Sc Pathway Scoring

What it does

When your agent uses it

• Tasks that involve Bioinformatics

Example prompts

• “/sc-pathway-scoring”

Requirements

• Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Load AnnData (--input) or build a demo.
2. 2Load gene sets: parse --gene-sets GMT, OR fetch via --gene-set-db and write a resolved GMT.
3. 3Validate: at least one gene-set member overlaps the input features (feature_label_source chosen from var_names / var["gene_symbol"] / etc.).
4. 4Run preflight; resolve --groupby (auto-pick from leiden / louvain / cell_type if unset).
5. 5Dispatch to method
6. 6Compute group-aware aggregates if --groupby is set.
7. 7Save tables, figures, processed.h5ad, report.md, result.json.

What it can do on your machine

Read from SKILL.md and the folder at commit 90a3bec. 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

  Ships script files (Python and R), which the agent can run.

  Shell commands in SKILL.md call:

  • python

  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

Sc Pathway Scoring loads about 2.2k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 77 tokens; SKILL.md has 759 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~77

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.2k

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

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 TianGzlab/OmicsClaw at commit 90a3bec, republished under its Apache-2.0 licence (© TianGzlab). 759 words, ~2,226 tokens.

name

sc-pathway-scoring

description

Load when computing per-cell pathway / gene-set scores on a normalised scRNA AnnData via AUCell (R or Python) or Scanpy score_genes. Skip when running condition-vs-control bulk-style enrichment on top of a DE table (use sc-enrichment); de-novo gene-program discovery (use sc-gene-programs).

trigger

pathway score, pathway scoring, gene set score, module score, pathway activity, signature score

tags

singlecell, scrna, pathway-scoring, aucell, scanpy-score-genes, gene-sets, decoupler

# Score PBMC lineage gene sets with the Python AUCell implementation.
# Reads pbmc3k_processed and uses its log-normalized raw snapshot.
# Calls sc-pathway-scoring: score_gene_sets, group_scores, score_distribution_figure.

from skills._sdk.notebook import load_demo, load_skill, write_output

pathways = load_skill('sc-pathway-scoring')
adata = load_demo('pbmc3k_processed').raw.to_adata()
gene_sets = {
    'B_cell': ['MS4A1', 'CD79A', 'CD79B', 'CD74', 'HLA-DRA'],
    'T_cell': ['CD3D', 'CD3E', 'CD3G', 'TRAC', 'IL7R'],
    'Myeloid': ['LYZ', 'S100A8', 'S100A9', 'FCN1', 'CTSS'],
}

scores = pathways.score_gene_sets(adata, gene_sets, method='aucell_py')
write_output(scores, 'tables/pathway_scores.csv')
write_output(pathways.group_scores(adata, scores, groupby='louvain'), 'tables/group_scores.csv')
write_output(pathways.score_distribution_figure(scores), 'figures/score_distribution.png')

assert scores.index.equals(adata.obs_names)
assert set(scores.columns) == set(gene_sets)
assert scores.max().max() > 0
assert scores.min().min() >= 0

# Demo (built-in gene sets)
python skills/singlecell/scrna/sc-pathway-scoring/sc_pathway_scoring.py --demo --output /tmp/sc_pw_demo

# AUCell-R with MSigDB Hallmark, grouped by cell type
python skills/singlecell/scrna/sc-pathway-scoring/sc_pathway_scoring.py \
  --input clustered.h5ad --output results/ \
  --gene-set-db hallmark --groupby cell_type

# AUCell-Python (no R needed) with custom GMT
python skills/singlecell/scrna/sc-pathway-scoring/sc_pathway_scoring.py \
  --input clustered.h5ad --output results/ \
  --method aucell_py --gene-sets pathways.gmt --groupby leiden

# Scanpy score_genes for fast prototyping
python skills/singlecell/scrna/sc-pathway-scoring/sc_pathway_scoring.py \
  --input clustered.h5ad --output results/ \
  --method score_genes_py --gene-sets pathways.gmt

<!-- api:begin generated from _api.py; regenerate with run.py api <skill dir> --write -->

<!-- api:end -->

© TianGzlab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (references) in skills/singlecell/scrna/sc-pathway-scoring of TianGzlab/OmicsClaw.

• SKILL.md
• _api.py
• examples/example_step.py
• references/methodology.md
• references/output_contract.md
• references/parameters.md
• references/r_visualization.md
• rscripts/sc_aucell.R
• sc_pathway_scoring.py
• tests/test_pathway_api.py
• tests/test_sc_pathway_scoring.py
• tests/test_sc_pathway_scoring_methods.py

Open the folder on GitHubat commit 90a3bec