Peer Review
K-Dense-AI/claude-scientific-writer
Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments.
Full statistical audit of experiment results. An agent skill from appleweiping/WEIPING_WIKI.
Install Aris Experiment Audit
$ npx skills add appleweiping/WEIPING_WIKI --skill aris-experiment-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install appleweiping/WEIPING_WIKI aris-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/.codex/skills/aris-experiment-audit .claude/skills/aris-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 "aris-experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-audit into .claude/skills/aris-experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-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/.codex/skills/aris-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 aris-experiment-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install appleweiping/WEIPING_WIKI aris-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/.codex/skills/aris-experiment-audit .agents/skills/aris-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 "aris-experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-audit into .agents/skills/aris-experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-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 aris-experiment-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install appleweiping/WEIPING_WIKI aris-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/.codex/skills/aris-experiment-audit .cursor/skills/aris-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 "aris-experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-audit into .cursor/skills/aris-experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-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 .codex/skills/aris-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 aris-experiment-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install appleweiping/WEIPING_WIKI aris-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/.codex/skills/aris-experiment-audit .gemini/skills/aris-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 "aris-experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-audit into .gemini/skills/aris-experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-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 aris-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 aris-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/.codex/skills/aris-experiment-audit .github/skills/aris-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 "aris-experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-audit into .github/skills/aris-experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-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 aris-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 aris-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/.codex/skills/aris-experiment-audit .opencode/skills/aris-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 "aris-experiment-audit" agent skill from https://github.com/appleweiping/WEIPING_WIKI/tree/main/.codex/skills/aris-experiment-audit into .opencode/skills/aris-experiment-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aris-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
aris-experiment-audit- GitHub stars
- 119
- Token cost
- ~2.3k tokens
- SKILL.md length
- 938 words
- Files
- 1
- Skills in repo
- 51
- Repo updated
- First seen
- Licence
- MIT
At a glance
Full statistical audit of experiment results. An agent skill from appleweiping/WEIPING_WIKI.
- Works in 5 steps: Statistical Validity → Reproducibility Audit → Fair Comparison Audit → …
- Tasks that involve Reproducible research
- SKILL.md covers Your Mandate, Phase 1: Statistical Validity, Phase 2: Reproducibility Audit and Phase 3: Fair Comparison Audit, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Aris Experiment Audit is an agent skill from appleweiping/WEIPING_WIKI. Full statistical audit of experiment results. This is Codex's PRIMARY role in ARIS. Check significance, effect sizes, fair comparison, reproducibility, evidence labeling. Triggers: "experiment-audit", "audit results", "check my results", "审核实验", "statistical review", "are these results valid", "can I publish this"
Its SKILL.md is about 2.3k 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 and Statistics. The repository describes itself as: knowledge base managed with an LLM workflow. The licence is MIT.
When your agent uses it
- Tasks that involve Reproducible research
- Tasks that involve Statistics
Example prompts
- “experiment-audit”
- “audit results”
- “check my results”
- “/aris-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.
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
Aris Experiment Audit loads about 2.3k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 938 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). 938 words, ~2,321 tokens.
Download SKILL.mdSave it as
.claude/skills/aris-experiment-audit/SKILL.md (or your agent's skills folder).- name
- aris-experiment-audit
- description
- Full statistical audit of experiment results. This is Codex's PRIMARY role in ARIS. Check significance, effect sizes, fair comparison, reproducibility, evidence labeling. Triggers: "experiment-audit", "audit results", "check my results", "审核实验", "statistical review", "are these results valid", "can I publish this"
- role
- auditor
- stage
- experiment-audit
ARIS Experiment-Audit: Full Statistical Audit
This is your PRIMARY skill. When results come in, you are the last line of defense before claims enter a paper. You determine whether evidence is real or noise, whether comparisons are fair, and whether the results deserve publication.
