Peer Review
K-Dense-AI/claude-scientific-writer
Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments.
Rigorous audit of experiment results before they become paper claims.
Install Experiment Audit
$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install appleweiping/WEIPING_WIKI experiment-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-audit .claude/skills/experiment-audit && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-audit into .claude/skills/experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-audit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-auditType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install appleweiping/WEIPING_WIKI experiment-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-audit .agents/skills/experiment-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-audit into .agents/skills/experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-audit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install appleweiping/WEIPING_WIKI experiment-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-audit .cursor/skills/experiment-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-audit into .cursor/skills/experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-audit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/appleweiping/WEIPING_WIKI.git --path .claude/skills/aris/skills/experiment-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install appleweiping/WEIPING_WIKI experiment-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-audit .gemini/skills/experiment-audit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-audit into .gemini/skills/experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-audit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install appleweiping/WEIPING_WIKI experiment-auditInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-audit .github/skills/experiment-audit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-audit into .github/skills/experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-audit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add appleweiping/WEIPING_WIKI --skill experiment-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install appleweiping/WEIPING_WIKI experiment-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/aris/skills/experiment-audit .opencode/skills/experiment-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.claude/skills/aris/skills/experiment-audit into .opencode/skills/experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "experiment-audit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
experiment-audit- GitHub stars
- 119
- Token cost
- ~999 tokens
- SKILL.md length
- 431 words
- Files
- 1
- Skills in repo
- 51
- Repo updated
- First seen
- Licence
- MIT
At a glance
Rigorous audit of experiment results before they become paper claims.
- Works in 5 steps: Statistical Validity → Reproducibility Check → Fair Comparison → …
- User says experiment-audit
- SKILL.md covers Decision Gate, Phase 1 — Statistical Validity, Phase 2 — Reproducibility Check and Phase 3 — Fair Comparison, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Experiment Audit is an agent skill from appleweiping/WEIPING_WIKI. Rigorous audit of experiment results before they become paper claims. Checks statistical validity, reproducibility, fair comparison, and evidence quality. Use when user says "experiment-audit", "审核实验", "audit results", "check my results", or after run-experiment produces results that need validation.
Its SKILL.md is about 1000 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Research & Science, covering Reproducible research. The repository describes itself as: knowledge base managed with an LLM workflow. The licence is MIT.
When your agent uses it
- User says experiment-audit
- Check my results
- After run-experiment produces results that need validation
Example prompts
- “experiment-audit”
- “audit results”
- “check my results”
- “/experiment-audit”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 76fdc42. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Experiment Audit loads about 999 tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 431 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from appleweiping/WEIPING_WIKI at commit 76fdc42, republished under its MIT licence (© appleweiping). 431 words, ~999 tokens.
Download SKILL.mdSave it as
.claude/skills/experiment-audit/SKILL.md (or your agent's skills folder).- name
- experiment-audit
- description
- Rigorous audit of experiment results before they become paper claims. Checks statistical validity, reproducibility, fair comparison, and evidence quality. Use when user says "experiment-audit", "审核实验", "audit results", "check my results", or after run-experiment produces results that need validation.
Experiment Audit
Audit experiment results with the rigor of a hostile reviewer. Your job is to find problems BEFORE submission.
Decision Gate
Before running:
- Results exist in
results/orrefine-logs/EXPERIMENT_TRACKER.mdshows completed blocks - At least one block has full seed runs (20+ seeds for paper claims)
- You have access to the experiment configs and code
Phase 1 — Statistical Validity
For each reported result:
- Sample size check: Are there 20+ seeds? (Required for paper evidence)
- Significance test: Run paired t-test or Wilcoxon signed-rank between our method and each baseline
- Effect size: Report Cohen's d or similar — is the improvement meaningful, not just significant?
