experiment-audit — upstream index

This is an index-only record created by OpenScientificSkills. It contains an attributed catalog summary, but does not bundle, mirror, or redistribute the upstream Skill instructions, code, or assets.

What this Skill is for

This indexed Skill is intended for planning, running, or documenting research experiments. It helps researchers discover the upstream project that may provide instructions, templates, scripts, or workflow guidance for that task. Exact capabilities, requirements, and behavior must be confirmed in the canonical repository because they can change upstream.

Attributed upstream catalog summary:

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.

Canonical source

• Upstream author or maintainer: wanshuiyin
• Repository: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
• Upstream Skill path: skills/experiment-audit/SKILL.md
• Upstream license status: not verified

The CC0-1.0 value on this ModelScope entry applies only to the newly written index structure and explanatory text. It does not apply to the attributed upstream summary and does not grant any license to the upstream repository.

Before use

Open the canonical repository, review its current license, security posture, dependencies, and instructions, and obtain any permission required by the upstream author. Always treat the upstream repository as the source of truth.