Experiment Audit
Experiment Audit is an agent skill (a SKILL.md file) from wanshuiyin/Auto-claude-code-research-in-sleep. Audit experiment integrity before claiming results. It works with Claude Code and Codex and has 18,089 GitHub stars across a repository of 5 listed skills. Install it by copying the skill folder into your agent's skills directory.
Data as of from the GitHub API; description from the skill's SKILL.md. Report an error
Add this skill
Claude
This repository is a Claude Code plugin marketplace. In Claude Code:
/plugin marketplace add wanshuiyin/Auto-claude-code-research-in-sleep
/plugin install aris@arisIn the Claude apps, zip the experiment-audit folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).
ChatGPT / Codex
Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:
git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git
cp -r Auto-claude-code-research-in-sleep/skills/experiment-audit .agents/skills/experiment-audit # repo; ~/.agents/skills for all projectsStandalone skills also load in the ChatGPT desktop app.
Cursor
Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:
git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git
cp -r Auto-claude-code-research-in-sleep/skills/experiment-audit .cursor/skills/experiment-audit # project; ~/.cursor/skills for all projectsSource (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)
What this skill does
Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
When it triggers
- Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope.
- Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
- "审计实验"
- "check experiment integrity"
- "audit results"
- "实验诚实度"
More skills in wanshuiyin/Auto-claude-code-research-in-sleep
5 skills are listed from this repository.
Similar skills
More security skills
Long Horizon Prompting
muratcankoylan/Agent-Skills-for-Context-Engineering
This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal…
Active · last commit Oct 12, 2026
SecurityPythonLark Shared
larksuite/cli
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or…
Active · last commit Oct 14, 2026
SecurityGoCode Review
phuryn/pm-skills
Review code for actionable defects. Correctness is the core; performance and security are optional sub-cases of the same engine.
Active · last commit Oct 16, 2026
SecuritySkill Security Auditor
eigent-ai/eigent
Security auditing for code, configs, and infrastructure.
Active · last commit Oct 25, 2026
SecurityTypeScriptAnalyzing Indicators Of Compromise
mukul975/Anthropic-Cybersecurity-Skills
Analyzes indicators of compromise (IOCs) including IP addresses, domains, file hashes, URLs, and email artifacts to determine maliciousness confidence, campaign attribution, and blocking priority.
Active · last commit Aug 31, 2026
SecurityPythonLoop Library
alirezarezvani/claude-skills
Discover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, verification, stopping conditions, guardrails, and handoffs.
Active · last commit Oct 23, 2026
SecurityPython
How do I install the Experiment Audit skill?
In Claude Code, run /plugin marketplace add wanshuiyin/Auto-claude-code-research-in-sleep and then /plugin install aris@aris. For Codex or Cursor, copy the experiment-audit folder into .agents/skills/ or .cursor/skills/.
Is the Experiment Audit skill free?
Yes. The repository is open source under the MIT license.
Is Experiment Audit maintained?
The repository's most recent commit was on Oct 24, 2026. Its latest release is v0.4.28. appsgit only lists skills from repositories with a commit in the last six months.