Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add appleweiping/WEIPING_WIKI --skill experiment-auditgit clone --depth 1 https://github.com/appleweiping/WEIPING_WIKIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/appleweiping/weiping_wiki/experiment-audit)<a href="https://agentmods.dev/skills/appleweiping/weiping_wiki/experiment-audit"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/experiment-audit.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.00953 |
| Opus 5 | $0.00032 | $0.00477 |
| Sonnet 5 | $0.00013 | $0.00191 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
experiment-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 105 lines · 63 tokens per session scan A 91e94643de80
experiment-audit is a skill published in the GitHub repository appleweiping/WEIPING_WIKI (122 stars, last pushed 13d ago), licensed MIT. It adds 63 tokens to every session and 953 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…