Your Mandate
- NO result enters a paper without your audit stamp
- You protect the researcher from publishing false claims
- You protect the field from irreproducible results
- A "PASS" from you means: "I would defend these results under cross-examination"
Phase 1: Statistical Validity
1.1 Significance Testing
For EACH claimed improvement, verify:
| Claim | Test Used | p-value | Threshold | Significant? | Appropriate Test? |
|---|---|---|---|---|---|
| [claim] | [test] | [p] | [alpha] | Yes/No | Yes/No |
Required Checks
- Correct test selected for data distribution
- Normal data → paired t-test or ANOVA
- Non-normal → Wilcoxon signed-rank or Mann-Whitney U
- Multiple comparisons → Bonferroni/Holm correction applied
- Two-tailed test used (unless one-tailed pre-registered)
- Sample size sufficient for claimed effect (power analysis)
- Independence assumption holds (seeds are truly independent runs)
- Multiple comparison correction applied if >3 comparisons
Significance Red Flags
| Flag | Severity | Action |
|---|---|---|
| p = 0.04-0.05 with no correction | HIGH | Require more seeds or correction |
| Only best seed reported | CRITICAL | Invalidate result |
| Significance claimed without test | CRITICAL | Cannot publish |
| Different N across methods | HIGH | Explain or equalize |
| p-hacking pattern (many metrics, report best) | CRITICAL | Require pre-registration |
1.2 Effect Size
Raw p-values are insufficient. For each significant result:
| Comparison | Effect Size Metric | Value | Interpretation |
|---|---|---|---|
| [A vs B] | Cohen's d / eta^2 / CLES | [value] | Negligible/Small/Medium/Large |
Effect Size Interpretation (Cohen's d)
- |d| < 0.2: Negligible — not practically meaningful even if significant
- 0.2 <= |d| < 0.5: Small — real but may not matter in practice
- 0.5 <= |d| < 0.8: Medium — meaningful improvement
- |d| >= 0.8: Large — substantial improvement
Hard rule: If effect size is "Negligible" → result cannot be a main claim.
1.3 Confidence Intervals
- 95% CI reported for all main results
- CIs do not overlap for claimed improvements (or overlap is minimal)
- CI width is reasonable (not so wide as to be uninformative)
- Bootstrap CIs used if distribution is unclear
Phase 2: Reproducibility Audit
2.1 Seed Variance Analysis
| Method | Mean | Std | CV (%) | Min | Max | Outlier Seeds? |
|---|---|---|---|---|---|---|
| Proposed | ||||||
| Baseline 1 | ||||||
| Baseline 2 |
Variance Checks
- CV < 5% for stable methods (flag if higher)
- No single seed dominates the mean (remove-one-seed sensitivity)
- Variance is similar across methods (heteroscedasticity check)
- Number of seeds >= 20 for paper results, >= 5 for pilot
- All seeds completed (no silent failures)
Variance Red Flags
| Flag | Severity | Implication |
|---|---|---|
| CV > 10% | HIGH | Results unstable, need more seeds |
| One seed is 2+ std from mean | MEDIUM | Investigate outlier |
| Proposed method has lower variance than baselines | MEDIUM | May indicate overfitting to eval |
| Some seeds failed/missing | HIGH | Survivorship bias |
2.2 Config Alignment Verification
- Reported config matches actual run config (check logs)
- No manual overrides during execution
- Hardware matches what's reported
- Library versions are pinned and recorded
Phase 3: Fair Comparison Audit
3.1 Condition Equality
For each pair of methods being compared:
| Condition | Method A | Method B | Equal? |
|---|---|---|---|
| Training data | |||
| Preprocessing | |||
| Compute budget (FLOPs or time) | |||
| Hyperparameter tuning budget | |||
| Number of parameters | |||
| Evaluation data | |||
| Evaluation metric implementation | |||
| Random seeds used | |||
| Hardware |
3.2 Unfair Advantage Detection
Check for these common sources of unfair advantage:
- Proposed method does NOT get more tuning iterations
- Proposed method does NOT use additional data (pre-training, augmentation)
- Proposed method does NOT have more parameters without acknowledgment
- Baselines are NOT using outdated implementations
- Baselines are NOT using known-bad hyperparameters
- Evaluation metric is NOT custom-designed to favor proposed method
- Test set was NOT used for any development decisions
Show full SKILL.md (370 more words)Show less
3.3 Comparison Verdict
COMPARISON FAIRNESS: [FAIR / MOSTLY_FAIR / UNFAIR]
ADVANTAGES DETECTED: [list]
DISADVANTAGES TO BASELINES: [list]
RECOMMENDATION: [proceed / equalize / re-run]Phase 4: Evidence Labeling
Every result must be labeled with its evidence tier. This determines where it can appear.
