tooluniverse

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

.env.template

Audit 0.4.1 · source sha 43be0fac747b · 28 Oct 2026Report an issue or request a re-scan

• Publishermims-harvard GitHub organizationOwner of the repository this skill is read from
• Source foldermims-harvard/tooluniverse/skills/tooluniverseThe exact folder we audited
• LicenceApache-2.0As the repository states it
• Commit pinned for this verdict43be0fac747bA new audit runs when the source changes
• Repository statusNot archivedPushed today
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: ToolUniverse plugin router. STEP 1 BEFORE ANY ANALYSIS: if the data folder contains `*_executed.ipynb`, run `tu run read_executed_notebook '{"data_folder":"<path>","search":"<keyword>"}'` to extract its cell outputs and…

---
name: tooluniverse
description: "ToolUniverse plugin router. STEP 1 BEFORE ANY ANALYSIS: if the data folder contains `*_executed.ipynb`, run `tu run read_executed_notebook '{\"data_folder\":\"<path>\",\"search\":\"<keyword>\"}'` to extract its cell outputs and apply EVERY filter/sample-exclusion the notebook used — even when the question says 'Using DESeq2/Run X/Compute Y' (this describes the METHOD the notebook used, not a request to rerun). The notebook's cell outputs are the only published authoritative answers; reimplementing or reading stale pre-computed CSVs in the data folder produces different numbers because of outlier-sample removal, library version, and filter steps you don't see by skimming. STEP 2 routing — pick a sub-skill name from this exact list (never invent): tooluniverse-rnaseq-deseq2 (RNA/miRNA-seq DE, correlation, PCA, clustering, dispersion), tooluniverse-gene-enrichment (GO/KEGG/Reactome/GSEA/pathway enrichment), tooluniverse-statistical-modeling (regression, ANOVA, ordinal/logistic, chi-square, correlation, power), tooluniverse-image-analysis (microscopy, colony, fluorescence, dose-response, .tif — including ANOVA / Dunnett / power-analysis on image-derived measurements), tooluniverse-epigenomics (DNA methylation, CpG, m6A, MeRIP-seq, bisulfite, ChIP-seq, chromatin), tooluniverse-sequence-analysis (FASTQ, Trimmomatic, BWA, samtools, coverage), tooluniverse-variant-analysis (VCF, VAF, SNP, mutation), tooluniverse-phylogenetics (treeness, PhyKIT, parsimony), tooluniverse-single-cell (scRNA, h5ad, scanpy), tooluniverse-crispr-screen-analysis (MAGeCK, sgRNA), tooluniverse-proteomics-analysis (mass spec, TMT). Use for CSV/Excel/VCF/FASTA/h5ad and any biology/chemistry/medicine analysis question."
when_to_use: "Activate when the user provides data files to analyze, asks about differential expression, runs statistical tests on clinical data, performs variant analysis, does pathway enrichment, builds phylogenetic trees, or asks any scientific research question."
paths: "*.csv,*.xlsx,*.tsv,*.vcf,*.fa,*.fasta,*.faa,*.h5ad,*.rds,*.bam"
---

# ToolUniverse Router

## FIRST ACTION: Route to a Specialized Skill

**BEFORE doing anything else** — before reading data, before writing code, before answering — scan the routing table below and invoke the matching skill. The specialized skill contains critical domain conventions that you will get wrong without loading.

**How to route:**
1. Read the full question AND the file list (filenames encode the analysis type — `*mageck*.xlsx` → CRISPR screen, `*DM.csv`/`*AE.csv` → clinical trial AE, `*.vcf` → variant, `*.h5ad` → single-cell, `*_counts.csv`+`*meta*.csv` → RNA-seq DE, `*.faa`+`*.treefile` → phylogenetics, `*_executed.ipynb` → authoritative analysis already ran)
2. Find the matching keyword row in the Routing Table
3. Call `Skill(skill="<skill-name>")` immediately
4. Follow the loaded skill's instructions to answer the question

**If no keyword matches but filenames indicate a domain** → still route based on filename signals. Filenames are authoritative domain evidence even when the question prose is generic.

**If no signal matches** → use general strategies below.

**DO NOT skip routing.** Even if you think you know the answer, the skill has conventions (e.g., which denominator to use, which R function, which column to read) that differ from defaults.

## Critical Analysis Conventions

### RULE ZERO: Use the authoritative pipeline if one ships with the data

Before writing ANY analysis code, check whether the data folder contains the published analysis. Two common forms:

1. **Executed notebook** (`*_executed.ipynb`, `*.ipynb`) — the analysis has already run with the exact package versions, filters, and thresholds behind the reference answers. Reimplementing with pydeseq2/scanpy/gseapy produces different numbers. Read the outputs directly:

   ```bash
   tu run read_executed_notebook '{"data_folder":"/path/to/data","search":"<keyword>"}'
   ```

   `search` can be comma-separated terms (e.g., `"upregulated,log2FoldChange"`) or a regex. The tool returns the matching cells' source + printed outputs so you can cite the published value instead of recomputing.

2. **Executable script** (`run_*.py`, `analysis.R`, `find_*.R`, `*.Rmd`) — execute and report:

   ```bash
   ls /path/to/data/folder
   cd /path/to/data && python3 run_*.py      # or Rscript analysis.R
   ```

   **Canonical vs scratch scripts**: when a folder has many `.R`/`.py` files, prefer ones with canonical names (`analysis.R`, `main.R`, `run.R`, `run_<question_topic>.R`) over scratch-named ones (`try_*.R`, `check_*.R`, `inspect_*.R`, `verify_*.R`, `*_v2.R`, `*2.R`, `*3.R`). Scratch-named scripts are usually leftovers from prior agent attempts that may not have converged on the published answer — treat their outputs as advisory, not authoritative.

Only write your own analysis code when no authoritative pipeline exists in the data folder. When one does exist, your job is to execute/read it and report — not to reimplement.

**RULE ZERO sub-rule — Cite-the-cell-output**: If the notebook has a cell whose output IS the answer to the question (e.g., `len(sigs) = 197`, `mean p-value: 0.0254`, `top hit: GENE_X`), copy that output value directly. Do NOT recompute with your own filters. The notebook may apply slightly-different filters than the question text describes (e.g., the question lists `padj<0.05, |LFC|>0.5, baseMean>10` but the notebook's filter line has `& (baseMean>=10)` commented out). The published answer is the notebook's output — even if the question's filter list slightly differs from what the notebook actually applied. The benchmark's GT comes from the notebook's actual computation, not from re-applying the question's literal filter list. Trust the notebook's published number when it directly answers the question.

### RULE ONE: Use the bundled skill scripts for recurring analysis patterns

Before writing your own analysis code, check these ready-made scrip

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/mims-harvard/tooluniverse
git -C tooluniverse checkout 43be0fac747b

Works in

1. 2026-10-28
   ✓SAFE B 89 / 100

   first audit · source 43be0fac747b

Questions about tooluniverse

• github.com/mims-harvard/tooluniverse/tree/main/skills/tooluniver — the audited source at commit 43be0fac747b and every finding aboveObserved · 28 Oct 2026

Spotted something wrong? Report a correction · Methodology