Scanpy Single-Cell Analysis
davila7/claude-code-templates
Walks through single-cell RNA-seq analysis with Scanpy: loading .h5ad and 10X data, QC, normalization, PCA and UMAP, Leiden clustering, marker genes and cell type annotation.
Load when computing per-cell QC metrics (ngenes, total counts, mt%, ribo%) on a single-cell AnnData before filtering.
Install Sc Qc
$ npx skills add TianGzlab/OmicsClaw --skill sc-qc -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install TianGzlab/OmicsClaw sc-qc --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/singlecell/scrna/sc-qc .claude/skills/sc-qc && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "sc-qc" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/singlecell/scrna/sc-qc into .claude/skills/sc-qc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sc-qc", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/TianGzlab/OmicsClaw/tree/main/skills/singlecell/scrna/sc-qcType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add TianGzlab/OmicsClaw --skill sc-qc -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install TianGzlab/OmicsClaw sc-qc --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/singlecell/scrna/sc-qc .agents/skills/sc-qc && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sc-qc" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/singlecell/scrna/sc-qc into .agents/skills/sc-qc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sc-qc", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TianGzlab/OmicsClaw --skill sc-qc -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install TianGzlab/OmicsClaw sc-qc --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/singlecell/scrna/sc-qc .cursor/skills/sc-qc && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "sc-qc" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/singlecell/scrna/sc-qc into .cursor/skills/sc-qc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sc-qc", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/TianGzlab/OmicsClaw.git --path skills/singlecell/scrna/sc-qc--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add TianGzlab/OmicsClaw --skill sc-qc -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install TianGzlab/OmicsClaw sc-qc --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/singlecell/scrna/sc-qc .gemini/skills/sc-qc && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "sc-qc" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/singlecell/scrna/sc-qc into .gemini/skills/sc-qc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sc-qc", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install TianGzlab/OmicsClaw sc-qcInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add TianGzlab/OmicsClaw --skill sc-qc -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/singlecell/scrna/sc-qc .github/skills/sc-qc && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "sc-qc" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/singlecell/scrna/sc-qc into .github/skills/sc-qc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sc-qc", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TianGzlab/OmicsClaw --skill sc-qc -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install TianGzlab/OmicsClaw sc-qc --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/singlecell/scrna/sc-qc .opencode/skills/sc-qc && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "sc-qc" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/singlecell/scrna/sc-qc into .opencode/skills/sc-qc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sc-qc", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
sc-qc- GitHub stars
- 161
- Token cost
- ~2k tokens
- SKILL.md length
- 892 words
- Files
- 9 (incl. references)
- Skills in repo
- 88
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Load when computing per-cell QC metrics (ngenes, total counts, mt%, ribo%) on a single-cell AnnData before filtering.
- Tasks that involve Bioinformatics
- SKILL.md covers When to use, Use from a step, API and Methods and parameters, plus 5 more sections
- Runs Python scripts from its folder; calls python
What it does
Sc Qc is an agent skill from TianGzlab/OmicsClaw. Load when computing per-cell QC metrics (ngenes, total counts, mt%, ribo%) on a single-cell AnnData before filtering. Skip when reads are still raw FASTQ (use sc-fastq-qc); you want to filter cells now (use sc-filter).
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including reference files (for example `_api.py`, `examples/example_step.py` and `references/methodology.md`).
It sits in Research & Science, covering Bioinformatics. It works with AnnData. The repository describes itself as: Conversational & memory-enabled AI research partner for multi-omics analysis. CLI + Desktop App (installers in Releases). From biological idea to full research paper. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Bioinformatics
Example prompts
- “/sc-qc”
Requirements
- Python 3
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), 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 Qc loads about 2k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 56 tokens; SKILL.md has 892 words of instructions outside code blocks.
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
Auto-check passed
The automated check found no risky patterns in SKILL.md.
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). 892 words, ~1,981 tokens.
Download SKILL.mdSave it as
.claude/skills/sc-qc/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- sc-qc
- description
- Load when computing per-cell QC metrics (n_genes, total counts, mt%, ribo%) on a single-cell AnnData before filtering. Skip when reads are still raw FASTQ (use sc-fastq-qc); you want to filter cells now (use sc-filter).
