NanoResearch Experiment Skeleton

Turns an experiment blueprint JSON into a runnable multi-module ML training/eval/ablation skeleton

Tested · Works

Test report

Verdict
Tested · Works
Score
8.8/10
Tested
Jul 24, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 30, 2026 · 9a8be6d

This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 24, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Fed it a real CIFAR-10 label-smoothing blueprint with a four-value eps sweep: the skill produced 11 files across data/models/training/evaluation/configs plus one YAML per ablation value, both requested metrics (accuracy and expected calibration error), early stopping and checkpointing, all Python parsing and all YAML valid. The no-skill baseline collapsed the sweep into a single CLI flag and dropped the calibration metric entirely.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 8/10
  • Docs & honesty 4/5

What NanoResearch Experiment Skeleton does

Reads a papers/experiment_blueprint.json (datasets, baselines, metrics, ablation groups) and scaffolds an experiments/ project with data, models, training, evaluation, per-ablation YAML configs, and a run.py entry point. Triggers when you ask to scaffold or generate code from an ML experiment blueprint or plan.

How to install NanoResearch Experiment Skeleton

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger NanoResearch Experiment Skeleton

  • /nanoresearch-experiment Turns an experiment blueprint JSON into a runnable multi-module ML training/eval/ablation skeleton

It also activates on plain-language prompts like these:

  • Scaffold an ML experiment project from this blueprint JSON
  • Generate training and eval code for my ablation groups
  • Build the experiments skeleton from experiment_blueprint.json

Frequently asked questions

Is the NanoResearch Experiment Skeleton skill free?
Yes. The skill itself is free from OpenRaiser/NanoResearch. SkillProof publishes the install command and an independent test verdict at no cost.
Does NanoResearch Experiment Skeleton work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 24, 2026. Verdict: Tested · Works. Fed it a real CIFAR-10 label-smoothing blueprint with a four-value eps sweep: the skill produced 11 files across data/models/training/evaluation/configs plus one YAML per ablation value, both requested metrics (accuracy and expected calibration error), early stopping and checkpointing, all Python parsing and all YAML valid. The no-skill baseline collapsed the sweep into a single CLI flag and dropped the calibration metric entirely.
What is the NanoResearch Experiment Skeleton SkillProof Score?
8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install NanoResearch Experiment Skeleton?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use NanoResearch Experiment Skeleton with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.