- Confidence intervals: Report 95% CI for all primary metrics
- Multiple comparison correction: If testing against 8+ baselines, apply Bonferroni or Holm-Bonferroni
Verdict per comparison: PASS (p<0.05, meaningful effect) / MARGINAL (p<0.1) / FAIL (not significant)
Phase 2 — Reproducibility Check
- Config audit: Can you reproduce the exact run from config alone?
- Seed sensitivity: Is variance across seeds reasonable? (CV < 20% for stable metrics)
- Hardware sensitivity: Would different GPU/batch size change results?
- Code-result alignment: Does the code actually implement what the paper claims?
Red flags:
- Results only work with specific seeds → cherry-picking
- Variance is huge → unstable method
- Config doesn't match paper description → misrepresentation
Phase 3 — Fair Comparison
For each baseline:
- Same data splits? (Must be identical)
- Same preprocessing? (Must be identical)
- Same compute budget? (Comparable training time/FLOPs)
- Best hyperparameters? (Did you tune baselines fairly, or use defaults while tuning yours?)
- Official numbers match? (If using official implementation, do you reproduce their reported numbers?)
Red flags:
- Our method gets 10x more compute → unfair
- Baselines use default hyperparams while ours is tuned → unfair
- Different data splits → incomparable
Show full SKILL.md (144 more words)Show less
Phase 4 — Evidence Classification
Label every result:
| Label | Meaning | Can use in paper? |
|---|---|---|
paper_result | Full seeds, statistically valid, fair comparison | YES |
official | Full seeds but needs one more check | Almost |
diagnostic | Partial seeds or preliminary | NO (supplementary only) |
pilot | Quick test, not rigorous | NO |
Only paper_result labeled evidence goes into the main paper.
Phase 5 — Audit Report
Produce a structured audit report:
# Experiment Audit Report
Date: YYYY-MM-DD
Auditor: Codex (GPT-5.5)
## Summary Verdict: PASS / CONDITIONAL PASS / FAIL
## Per-Block Results
| Block | Seeds | Significance | Effect Size | Fair? | Evidence Label |
|-------|-------|-------------|-------------|-------|----------------|
## Issues Found
1. [CRITICAL/MAJOR/MINOR] Description...
## Recommendations
1. ...Handoff
- Output:
refine-logs/AUDIT_REPORT.md - Update
refine-logs/EXPERIMENT_TRACKER.mdwith audit status - If PASS → Next ARIS step: paper-plan
- If CONDITIONAL PASS → Fix issues, re-audit
- If FAIL → Back to experiment-bridge or pivot
Hard Rules
- Never approve results with <20 seeds as paper evidence
- Never approve unfair comparisons (compute, tuning, data asymmetry)
- Always run significance tests — "looks better" is not evidence
- Audit must be done by a different agent than the one who ran experiments (cross-model review)
- Be adversarial — your job is to find problems, not confirm success
© appleweiping, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/aris/skills/experiment-audit of appleweiping/WEIPING_WIKI.
Open the folder on GitHubat commit 76fdc42
Compare with similar skills
Experiment Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Experiment Audit this skillappleweiping/WEIPING_WIKI | 119 | — | ~999 | Automated safety check: Pass | MIT | |
| Peer ReviewK-Dense-AI/claude-scientific-writer | 2.4k | 2 repos | ~3.1k | Automated safety check: Notes | MIT | |
| Compute Environment Setupaipoch/open-science | 5.5k | 1 repos | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| CHARLS Paper Reproduction Guidexjtulyc/MedgeClaw | 617 | 1 repos | ~1.8k | Automated safety check: Pass | None | |
| Figure Styleaipoch/open-science | 5.5k | — | ~5.1k | Automated safety check: Pass | Apache-2.0 | |
| Add Bactopia Toolbactopia/bactopia | 522 | — | ~4.1k | Automated safety check: Pass | MIT |
Similar skills
Compute Environment Setup
aipoch/open-science
Prepares setup instructions and a named activation file for a user-managed software environment on an Open-Science SSH or Slurm compute host.
