Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mims-harvard/tooluniverse
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 re
2 of 24 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 2 comparable cases; this report requires 8.
This benchmark measured an earlier version of the skill.
A test case the skill fixed. Same model, same prompt, with and without the skill.
In `/data/analysis_dir/`, there are two R scripts: `inspect_check_v2.R` and `analysis.R`. Which script should be executed to obtain the primary published analysis result?
| Checked | Without skill | With skill |
|---|---|---|
| Selects the canonical script analysis.R rather than inspect_check_v2.R. | Missed | Passed |
The instructions your model reads when the skill loads.
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:
*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)Skill(skill="<skill-name>") immediatelyIf 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.
Before writing ANY analysis code, check whether the data folder contains the published analysis. Two common forms:
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:
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.
Executable script (run_*.py, analysis.R, find_*.R, *.Rmd) — execute and report:
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.
test cases passed with the skill
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.