skills.rest
Zayne-sprague
Zayne-spragueCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

experiment-management

Standardize experiment folders and lifecycle artifacts across research workflows.

5|Updated Mar 27, 2026
Search Tags:#workflow#documentation#research#lifecycle#red-team#experiment#canary
One-click install
npx skills add https://github.com/Zayne-sprague/Dr-Claude-Code --skill experiment-management
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: experiment-management
Source: https://github.com/Zayne-sprague/Dr-Claude-Code/tree/main/.claude/skills/experiment-management
Command: npx skills add https://github.com/Zayne-sprague/Dr-Claude-Code --skill experiment-management

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill ensures experiments are structured, tracked, and reproducible by enforcing a standard folder layout and lifecycle across the research workflow.

Core Features & Use Cases

  • Standardizes the experiment workspace with required artifacts (experiment.yaml, EXPERIMENT_README.md, flow_state.json, activity_log.jsonl, HUGGINGFACE_REPOS.md, questions.md, red_team_brief.md, user/).
  • Enforces the lifecycle stages (design, redteam, canary, validate, run, review) and governance rules described in .claude/rules/experiments.md.
  • Helps researchers bootstrap and track experiments from planning to review, with automatic dashboard syncing and artifact logging.

Quick Start

Create the directory notes/experiments/<name>/ and initialize the required files to begin tracking an experiment.

Frequently Asked Questions about experiment-management

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I structure reproducible research experiments with standardized artifacts?▼

The experiment lifecycle enforces sequential stages: design, redteam, canary, validate, run, and review. Each phase requires specific artifacts like red_team_brief.md during redteam or activity_log.jsonl during run, ensuring structured progression and thorough validation before full deployment.

What files do I need to bootstrap a tracked experiment workspace?▼

Yes, red-team phases are fully supported through red_team_brief.md artifacts and governance rules described in .claude/rules/experiments.md. This enforces adversarial testing within the experiment lifecycle, ensuring hypotheses undergo rigorous critique before proceeding to canary and validation stages.

Can I integrate HuggingFace repositories into my experiment lifecycle?▼

HuggingFace repository integration is tracked using the HUGGINGFACE_REPOS.md artifact within the standardized experiment workspace. This file logs relevant repositories alongside other lifecycle artifacts, maintaining reproducibility and governance across design, redteam, canary, validate, run, and review phases.

What's the best way to govern experiment workflows across multiple research phases?▼

Governing experiment workflows uses .claude/rules/experiments.md to enforce lifecycle stages and required artifacts across all research phases. This standardized approach ensures consistent folder layouts, automatic dashboard syncing, and comprehensive artifact logging from initial design through final review.

Related Skills

Explore More Education & Research Skills→
Tx1207Tx1207
5

~analyze

Summarize experiment results by evaluating evidence against the stated hypothesis and comparing to baselines.

Community
Intermediate
briannadoubtbriannadoubt

observability

Configure structured logs, metrics, and traces for Trebuchet actors with CloudWatch export.

Community
Intermediate
ihatesea69ihatesea69
3

weights-and-biases

Track, visualize, and optimize machine learning experiments with automatic logging and hyperparameter sweeps.

Community
Intermediate
nomoorynomoory
8

initiative-research

Create standardized research artifacts with enforced YAML frontmatter metadata and index updates for initiative subtopics.

Community
Advanced