CHARLS Paper Reproduction Guide
xjtulyc/MedgeClaw
Guides an agent through reproducing papers built on the CHARLS health and retirement survey, from variable mapping to cognition, depression and isolation scores.
Figure Style
aipoch/open-science
Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots.
Add Bactopia Tool
bactopia/bactopia
Scaffold a complete Bactopia Tool across all three tiers -- module, subworkflow, and workflow entry point under workflows/bactopia-tools/.
Modeling Code and Result Contracts
yushui2022/MathModel-Skill
Generates result-evidence contracts, tables and runnable q1 to q3 modeling code scaffolds for a math modeling paper from a model route, a data plan and cleaned data.
More from appleweiping/WEIPING_WIKI
All 51 skills in this repoCommunication Assistant
appleweiping/WEIPING_WIKI
Unified lazy-mode communication assistant for Vipin across WhatsApp, WeChat, QQ, Feishu/Lark, and email.
Content Refinement Agent
appleweiping/WEIPING_WIKI
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from appleweiping/WEIPING_WIKI.
Chrome Automation
appleweiping/WEIPING_WIKI
Connect to and control Google Chrome browser using agent-browser with CDP (Chrome DevTools Protocol).
Email Assistant
appleweiping/WEIPING_WIKI
Personal Gmail and Google Workspace email assistant for Vipin.
Wechat Video Channel Publish
appleweiping/WEIPING_WIKI
A skill your agent uses when the user wants to log into 微信视频号, validate cookie state, upload videos, set scheduled publish time, fill long description, set a cover image, or save drafts through a…
Feishu Bridge
appleweiping/WEIPING_WIKI
Route Feishu/Lark content access for Codex. An agent skill from appleweiping/WEIPING_WIKI.
Related
Categories
Questions about Experiment Audit
What does Experiment Audit do?
Rigorous audit of experiment results before they become paper claims. Experiment Audit is an agent skill from appleweiping/WEIPING_WIKI. Rigorous audit of experiment results before they become paper claims.
When should I use Experiment Audit?
Experiment Audit fits situations like: user says experiment-audit; check my results; after run-experiment produces results that need validation.
How do I install Experiment Audit in Claude Code?
Run `npx skills add appleweiping/WEIPING_WIKI --skill experiment-audit -a claude-code`. Or copy the skill folder (.claude/skills/aris/skills/experiment-audit in appleweiping/WEIPING_WIKI) into .claude/skills/experiment-audit in your project. Claude Code loads it when a task matches its description.
How do I install Experiment Audit in Codex?
Run `npx skills add appleweiping/WEIPING_WIKI --skill experiment-audit -a codex`. Or copy the skill folder (.claude/skills/aris/skills/experiment-audit in appleweiping/WEIPING_WIKI) into .agents/skills/experiment-audit in your project. Codex loads it when a task matches its description.
Can I use Experiment Audit in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add appleweiping/WEIPING_WIKI --skill experiment-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/experiment-audit, .gemini/skills/experiment-audit, .github/skills/experiment-audit and .opencode/skills/experiment-audit in your project.
What does Experiment Audit need to run?
SKILL.md names no scripts, command-line tools or credentials: Experiment Audit is instructions for the agent only.
Does Experiment Audit access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Experiment Audit safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Experiment Audit use?
Experiment Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Experiment Audit use?
About 999 tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Experiment Audit?
Skills that share tags, products or a category with Experiment Audit: Peer Review (K-Dense-AI/claude-scientific-writer, 2.4k stars), Compute Environment Setup (aipoch/open-science, 5.5k stars), CHARLS Paper Reproduction Guide (xjtulyc/MedgeClaw, 617 stars) and Figure Style (aipoch/open-science, 5.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Experiment Audit?
appleweiping (a GitHub user) maintains it in appleweiping/WEIPING_WIKI, which has 119 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on August 26, 2026.
Source: appleweiping/WEIPING_WIKI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.