ml-experiment-design

ml-experiment-design is a skill for Claude Code from pengzhangzhi/superpowers-ml. It costs 42 tokens per session (767 once invoked), scanned A, original, MIT.

A planning guide that turns a rough machine-learning idea into a short experiment card before any training code is written. The card records the question, falsifiable prediction, exact comparison, metric, budget, and cheapest useful check.

In plain words
What is it for?
Use it to define an ML experiment's hypothesis, baseline, variant, primary metric, safeguards, resource budget, and first verification step.
Why use it?
It prevents experiments from starting with unclear goals or changing measurements. A single tested change and a predefined decision rule make the result easier to interpret.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the superpowers-ml plugin — 17 skills, 1 hook shipped together

Good fit Use it to define an ML experiment's hypothesis, baseline, variant, primary metric, safeguards, resource budget, and first verification step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pengzhangzhi/superpowers-ml/ml-experiment-design
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add pengzhangzhi/superpowers-ml --skill ml-experiment-design
Clone the repo
git clone --depth 1 https://github.com/pengzhangzhi/superpowers-ml

Made for: Claude Code.

Or install superpowers-ml, the plugin that ships this one along with the rest of its 17 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ml-experiment-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/pengzhangzhi/superpowers-ml/ml-experiment-design/github.svg)](https://agentmods.dev/skills/pengzhangzhi/superpowers-ml/ml-experiment-design)
Your own site
<a href="https://agentmods.dev/skills/pengzhangzhi/superpowers-ml/ml-experiment-design"><img src="https://agentmods.dev/badge/skills/pengzhangzhi/superpowers-ml/ml-experiment-design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ml-experiment-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/pengzhangzhi/superpowers-ml/ml-experiment-design"><img src="https://agentmods.dev/badge/skills/pengzhangzhi/superpowers-ml/ml-experiment-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 767 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.00767
Opus 5 $0.00021 $0.00383
Sonnet 5 $0.00008 $0.00153
Haiku 4.5 $0.00004 $0.00077

Measured 11d ago against content hash 33ca42749e9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ml-experiment-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ml-experiment-design/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ML Experiment Design

Overview

An ML idea is not runnable until it is a CARD. This skill turns a rough idea into a compact, one-screen experiment card — rung R0, the precondition for planning or launching anything. Fill it WITH your human partner; do not write training code until the card is settled.

Core principle: One change under test, one locked metric, one decision rule. If you cannot state in advance what result would change your mind, you are not ready to run.

Upstream: the idea comes from superpowers-ml:brainstorming. Downstream: the card drives superpowers-ml:ml-feedback-ladder (how to verify it cheaply) and superpowers-ml:writing-plans (the tasks).

The Experiment Card

Settle every field. Keep each to a line or two — a card, not a document.

  • Research question — the one question this run answers.
  • Hypothesis — specific and falsifiable: what changes, and the direction you expect.
  • Baseline — the exact, runnable comparison (config / commit, not "the usual setup").
  • Variant(s) — the SINGLE change under test. Anything else is a separate experiment.
  • Primary metric — one metric, locked now, that decides the outcome.
  • Guardrail metrics — what must NOT regress while the primary metric moves (cost, latency, memory, a quality/safety metric).
  • Dataset / split — train / val / test, and the leakage risk you checked for.
  • Seed policy — how many seeds, fixed or swept; how you tell seed noise from a real effect.
  • Budget — the compute / wall-clock ceiling you will spend before stopping to decide.
  • Cheapest useful rung — the smallest rung that tells you something real, to start at (see superpowers-ml:ml-feedback-ladder).
  • Success criterion — the threshold on the primary metric that CONFIRMS the hypothesis, set before running.
  • Exploratory-only — what this run may suggest but can never confirm (anything the locked primary metric does not measure).

One Change At A Time

A variant is ONE change, or you cannot attribute the result — two changes is two experiments. If your human partner wants to vary many things, that is a study: write a card per change, then design a ladder for each.

Read the full file on GitHub · 62 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 62 lines · 42 tokens per session scan A 33ca42749e9c

Subscribe to this mod's changes

ml-experiment-design is a skill published in the GitHub repository pengzhangzhi/superpowers-ml (8 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 767 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

hugging-face-model-trainer

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…

patchy631/ai-engineering-hub · 131 tokens

hugging-face-datasets

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.

patchy631/ai-engineering-hub · 49 tokens

marimo-pair

Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.

marimo-team/marimo · 57 tokens

grpo-finetune

Fine-tune a model with GRPO on Fireworks-managed GPUs from a plain-English task description and a dataset. Use this skill whenever the user wants to fine-tune, RL-tune, or GRPO-train a model on their own data — or says things like "train a model to extract/classify/score X", "fine-tune on this dataset", "set up a GRPO…

patchy631/ai-engineering-hub · 122 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

physicsnemo-shard-tensor

Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…

NVIDIA/physicsnemo · 152 tokens