- trigger
- scRNA QC, single-cell QC, quality control, mitochondrial percentage, ribosomal percentage, QC violin, QC scatter, n genes per cell
- tags
- singlecell, scrna, qc, mitochondrial, ribosomal
sc-qc
When to use
The user has a single-cell AnnData (post-counting / post-standardisation)
and wants to review cell quality — counts, detected genes, mitochondrial
percentage, ribosomal percentage — before any filtering. This skill
reports, it does not remove cells. Use sc-filter to actually drop
cells based on these metrics.
Use from a step
qc = load_skill("sc-qc")
adata = qc.calculate_qc(read_input("data/pbmc.h5ad"), species="human")
write_output(qc.qc_summary(adata), "tables/qc_metrics_summary.csv")
write_output(qc.qc_figure(adata), "figures/qc_histograms.png")
write_output(adata, "intermediate/adata_qc.h5ad")A complete step that runs on demo data: examples/example_step.py.
API
<!-- api:begin generated from _api.py; regenerate with run.py api <skill dir> --write -->calculate_qc(adata, *, species: str='human', calculate_ribo: bool=True)
Bring the input into the OmicsClaw scRNA contract and add per-cell QC metrics to obs.
The count-like matrix becomes X and layers['counts'], raw keeps a
counts snapshot, and gene names are made unique. Then scanpy's
calculate_qc_metrics adds n_genes_by_counts, total_counts,
pct_counts_mt and pct_counts_ribo (when the gene prefixes match), plus
log10_total_counts and log10_n_genes_by_counts; var gets mt and
ribo flags. How the input was read is recorded for :func:run_info.
:param species: "human" (MT-, RPS/RPL prefixes) or "mouse"
(mt-, Rps/Rpl). Default "human", the CLI default. Set it to the
organism of the data: with the wrong one no mitochondrial gene matches and
pct_counts_mt is not computed at all.
:param calculate_ribo: Also compute pct_counts_ribo. Default True, as the CLI does.
:returns: A new AnnData (the standardized copy), with the metrics in obs.
:raises ValueError: no count-like matrix can be found in X, layers or raw.
run_info(adata, *, keep: bool=True) -> dict
What :func:calculate_qc recorded about the input it prepared.
Keys: species, calculate_ribo, expression_source (the matrix used
as counts), gene_name_source, warnings, input_contract,
matrix_contract and qc_obs_columns.
:param keep: Leave the record in adata.uns; False removes it.
:returns: The record, or an empty dict when calculate_qc has not run on adata.
qc_summary(adata) -> pd.DataFrame
One row per QC metric with min, max, mean, median, std, q25 and q75.
:returns: Columns metric, min, max, mean, median, std, q25,
q75, for the metrics :func:calculate_qc added.
qc_metrics_table(adata) -> pd.DataFrame
The per-cell QC metrics, one row per cell.
:returns: Column cell_id followed by the QC metrics present in obs.
highest_expressed_genes(adata, *, n_top: int=20) -> pd.DataFrame
The genes with the highest mean expression in X.
A few genes dominating the counts (mitochondrial, ribosomal, MALAT1) point to stressed cells or ambient RNA.
:param n_top: How many genes to return. Default 20, the CLI's table length.
:returns: Columns gene and mean_expression, highest first.
barcode_rank_table(adata) -> pd.DataFrame
Library sizes ranked from largest to smallest, for a barcode-rank (knee) plot.
:returns: Columns rank, total_counts, log10_rank and log10_total_counts.
:raises KeyError: total_counts is not in obs; run :func:calculate_qc first.
qc_correlation_table(adata, *, metrics: list[str] | None=None) -> pd.DataFrame
Pearson correlations between QC metrics across cells.
:param metrics: The obs columns to correlate. Default: the QC metrics present.
:returns: A square table with a metric column naming each row.
qc_figure(adata, *, metrics: list[str] | None=None)
Histograms of the QC metrics, one panel per metric, with the median marked.
