scgpt SKILL.md skillA

scgpt from aipoch/open-science is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add aipoch/open-science/scgpt@git:20260907.1f786cf

Pins git:20260907.1f786cf in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
aipoch/open-science
Path
resources/skills/scgpt/SKILL.md
Versions recorded
3
Latest version
git:20260907.1f786cf, committed Sep 7, 2026
First version recorded
Jul 14, 2026
Size
5,961 bytes
Repository stars
5,279
License
Apache-2.0

Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use this skill when: (1) Producing cell embeddings from an AnnData for clustering/integration, (2) Zero-shot or fine-tuned cell-type annotation, (3) Gene-level representation for perturbation/GRN tasks. For probabilistic single-cell models (scVI etc.), use the scvi-tools library.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# scGPT — Single-Cell Foundation Model

## Prerequisites

| Requirement | Minimum | Recommended |
| ----------- | ------- | ----------- |
| Python      | 3.10+   | 3.11        |
| CUDA        | 12.1+   | 12.4+       |
| GPU VRAM    | 16 GB   | 24 GB+      |

## How to run

### Loading the vocabulary and checkpoint

scGPT checkpoints are **raw directories** (`args.json`, `best_model.pt`,
`vocab.json`) — not Hugging Face hub repos. Point at the directory, not an HF
repo id.

```python
from scgpt.tokenizer.gene_tokenizer import GeneVocab
gv = GeneVocab.from_file("/path/to/scgpt-human/vocab.json")
print(len(gv))   # 60697 for the released human checkpoint
```

### Embedding an AnnData

```python
import anndata as ad
from scgpt.tasks import embed_data

adata = ad.read_h5ad("dataset.h5ad")        # var must contain a gene-name column
emb = embed_data(
    adata,
    model_dir="/path/to/scgpt-human",
    gene_col="feature_name",
    use_fast_transformer=False,             # see Gotchas
)
# emb is an AnnData with .obsm["X_scGPT"]
```

## Output format

`embed_data` returns an `AnnData` whose `.obsm["X_scGPT"]` is the per-cell
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add aipoch/open-science/scgpt@sha256:a87b3b7f3990ca24

The line at the top of this page pins the label git:20260907.1f786cf, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_my2oniu4345glzo7.svg)](https://markdownregistry.com/a/art_my2oniu4345glzo7)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Jul 14, 2026 and Sep 7, 2026, about one every 28 days.

versioncommittedcommitsizeaudit
git:20260907.1f786cf latest2026-09-07 1f786cf 5,961 BA view · diff
git:20260811.e7618cb2026-08-11 e7618cb 5,980 BA view · diff
git:20260714.a2a32822026-07-14 a2a3282 5,347 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5961 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

aipoch/open-science · 5,279 stars · license Apache-2.0 · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_my2oniu4345glzo7
GET https://markdownregistry.com/api/v1/resolve?ref=aipoch/open-science/scgpt
GET https://markdownregistry.com/api/v1/blob/a87b3b7f3990ca24e087feb462201129711dc6684788ff7b789a2874bff95282

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from aipoch/open-science

AGENTS.md AGENTS.md file
aipoch/open-science · AGENTS.md
git:20261012.84123ea · audit A · 5,279 stars
alphafold2 SKILL.md skill
aipoch/open-science · resources/skills/alphafold2/SKILL.md · Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022…
git:20260814.c9a70d8 · audit A · 5,279 stars
boltz SKILL.md skill
aipoch/open-science · resources/skills/boltz/SKILL.md · Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al…
git:20260814.c9a70d8 · audit A · 5,279 stars
borzoi SKILL.md skill
aipoch/open-science · resources/skills/borzoi/SKILL.md · Predict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi. Use this skill when…
git:20260907.1f786cf · audit A · 5,279 stars
chai1 SKILL.md skill
aipoch/open-science · resources/skills/chai1/SKILL.md · Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai…
git:20260814.c9a70d8 · audit A · 5,279 stars
compute-env-setup SKILL.md skill
aipoch/open-science · resources/skills/compute-env-setup/SKILL.md · Prepare reproducible setup instructions and validate a user-managed named software environment on an Open-Science SSH…
git:20260917.4395768 · audit A · 5,279 stars
customize SKILL.md skill
aipoch/open-science · resources/skills/customize/SKILL.md · Use when the user wants to create or manage a Specialist agent or create, revise, publish, or delete a Skill through…
git:20260821.3c0aa12 · audit A · 5,279 stars
diffdock SKILL.md skill
aipoch/open-science · resources/skills/diffdock/SKILL.md · Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) — blind…
git:20260814.c9a70d8 · audit A · 5,279 stars
env-management SKILL.md skill
aipoch/open-science · resources/skills/env-management/SKILL.md · Use when a notebook run fails on a missing package (ImportError, ModuleNotFoundError, "there is no package called")…
git:20260824.727a607 · audit B · 5,279 stars
esmfold2 SKILL.md skill
aipoch/open-science · resources/skills/esmfold2/SKILL.md · Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and…
git:20260814.c9a70d8 · audit A · 5,279 stars
evo2 SKILL.md skill
aipoch/open-science · resources/skills/evo2/SKILL.md · Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1)…
git:20260907.1f786cf · audit A · 5,279 stars
fair-esm2 SKILL.md skill
aipoch/open-science · resources/skills/fair-esm2/SKILL.md · Embed proteins with Meta AI's ESM-2 (`fair-esm` package). Use this skill when: (1) Extracting per-residue or…
git:20260915.c156910 · audit A · 5,279 stars

Every file in aipoch/open-science

Other files named scgpt

scgpt SKILL.md skill
pengqianhan/ai-human-research-os · research-skills-hub/claude-science-skills/skills/scgpt/SKILL.md · Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use this skill…
git:20260715.38d79be · audit A · 3 stars

Browse by kind, by grade A, or by owner.