experiment-craft

A structured method for debugging and improving an existing research experiment, with records of hypotheses, runs, failures, results, and next steps.

In plain words
What is it for?
It is for diagnosing failed methods, investigating unexpected results, organizing experiment logs, and deciding what to test next.
Why use it?
It helps explain why an experiment is underperforming instead of encouraging repeated trial and error without learning from each run.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/camusgit/evoquant/experiment-craft
Any agent
npx skills add CamusGIT/EvoQuant --skill experiment-craft
Clone the repo
git clone --depth 1 https://github.com/CamusGIT/EvoQuant

Made for: Claude Code, Codex.

Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% copy Near-identical to another mod 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 $0.00172 $0.01585
Opus 5 $0.00086 $0.00792
Sonnet 5 $0.00034 $0.00317
Haiku 4.5 $0.00017 $0.00159

Measured 3d ago against content hash e70077c0c7b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

experiment-craft 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 3d 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.

Origin

This is a copy

94% identical to experiment-craft — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

EvoQuant/skills/experiment-craft/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experiment Craft

A systematic approach to running, debugging, and iterating on research experiments. The critical skill is not running more experiments — it's understanding WHY experiments fail.

When to Use This Skill

  • User's experiment is not working or producing unexpected results
  • User needs help diagnosing why a method fails on certain data
  • User wants to organize their experiment process with structured logging
  • User asks about debugging research code or iterating on approaches
  • User mentions "experiment debugging", "why doesn't this work", "experiment log", "results are wrong"

This skill is typically loaded from within experiment-pipeline when a stage attempt fails. After debugging, return to the pipeline's stage-gate structure to continue. Can also be used standalone for any experiment debugging.

The Debugging Mindset

Finding WHY experiments fail is the most critical research skill. Not analyzing results leads to two failure modes:

  1. Slow progress: Running random experiments without understanding failure causes
  2. Wasted time: Abandoning good approaches because activation tricks were missed

The goal is not to run more experiments. The goal is to run the RIGHT experiments — ones that isolate causes and test specific hypotheses.

5-Step Diagnostic Flow

When an experiment fails or produces unexpected results, follow these five steps:

Step 1: Collect Failure Cases

Gather concrete examples of bad results. Look at the actual outputs, not just aggregate metrics. What specifically went wrong? Are the failures systematic or random?

Step 2: Find a Working Version

You need a baseline that works. Two ways to find one:

  • Simplify the task: Reduce data complexity, relax the task setting, add more supervision, use easier inputs
  • Remove your changes: Start from the baseline method and remove your algorithmic improvements one by one

If you can't find any working version, simplify further until something works. There is always a simple enough version that works.

Read the full file on GitHub · 131 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 131 lines · 172 tokens per session scan A e70077c0c7b3

Subscribe to this mod's changes

experiment-craft is a skill published in the GitHub repository CamusGIT/EvoQuant (215 stars, last pushed 16d ago), licensed Apache-2.0. It adds 172 tokens to every session and 1,585 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to experiment-craft, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…

first-fluke/oh-my-agent · 73 tokens

jupyter-live-kernel

Use a live Jupyter kernel for stateful, iterative Python execution via hamelnb. Load this skill when the task involves exploration, iteration, or inspecting intermediate results — data science, ML experimentation, API exploration, or building up complex code step-by-step. Uses terminal to run CLI commands against a…

graniet/kheish · 70 tokens

manim-explainer

Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.

TeamWiseFlow/xiaobei · 55 tokens

songsee

Generate spectrograms and audio feature visualizations (mel, chroma, MFCC, tempogram, etc.) from audio files via CLI. Useful for audio analysis, music production debugging, and visual documentation.

graniet/kheish · 42 tokens

labrat-operator

Use when operating a labrat lab with Codex: checking health, choosing the next phase prompt, supervising runtime cycles, auditing candidates, synthesizing recent evaluations, or writing checkpoint notes.

ProjectDXAI/labrat · 42 tokens

research-innovation-explorer

Build literature-grounded research-question candidate landscapes by collecting papers, generating A+B matrices, and dynamically reviewing combinations with traceable evidence, uncertainty, and next checks. Use when an AI agent needs to explore a field, screen research questions, compare paper combinations, inspect…

foryourhealth111-pixel/research-innovation-explorer · 70 tokens