Evidence Tier Definitions
| Tier | Label | Requirements | Can Appear In |
|---|---|---|---|
| T1 | paper_result | >=20 seeds, significance test passes, effect size reported, fair comparison | Main paper claims |
| T2 | official | >=10 seeds, significance test passes, fair comparison | Paper with caveat |
| T3 | diagnostic | >=5 seeds, informative but not rigorous enough for claims | Appendix only |
| T4 | pilot | <5 seeds or exploratory | Internal use only |
Labeling Checklist
For each result, assign tier:
| Result | Seeds | Sig. Test | Effect Size | Fair | Tier |
|---|---|---|---|---|---|
| [result 1] | Pass/Fail | Reported? | Yes/No | T? | |
| [result 2] | Pass/Fail | Reported? | Yes/No | T? |
Labeling Rules
- A result CANNOT be labeled higher than its weakest dimension allows
- If seeds < 20 → maximum T2
- If no significance test → maximum T3
- If comparison is unfair → maximum T3
- If effect size is negligible → maximum T3 regardless of other factors
- Pilot results (T4) must NEVER appear in paper, even in appendix
Phase 5: Structured Audit Report
Summary Scores
| Dimension | Score | Status |
|---|---|---|
| Statistical Validity | /10 | |
| Reproducibility | /10 | |
| Fair Comparison | /10 | |
| Evidence Quality | /10 | |
| Paper Readiness | /10 |
Scoring Rubric
- 1-3: Results are unreliable. Cannot be published in any form.
- 4-5: Results have significant gaps. Major revisions needed.
- 6-7: Results are acceptable with noted limitations.
- 8-9: Results are strong. Minor notes only.
- 10: Results are exemplary. Would survive any review.
Verdict Decision Matrix
| Condition | Verdict |
|---|---|
| All >= 8, all T1 results have full evidence | PASS — ready for paper |
| All >= 6, most results T1/T2 | CONDITIONAL PASS — address notes |
| Any dimension <= 4 | FAIL — fix before any publication |
| Statistical validity <= 5 | FAIL — fundamental stats issues |
| Fair comparison <= 5 | FAIL — re-run with equalized conditions |
| Only T3/T4 results | INSUFFICIENT — need more seeds/rigor |
Final Verdict Format
========================================
EXPERIMENT AUDIT VERDICT
========================================
VERDICT: [PASS / CONDITIONAL PASS / FAIL / INSUFFICIENT]
CONFIDENCE: [Low / Medium / High]
SCORES:
Statistical Validity: X/10
Reproducibility: X/10
Fair Comparison: X/10
Evidence Quality: X/10
Paper Readiness: X/10
AVERAGE: X.X/10
EVIDENCE TIERS:
T1 (paper_result): [count] results
T2 (official): [count] results
T3 (diagnostic): [count] results
T4 (pilot): [count] results
CRITICAL ISSUES: [count]
[list each]
HIGH ISSUES: [count]
[list each]
BLOCKING FOR PUBLICATION: [Yes/No]
BLOCKING ISSUE: [one-line or "None"]
RECOMMENDED ACTIONS:
1. [most important fix]
2. [second fix]
3. [third fix]
========================================Interaction Rules
- This is your most important role. Be thorough. Miss nothing.
- Never rubber-stamp results. Even good results deserve full audit.
- If you cannot verify something (e.g., you don't have access to logs), state it explicitly.
- Distinguish between "I verified this is correct" and "I cannot check this."
- If results are genuinely strong, say so clearly. Researchers need confidence too.
- Track audit history. If results were previously FAIL and are resubmitted, verify fixes.
- When in doubt, request more seeds. Seeds are cheap; retracted papers are expensive.
© 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 .codex/skills/aris-experiment-audit of appleweiping/WEIPING_WIKI.
