ai-research-explore

Agent skill from lllllllama/rigorpilot-skills.

lllllllama ↓ 161k
Claude Code
View source ↗

What it does

  • Explicit exploration authorization such as candidate-only work, isolated
  • A durable currentresearch context such as a branch, commit, checkpoint,
  • Outer loop: understand the repository, freeze task/dataset/evaluation/budget,
  • Inner loop: make one bounded candidate change or run, smoke-check it, collect
  • Before execution, prioritize candidates by expected gain, cost, success
  • After execution, rank by real evidence first: command status, observed
  • Keep researcher-provided evaluationsource and sotareference frozen for

Requirements & configuration

  • requires real execution evidence.

Configuration: SCIENTIFIC_CHANGELOGCOMPARABILITY_REPORT

Derived from the skill's own SKILL.md documentation · extracted 2026-07-23

ai-research-explore FAQ

What does the ai-research-explore skill do?

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. Explicit exploration authorization such as candidate-only work, isolated A durable currentresearch context such as a branch, commit, checkpoint,

What does ai-research-explore require?

requires real execution evidence. Configuration keys: SCIENTIFIC_CHANGELOG, COMPARABILITY_REPORT.

How do I install ai-research-explore?

Run: npx -y skills add https://github.com/lllllllama/rigorpilot-skills --skill ai-research-explore --agent claude-code — the source lives at github.com/lllllllama/rigorpilot-skills.

Maintain ai-research-explore?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

ai-research-explore on getagentictools
[![ai-research-explore on getagentictools](https://getagentictools.com/badge/skills/lllllllama-rigorpilot-skills-ai-research-explore.svg)](https://getagentictools.com/skills/lllllllama-rigorpilot-skills-ai-research-explore?ref=badge)
npx agentictools info skills/lllllllama-rigorpilot-skills-ai-research-explore

The second line is the CLI lookup for this page — handy in READMEs and docs.