CC tooluniverse-single-cell
Production-ready single-cell and expression matrix analysis using scanpy, anndata, and scipy. Performs scRNA-seq QC, normalization, PCA, UMAP, Leiden/Louvain clustering, differential expression (Wilcoxon, t-test, DESeq2), cell type annotation, per-cell-type statistical analysis, gene-expression correlation, batch correction (Harmony), trajectory inference, and cell-cell communication analysis. NEW: Analyzes ligand-receptor interactions between cell types using OmniPath (CellPhoneDB, CellChatDB), scores communication strength, identifies signaling cascades, and handles multi-subunit receptor complexes. Integrates with ToolUniverse gene annotation tools (HPA, Ensembl, MyGene, UniProt) and enrichment tools (gseapy, PANTHER, STRING). Supports h5ad, 10X, CSV/TSV count matrices, and pre-annotated datasets. Use when analyzing single-cell RNA-seq data, studying cell-cell interactions, performing cell type differential expression, computing gene-expression correlations by cell type, analyzing tumor-immune communication, or answering questions about scRNA-seq datasets.
Production-ready single-cell and expression matrix analysis using scanpy, anndata, and scipy.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1075 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5591 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Execution cost. Instruction body is 5591 tokens
- 85Steps. 56 steps, 2 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 18 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1075: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 34 headings
- +3Step-by-step instructions: 56 items
- +4Has examples (21 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.