Home / Skills / experiment-forensics
experiment-forensics
wanshuiyin/Anti-AutoresearchSkill
Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope inflation, method-described ≠ method-evaluated drift, synthesized-looking results, placeholder/fake data still wired into a released result, code-output ≠ reported-number mismatch, and missing reproducibility artifacts (an empirical/agent/LLM paper shipping neither code nor the prompts/c
Why this score
This repo hosts 10 skills, so its 165 stars are split between them (about 17 each) for scoring.
Popularity score: 60/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 20, 2026 at commit 5f5d82421c75, with Cisco's open-source skill-scanner.
What its code does:
- Runs shell commands Common for dev tools. Read the commands it runs.SKILL.md:183
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This oneexperiment-forensics wanshuiyin/Anti-Autoresearch · Skill | 60 | ★ 165 | ≈155 always | 18d ago |
| file-forensics apache/tika · Skill Both about forensic | 77 | ★ 4.1k | ≈22 always | 16d ago |
| forensic-prompt-compiler AnastasiyaW/codex-claude-code-config · Skill Both about forensic | 62 | ★ 212 | ≈28 always | 16d ago |
| experiment-design fcakyon/phd-skills · Skill Both about experiment | 64 | ★ 424 | ≈22 always | 24d ago |
| disk-forensics briiirussell/cybersecurity-skills · Skill Both about forensic and artifact | 55 | ★ 426 | ≈116 always | 5mo ago |
| forensics-analyst 0xSteph/pentest-ai-agents · Subagent Both about forensic and evidence | 64 | ★ 2.4k | ≈55 in chat | 29d ago |