:param metrics: The obs columns to plot. Default: the QC metrics present.
:returns: A matplotlib Figure.
<!-- api:end -->Show full SKILL.md (436 more words)Show less
Methods and parameters
There is one method: scanpy's calculate_qc_metrics on the count matrix,
after the input is brought into the OmicsClaw scRNA contract (counts in X
and layers['counts'], a counts snapshot in raw, unique gene names).
| Parameter | Default | Where it comes from | When to change it |
|---|---|---|---|
species | "human" | the CLI default | Always set it to the organism of the data. It picks the gene prefixes: MT- and RPS/RPL for human, mt- and Rps/Rpl for mouse. Ask the user when the organism is not in the data description. |
calculate_ribo | True | the CLI's fixed behaviour | Leave it on; set False only when ribosomal content is irrelevant to the question. |
n_top of highest_expressed_genes | 20 | the CLI's table length | Raise it to look for more contaminating genes. |
QC thresholds are not chosen here. Read qc_summary and the figure, then
choose thresholds for sc-filter or sc-preprocessing with the user; the
usual starting points per tissue are in references/methodology.md.
Gotchas
- No filtering happens here.
calculate_qckeeps every cell and gene. Filtering issc-filter(or the thresholds ofsc-preprocessing). - A wrong
speciesloses the mitochondrial metric. With no gene matching the prefix,pct_counts_mtis not computed at all, andqc_summaryhas no row for it. Check that the row is there before reporting mitochondrial content. run_info(adata)["expression_source"]says which matrix was used as counts:layers.counts,adata.raworadata.X. QC fractions only mean something on a count-like source; report it when the input came from outside OmicsClaw.calculate_qcreturns a new object. Keep the return value (adata = qc.calculate_qc(adata)); the input AnnData is left as it was.- Non-count input raises
ValueError. A log-normalisedXwith nocountslayer or count-likerawcannot be QC'd; ask for the raw counts.
Inputs and outputs
calculate_qcreads the count-like matrix fromlayers['counts'],raworX, and gene names fromvar(a gene-symbol column when there is one). It writesobs:n_genes_by_counts,total_counts,pct_counts_mt,pct_counts_ribo,log10_total_counts,log10_n_genes_by_counts;var:mt,ribo;layers['counts'],raw, and the contract entries inuns.- The table functions read those
obscolumns and return DataFrames;qc_figurereturns a matplotlib Figure.
CLI
sc_qc.py runs the same functions outside a project and writes a report,
figures, tables and processed.h5ad: python <skill directory>/sc_qc.py --help.
--demo runs it on PBMC3K.
See also
references/parameters.md— every CLI flag and tuning hintreferences/methodology.md— mt/ribo gene-pattern detection, scanpy QC parameters, tissue thresholdsreferences/output_contract.md— the CLI's table column schemas and figure roles- Adjacent skills:
sc-standardize-input(upstream — required if input is external),sc-filter(next step — actually removes cells),sc-doublet-detection(parallel — finds doublets)
Dependencies
Python packages this skill's script needs. They are not installed for you — check before a long run.
anndata, matplotlib, numpy, pandas, scanpy, scipy, seaborn
© 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 8 other files (references) in skills/singlecell/scrna/sc-qc 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
- sc_qc.py
- tests/test_sc_qc.py
Open the folder on GitHubat commit 90a3bec
Compare with similar skills
Sc Qc next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Sc Qc this skillTianGzlab/OmicsClaw | 161 | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Scanpy Single-Cell Analysisdavila7/claude-code-templates | 32k | 15 repos | ~2.8k | Automated safety check: Pass | MIT | |
| ScgptJimLiu/science-skills | 227 | 4 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| PyDESeq2 Differential Expressiondavila7/claude-code-templates | 32k | 11 repos | ~4k | Automated safety check: Pass | MIT | |
| Anndatadavila7/claude-code-templates | 32k | 11 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Single-Cell Initial AnalysisLigphiDonk/Oh-my--paper | 738 | 1 repos | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
Scgpt
JimLiu/science-skills
Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology.