Open the folder on GitHubat commit 76fdc42
Compare with similar skills
Aris 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 |
|---|---|---|---|---|---|---|
| Aris Experiment Audit this skillappleweiping/WEIPING_WIKI | 119 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Peer ReviewK-Dense-AI/claude-scientific-writer | 2.4k | 2 repos | ~3.1k | Automated safety check: Notes | MIT | |
| Academic Paper Reproduction Methodologyxjtulyc/MedgeClaw | 617 | 1 repos | ~1.3k | Automated safety check: Pass | None | |
| Bio Experimental Design Multiple TestingGPTomics/bioSkills | 1.2k | 1 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Scientific Critical Thinkingjaechang-hits/SciAgent-Skills | 371 | 1 repos | ~4.7k | Automated safety check: Pass | CC-BY-4.0 | |
| Fcr Revision And Rebuttalfranklee16/academic-research-skills | 223 | 1 repos | ~1.1k | Automated safety check: Pass | None |
Similar skills
Academic Paper Reproduction Methodology
xjtulyc/MedgeClaw
Six-phase process for reproducing a published paper's results from provided data, from variable mapping and sample filtering through regression tables and a written report.
Bio Experimental Design Multiple Testing
GPTomics/bioSkills
Controls error rates across thousands of simultaneous tests in genomics discovery using false-discovery-rate methods (Benjamini-Hochberg 1995; Benjamini-Yekutieli 2001 for arbitrary dependence…
Scientific Critical Thinking
jaechang-hits/SciAgent-Skills
Evaluating scientific evidence and claims. An agent skill from jaechang-hits/SciAgent-Skills.
Fcr Revision And Rebuttal
franklee16/academic-research-skills
A skill your agent uses when writing the response to a Field Crops Research (FCR) revision decision (major or minor) and revising the manuscript.
Aistats Writing Style
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when revising an AISTATS paper for concise AI-statistics framing, theorem-and-experiment clarity, 8-page two-column compression, double-blind wording, reproducibility…
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 Aris Experiment Audit
What does Aris Experiment Audit do?
Full statistical audit of experiment results. An agent skill from appleweiping/WEIPING_WIKI. Aris Experiment Audit is an agent skill from appleweiping/WEIPING_WIKI. Full statistical audit of experiment results.
When should I use Aris Experiment Audit?
Aris Experiment Audit fits situations like: tasks that involve Reproducible research; tasks that involve Statistics.
How do I install Aris Experiment Audit in Claude Code?
Run `npx skills add appleweiping/WEIPING_WIKI --skill aris-experiment-audit -a claude-code`. Or copy the skill folder (.codex/skills/aris-experiment-audit in appleweiping/WEIPING_WIKI) into .claude/skills/aris-experiment-audit in your project. Claude Code loads it when a task matches its description.
How do I install Aris Experiment Audit in Codex?
Run `npx skills add appleweiping/WEIPING_WIKI --skill aris-experiment-audit -a codex`. Or copy the skill folder (.codex/skills/aris-experiment-audit in appleweiping/WEIPING_WIKI) into .agents/skills/aris-experiment-audit in your project. Codex loads it when a task matches its description.
Can I use Aris 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 aris-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/aris-experiment-audit, .gemini/skills/aris-experiment-audit, .github/skills/aris-experiment-audit and .opencode/skills/aris-experiment-audit in your project.
What does Aris Experiment Audit need to run?
SKILL.md names no scripts, command-line tools or credentials: Aris Experiment Audit is instructions for the agent only.
Does Aris 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 Aris 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 Aris Experiment Audit use?
Aris 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 Aris Experiment Audit use?
About 2.3k tokens (SKILL.md is roughly 9.3k 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 Aris Experiment Audit?
Skills that share tags, products or a category with Aris Experiment Audit: Peer Review (K-Dense-AI/claude-scientific-writer, 2.4k stars), Academic Paper Reproduction Methodology (xjtulyc/MedgeClaw, 617 stars), Bio Experimental Design Multiple Testing (GPTomics/bioSkills, 1.2k stars) and Scientific Critical Thinking (jaechang-hits/SciAgent-Skills, 371 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Aris 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.