Experiment Audit

Experiment Audit is a Quality skill for Claude Code, published by wanshuiyin in Auto-claude-code-research-in-sleep.

14.7K stars1.3K forkson wanshuiyin/Auto-claude-code-research-in-sleepAdded 2026/08/14Repository updated 2026/08/11

ai-researchai-toolsarisautonomous-agentclaudeclaude-codeclaude-code-skillscodexdeep-learninggptidea-generationllmmachine-learningmcpmcp-serverml-researchopenaipaper-reviewpaper-writingresearch-automation

Install in seconds

Install Experiment Audit

Copy Experiment Audit into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/main/skills/experiment-audit ~/.claude/skills/experiment-audit

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/experiment-audit/SKILL.md in wanshuiyin/Auto-claude-code-research-in-sleep
Installs to: ~/.claude/skills/experiment-audit
Collection: One of 25 skills cataloged from this repository
Category: Quality — 1354 skills

What Experiment Audit does

Experiment Audit verifies experiment integrity before results are claimed, using cross-model review to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use it when the user asks to audit experiments or after experiments complete but before writing claims.

Experiment Audit is cataloged under Quality on DirSkills. Experiment Audit comes from a repository tagged ai-research, ai-tools, aris, autonomous-agent and claude.

Documentation

README

Excerpt

Experiment Audit: Cross-Model Integrity Verification

🔒 Do not wrap this skill in /loop, /schedule, or CronCreate. It is verdict-bearing — it judges experiment integrity. Re-running that verdict on a timer adds no new signal, and a loop that accepts its own output to decide when to stop crosses into self-acquittal (acceptance-gate.md). Schedule the external wait that precedes it — experiments done → then audit once. See shared-references/external-cadence.md.

Audit experiment integrity for: $ARGUMENTS

Why This Exists

This is the opening of the README. Read the full README on GitHub.

Commands Experiment Audit provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/loop
/schedule
/research-pipeline
/experiment-bridge
/auto-review-loop
/experiment-audit
/result-to-claim
/paper-write

Frequently asked about Experiment Audit

What else does wanshuiyin publish alongside Experiment Audit?
Experiment Audit is one of 25 skills that DirSkills catalogs from wanshuiyin/Auto-claude-code-research-in-sleep, the repository it ships in. Its siblings there include Ablation Planner, AlphaXiv and Analyze Results. Each one is a separate skill with its own page in this directory, installs the same way Experiment Audit does, and is maintained by wanshuiyin in that same repository. The rest of the collection is listed on the wanshuiyin/Auto-claude-code-research-in-sleep page.
How does Experiment Audit compare to other Quality skills?
Experiment Audit ranks #159 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Experiment Audit against them. Open each page to compare what they document and how they install.