PyDESeq2 Differential Expression
davila7/claude-code-templates
Runs differential gene expression analysis on bulk RNA-seq counts with PyDESeq2: design formulas, Wald tests, FDR correction and volcano or MA plots.
Anndata
davila7/claude-code-templates
This skill should be used when working with annotated data matrices in Python, particularly for single-cell genomics analysis, managing experimental measurements with metadata, or handling…
Single-Cell Initial Analysis
LigphiDonk/Oh-my--paper
Runs a seven-step quality-control and exploration pipeline on scRNA-seq, CyTOF or flow cytometry data and writes a plain-language report of what it found.
Single Cell Data Prep Qc
harrisongzhang/TheVirtualBiotech
Single-cell RNA-seq data preparation and quality control pipeline.
More from TianGzlab/OmicsClaw
All 88 skills in this repoBulkrna Cosinor Rhythm
TianGzlab/OmicsClaw
Load when the user needs Deterministic fixed-period 24-hour single-component cosinor OLS rhythm analysis for a bulk RNA time-course CSV.
Bulkrna Batch Correction
TianGzlab/OmicsClaw
Load when correcting batch effects in bulk expression using R sva ComBat or the legacy Python parametric approximation.
Bulkrna Coexpression
TianGzlab/OmicsClaw
Load when discovering bulk gene co-expression modules and hub genes with R WGCNA.
Bulkrna De
TianGzlab/OmicsClaw
Load when comparing gene expression between two conditions in bulk RNA-seq count data.
Bulkrna Deconvolution
TianGzlab/OmicsClaw
Load when estimating cell-type proportions in bulk RNA-seq samples from a single-cell or signature-matrix reference.
Bulkrna Enrichment
TianGzlab/OmicsClaw
Load when running pathway / GO term enrichment on a bulk RNA-seq DE result list.
Related
Works with
Categories
Questions about Sc Qc
What does Sc Qc do?
Load when computing per-cell QC metrics (ngenes, total counts, mt%, ribo%) on a single-cell AnnData before filtering. Sc Qc is an agent skill from TianGzlab/OmicsClaw. Load when computing per-cell QC metrics (ngenes, total counts, mt%, ribo%) on a single-cell AnnData before filtering.
When should I use Sc Qc?
Sc Qc fits situations like: tasks that involve Bioinformatics.
How do I install Sc Qc in Claude Code?
Run `npx skills add TianGzlab/OmicsClaw --skill sc-qc -a claude-code`. Or copy the skill folder (skills/singlecell/scrna/sc-qc in TianGzlab/OmicsClaw) into .claude/skills/sc-qc in your project. Claude Code loads it when a task matches its description.
How do I install Sc Qc in Codex?
Run `npx skills add TianGzlab/OmicsClaw --skill sc-qc -a codex`. Or copy the skill folder (skills/singlecell/scrna/sc-qc in TianGzlab/OmicsClaw) into .agents/skills/sc-qc in your project. Codex loads it when a task matches its description.
Can I use Sc Qc in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TianGzlab/OmicsClaw --skill sc-qc -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sc-qc, .gemini/skills/sc-qc, .github/skills/sc-qc and .opencode/skills/sc-qc in your project.
What does Sc Qc need to run?
Going by SKILL.md and its folder, Sc Qc needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Sc Qc access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Sc Qc safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Sc Qc use?
Sc Qc is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Sc Qc use?
About 2k tokens (SKILL.md is roughly 7.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3k tokens, read only when the agent opens those files.
What are the alternatives to Sc Qc?
Skills that share tags, products or a category with Sc Qc: Scanpy Single-Cell Analysis (davila7/claude-code-templates, 32k stars), Scgpt (JimLiu/science-skills, 227 stars), PyDESeq2 Differential Expression (davila7/claude-code-templates, 32k stars) and Anndata (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Sc Qc?
TianGzlab (a GitHub organization) maintains it in TianGzlab/OmicsClaw, which has 161 GitHub stars. The repository holds 88 skills in this directory. The repository was last updated on October 7, 2026.
Source: TianGzlab/OmicsClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.