OpenAgentSkill Registry Manifest
Skill: experiment-audit
Slug: wanshuiyin-experiment-audit
Category: security
Description: 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.

Agent fit:
- Decision: 100/100 Production-ready
- Primary fit: Research agents
- Role: Primary pick

Supply profile:
- Track: Research and knowledge work
- Scenario: Research agents
- Applicable agents: Claude Code, OpenAI Agents, CLI, Codex, Cursor
- Maintenance: 13d since push
- Risk: Safe to try

Trust:
- Trust score: 85/100 Strong shortlist
- Audit: 89/100 Safe to try

Attribution:
- Status: Registry indexed
- Source: github fast track
- Creator: wanshuiyin
- Claim URL: https://www.openagentskill.com/skills/wanshuiyin-experiment-audit#claim-this-skill

Install:
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill experiment-audit

URLs:
- Web: https://www.openagentskill.com/skills/wanshuiyin-experiment-audit
- API: https://www.openagentskill.com/api/agent/skills/wanshuiyin-experiment-audit
- Install API: https://www.openagentskill.com/api/skills/wanshuiyin-experiment-audit/install
- Repository: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/main/skills/experiment-audit