Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TianGzlab/OmicsClaw --skill sc-batch-integrationgit clone --depth 1 https://github.com/TianGzlab/OmicsClawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-batch-integration)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-batch-integration"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-batch-integration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-batch-integration"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-batch-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 3 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.02113 |
| Opus 5.5 | $0.00028 | $0.00845 |
| Sonnet 5.5 | $0.00014 | $0.00423 |
| Haiku 4.5 | $0.00007 | $0.00211 |
Grade A, and why
sc-batch-integration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sc-batch-integration
When to use
Correct batch effects in merged, normalised scRNA data. The nine methods are Harmony (default), scVI, scANVI, BBKNN, Scanorama, SIMBA, fastMNN, Seurat CCA and Seurat RPCA. Check batch/condition confounding before correction: a batch fully confounded with the biological contrast cannot be separated statistically.
Steps
Start a notebook step with python skills/_sdk/notebook/run.py new integration.
Inside it, use integration = load_skill("sc-batch-integration"), then
adata = integration.integrate(adata, method="harmony", batch_key="batch").
This returns the corrected representation; choose neighbours, UMAP and
clustering separately with sc-clustering. After BBKNN, call
load_skill("sc-clustering").cluster(adata, use_existing_graph=True) to keep
the corrected graph. The default clustering call rebuilds it and loses BBKNN's
batch correction.
The CLI additionally builds neighbours/UMAP and writes the legacy report.
See examples/example_step.py for a runnable PBMC example.
Inputs & Outputs
Input is AnnData with a batch column and normalised X. Keep counts in
layers['counts'] for scVI/scANVI and R integration. Existing PCA is optional.
The API returns AnnData and separate table/Figure helpers; it writes no output
directory. R methods retain the existing H5AD bridge and need zellkonverter.
CLI outputs are processed.h5ad, report.md, result.json and
reproducibility/{commands.sh,requirements.txt}. Non-empty tables are written
to tables/{integration_summary,batch_sizes,cluster_sizes,batch_mixing_matrix,integration_metrics}.csv.
Label-dependent tables and plots are optional. Plot data, including UMAP
coordinates, live under figure_data/, not tables/umap.csv.
See references/output_contract.md for the conditional inventory.
Gotchas
result.json.data.requested_method,executed_method,fallback_usedandfallback_reasonrecord scANVI's fallback to scVI when labels are absent. Supply--labels-keyto choose an existing label column.tables/integration_metrics.csvomits unavailable LISI/ASW values; this is not evidence of good or bad integration. Label-free input has no label ASW._api.py:303:run_info(adata)contains a small JSON summary. The retained Seurat bridge also returns old R UMAP coordinates under the privateuns['_omicsclaw_legacy_integration_umap']key. The CLI moves these toobsm['X_umap']and removes the private key; the API adds no UMAP to obsm._api.py:39:obsm['X_harmony']uses existing PCA only when the requested PCA size would exceed the data's rank. Normal-sized input still recomputes PCA._api.py:182: SIMBA uses a temporary working directory; do not run it concurrently in threads. Its returned AnnData can be a cell-subset copy.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _api.py 19 KB runs code
- examples/example_step.py 1.0 KB runs code
- references/methodology.md 4.1 KB
- references/output_contract.md 1.2 KB
- references/parameters.md 3.5 KB
- references/r_visualization.md 855 B
- sc_integrate.py 30 KB runs code
- tests/__init__.py 0 B runs code
- tests/test_integration_api.py 6.2 KB runs code
- tests/test_sc_integrate_methods.py 616 B runs code
- tests/test_sc_integrate.py 3.0 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 17d ago Changed · +27 lines c4f27b1d9240
- 1mo ago First seen · 134 lines · 70 tokens per session scan A 3579f3aa8f82
sc-batch-integration is a skill published in the GitHub repository TianGzlab/OmicsClaw (161 stars, last pushed 17d ago), licensed Apache-2.0. It adds 70 tokens to every session and 2,113 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
spatial-integration
Multi-sample integration and batch correction for spatial transcriptomics data.
spatial-multi-sample-integration
Multi-sample spatial transcriptomics integration and batch correction with automatic method selection (STAligner, Harmony, BBKNN, Scanorama) and robust fallback.
Virtual Embryo — atlas data + knowledge graph
Query the Virtual Embryo knowledge graph (mouse/human developmental biology: genes, anatomy, Theiler/Carnegie stages, gene expression, diseases, papers) and its 3D atlas catalog (anatomical OPT/light-sheet volumes + 3D spatial- transcriptomics datasets), and visualise those datasets in 3D with the volume3d / spatial3d…
batch_integration_advisor
Recommend a batch-integration strategy and explain the tradeoffs for preserving biology versus removing technical effects.
onekgpd
Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which…
neuropixels-analysis
Analyzes Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when…