill ai-research-explore

skills.sh page · Source on GitHub · All skills from lllllllama/rigorpilot-skills

Installs: 311,280 on skills.sh, Sep 21, 2026
Repo stars: 492 lllllllama/rigorpilot-skills
First seen: May 26, 2026 on skills.sh

Weekly installs

-100% over 8 weeks · week to Sep 21

Weekly values

Week to	Installs
Aug 3	11,263
Aug 10	32,324
Aug 17	50,300
Aug 24	41,285
Aug 31	77
Sep 7	73
Sep 14	64
Sep 21	49

Category	category:science Research reproduction, financial data, charts and diagrams.
Type	type:workflow A multi-step process the agent follows: interview, debug, run a TDD loop, review.
Effect	effect:local Its own steps create or change files, git state or local tools.
Needs	needs:none Instructions only. Works in any agent that supports skills.
Publisher	by:community Everyone else. Unverified vendor claims default to community.
Topics	ml-research research
Stack	stack:python

SKILL.md

From lllllllama/rigorpilot-skills at fb3ccdf. Checked daily, last changed Oct 20, 2026.

Frontmatter

name: ai-research-explore
description: Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of `current_research` with auditable repo understanding, idea gating, fair comparison, and governed experiments written to `explore_outputs/`. Do not use for README-first trusted reproduction, open-ended direction finding, narrow code-only or run-only exploration, passive repo analysis, verified novelty claims, or implicit experimentation.

ai-research-explore

Purpose

Use this as the Rigor Explore compatible skill slug after the researcher explicitly authorizes candidate-only work on top of a durable current_research anchor. The installed slug remains ai-research-explore for compatibility. Rigor Explore is for meaningful and potentially novel deep learning research candidates while preserving scientific rigor, comparability, reproducibility, and auditable collaboration. Novelty and significance remain hypotheses before literature contrast, ablation evidence, and fair comparison. The skill does not promise autonomous discovery, global benchmark completeness, novelty proof, or trusted reproduction success.

Start from the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md, then load ../ai-research-reproduction/references/research-rigor-principles.md for research claims and ../ai-research-reproduction/references/deep-learning-experiment-principles.md when experiment details affect comparability or reproducibility.

Fit

Use this skill only when the request has both:

Explicit exploration authorization such as candidate-only work, isolated branch or worktree, sweep, several variants, or exploratory ranking.
A durable current_research context such as a branch, commit, checkpoint, run record, or already-trained local model state.

Keep narrow code-only requests on explore-code. Keep narrow run-only requests on explore-run. Keep passive repository analysis on analyze-project. Keep README-first reproduction on ai-research-reproduction.

Research Rhythm

Use a two-loop rhythm:

Outer loop: understand the repository, freeze task/dataset/evaluation/budget, preserve user ideas, map sources, gate ideas, and decide whether the next experiment is worth running.
Inner loop: make one bounded candidate change or run, smoke-check it, collect evidence, rank it against the current anchor, and either stop or return to the outer loop with the new evidence.

This rhythm is a guide, not a rigid autonomous loop. Stop at explicit blockers, unclear scientific meaning, exhausted budget, missing anchor/evaluation, or a human checkpoint.

Workflow

Confirm current_research and explicit explore-lane authorization.
Accept either legacy variant_spec or higher-level research_campaign.
In campaign mode, freeze the task, dataset, benchmark, evaluation source, SOTA reference, and budget before candidate work.
Build only the repo-understanding artifacts needed for the current campaign, usually through analyze-project.
Run bounded, cache-first source lookup when source support matters; prefer local curated literature such as Zotero if available, then seed sources, repo-local locators, public locators, or optional web lookup. Treat lookup as source resolution, not an open-ended literature search.
Preserve researcher-provided ideas, optionally add a small bounded set of single-variable seed ideas, and rank ideas with explicit gates and score breakdowns.
Prefer one clear candidate at a time. Use explore-code for bounded code adaptation and explore-run for short-cycle trials or sweeps.
Use minimal-run-and-audit or run-train only when the exploratory plan requires real execution evidence.
Write candidate-only outputs to analysis_outputs/, sources/, and explore_outputs/ as appropriate; never present exploratory gains as trusted reproduction success. Include SCIENTIFIC_CHANGELOG.md and COMPARABILITY_REPORT.md for candidate scientific meaning and comparison boundaries.

Ranking and Evidence

Before execution, prioritize candidates by expected gain, cost, success likelihood, patch surface, dependency drag, evaluation risk, and rollback ease.
After execution, rank by real evidence first: command status, observed metrics, artifacts, changed paths, smoke results, and reproducibility notes.
Keep researcher-provided evaluation_source and sota_reference frozen for the campaign; do not claim they are globally complete.
If the top ideas are too close or the implementation cannot be decomposed into auditable units, stop for a checkpoint instead of silently choosing.

Campaign Inputs

research_campaign is preferred for Rigor Explore campaigns, but it should stay minimal. The durable core is:

current_research
task_family
dataset
benchmark
evaluation_source
sota_reference
compute_budget

Use candidate_ideas, variant_spec, research_lookup, idea_policy, idea_generation, source_constraints, feasibility_policy, baseline_gate, and execution_policy as optional guidance, not as fields the agent must fill for every campaign. See references/research-campaign-spec.md for the advanced schema and artifact expectations.

Reference Loading

Load references/ai-research-explore-policy.md for lane safety and candidate semantics.
Load references/research-campaign-spec.md only when a campaign file is present or the user asks for Rigor Explore campaign governance.
Load ../ai-research-reproduction/references/explore-variant-spec.md for run-level variant matrix details.
Load ../ai-research-reproduction/references/research-thinking-loop.md before proposing or ranking candidate changes; it is the required greedy observe-ground-design-compare cycle.
Load ../ai-research-reproduction/references/research-rigor-principles.md before making novelty, contribution, SOTA, or comparability statements.
Consult ~/.rigorpilot/PERSONAL_RIGOR.md if present, under ../ai-research-reproduction/references/continuous-learning-policy.md (advisory only; core wins).
Load ../ai-research-reproduction/references/deep-learning-experiment-principles.md when training, evaluation, baseline, ablation, metric, checkpoint, or dataset details matter.
Use scripts/orchestrate_explore.py and scripts/write_outputs.py for the existing deterministic artifact workflow.