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 dralkh/iktinah --skill scanpygit clone --depth 1 https://github.com/dralkh/iktinahWrote 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/dralkh/iktinah/scanpy)<a href="https://agentmods.dev/skills/dralkh/iktinah/scanpy"><img src="https://agentmods.dev/badge/skills/dralkh/iktinah/scanpy/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/dralkh/iktinah/scanpy"><img src="https://agentmods.dev/badge/skills/dralkh/iktinah/scanpy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00093 | $0.05421 |
| Opus 5 | $0.00046 | $0.02710 |
| Sonnet 5 | $0.00019 | $0.01084 |
| Haiku 4.5 | $0.00009 | $0.00542 |
Grade A, and why
scanpy 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 8d 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.
This is a copy
86% identical to scanpy — 259 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scanpy: Single-Cell Analysis
Overview
Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis. Current stable release: scanpy 1.12.x (January 2026).
Installation
Requires Python 3.12+ (scanpy 1.12 dropped Python ≤3.11) and anndata ≥0.10.
uv pip install "scanpy[leiden]"
The [leiden] extra installs python-igraph and leidenalg, required for Leiden clustering. For reproducible environments, pin a version: uv pip install "scanpy[leiden]==1.12.1".
For large or out-of-core datasets, many functions support Dask arrays (experimental):
uv pip install "scanpy[leiden]" dask
See the Using dask with Scanpy tutorial. For GPU-accelerated scanpy-like operations, use rapids-singlecell as a separate package.
If the input is an R-native single-cell object (.rds, .RData, Seurat, or SingleCellExperiment), first convert it to .h5ad with R tooling, then load it with Scanpy. Read references/r_interop.md for agent-run installation and conversion instructions across macOS, Linux, and Windows.
For AnnData structure and I/O details, use the anndata skill. For probabilistic models and batch correction, use scvi-tools.
When to Use This Skill
This skill should be used when:
- Analyzing single-cell RNA-seq data (.h5ad, 10X, CSV formats)
- Working with R-friendly single-cell datasets (
.rds,.RData, Seurat, SingleCellExperiment) that need conversion to.h5ad - Performing quality control on scRNA-seq datasets
- Creating UMAP, t-SNE, or PCA visualizations
- Identifying cell clusters and finding marker genes
- Annotating cell types based on gene expression
- Conducting trajectory inference or pseudotime analysis
- Generating publication-quality single-cell plots
What ships with it
23 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.
- assets/analysis_template.py 9.6 KB runs code
- assets/celltype_mapping.json 184 B
- assets/gene_signatures.json 355 B
- assets/pipeline_config.json 380 B
- references/api_reference.md 8.2 KB
- references/plotting_guide.md 9.9 KB
- references/r_interop.md 11 KB
- references/standard_workflow.md 6.0 KB
- scripts/_common.py 4.0 KB runs code
- scripts/annotate.py 3.5 KB runs code
- scripts/batch_correct.py 2.7 KB runs code
- scripts/cluster.py 2.5 KB runs code
- scripts/convert.py 1.5 KB runs code
- scripts/find_markers.py 3.4 KB runs code
- scripts/inspect_data.py 2.8 KB runs code
- scripts/plot.py 3.5 KB runs code
- scripts/preprocess.py 3.7 KB runs code
- scripts/pseudobulk.py 2.9 KB runs code
- scripts/qc_analysis.py 4.5 KB runs code
- scripts/reduce_dimensions.py 2.6 KB runs code
- scripts/run_pipeline.py 7.9 KB runs code
- scripts/score_genes.py 3.7 KB runs code
- scripts/subset.py 2.5 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.
- 8d ago First seen · 512 lines · 93 tokens per session scan A dd17164b3bc6
scanpy is a skill published in the GitHub repository dralkh/iktinah (77 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 5,421 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to scanpy, differing in 259 lines, and is treated as a copy.
Other skills, from other repositories
sci-extract
Read an academic paper end to end and extract professional research insights, figures, metadata, and critique. Use this skill whenever the user shares a scientific paper, review paper, survey paper, systematic review, meta-analysis, scoping review, arXiv link, DOI, PDF, or pasted paper text and asks to read…
sci-polish
Two-stage academic paper polishing skill. Stage A reduces AI detection traces (targeting GPTZero, Turnitin, Originality.ai). Stage B performs 8-dimension quality improvement (grammar, tone, coherence, conciseness, terminology, structure, argument clarity, journal compliance). Use whenever the user asks to polish…
sci-ppt
Generate professional academic PowerPoint (PPTX) presentations from paper PDFs, structured outlines, or plain text. Use for thesis defense, seminar reports, literature presentations, and graduate school applications. Supports automatic figure extraction, LaTeX formula rendering, and bilingual (Chinese/English) layouts.
econ-compass
Your compass for navigating economics literature. Find the most important, must-read papers in any economics field or research area — from broad subfields like labor economics or macroeconomics to narrow topics like 'carbon pricing' or 'digitalization and firm innovation'. This skill curates essential reading lists by…
kami-deck
A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.
html-ppt-zhangzara-monochrome
A grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review committee.