agentmods.dev

pertpy

pertpy is a skill for Claude Code, Codex from CHENyiru3/AI-Skills-Collections. It costs 40 tokens per session (1,144 once invoked), scanned A, original, MIT.

A helper for analyzing single-cell perturbation data with pertpy, a Python toolkit for studying how experimental changes affect cells. It maps the research question and data structure to an appropriate pertpy workflow.

In plain words
What is it for?
Use it to assign guides, detect effective perturbations, test expression or composition, compare perturbations, rank responding cell types, predict responses, or annotate mechanisms. It also helps inspect the installed Python and pertpy versions and input modalities.
Why use it?
Perturbation analyses depend on correct controls, experimental units, sample labels, cell types, batches, and software versions. Misidentifying these can produce misleading comparisons or incompatible code.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the compbio plugin — 38 skills shipped together

not rated 2repo 3d ago A scan 40 tokens original MIT

Good fit Use it to assign guides, detect effective perturbations, test expression or composition, compare perturbations, rank responding cell types, predict responses, or annotate mechanisms. It also helps inspect the installed Python and pertpy versions and input modalities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chenyiru3/ai-skills-collections/pertpy
View source ↗ CHENyiru3/AI-Skills-Collections
Install

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.

Any agent
npx skills add CHENyiru3/AI-Skills-Collections --skill pertpy
Clone the repo
git clone --depth 1 https://github.com/CHENyiru3/AI-Skills-Collections

Made for: Claude Code, Codex.

Or install compbio, the plugin that ships this one along with the rest of its 38 skills.

Wrote 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.

agentmods badge for pertpy

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/pertpy/github.svg)](https://agentmods.dev/skills/chenyiru3/ai-skills-collections/pertpy)
Your own site
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/pertpy"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/pertpy/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.

agentmods 80×15 button for pertpy

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/pertpy"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/pertpy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,144 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.01144
Opus 5.5 $0.00016 $0.00458
Sonnet 5.5 $0.00008 $0.00229
Haiku 4.5 $0.00004 $0.00114

Measured yesterday against content hash c44c85fa3d98, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pertpy 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 yesterday.

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.

skills-market/compbio/single-cell/analysis/pertpy/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pertpy

Translate a perturbation-analysis question into the appropriate pertpy workflow, with explicit inputs, controls, experimental units, and interpretable outputs.

The references retain the original pertpy 1.4.0 source-review snapshot from 2026-10-08. Newer releases exist and stable documentation moves: inspect the project’s installed version before using version-sensitive calls. Sources and maintenance records the dated review and known mismatches; this collection import did not rerun the statistical workflows.

Start with the data and question

  1. Identify the requested outcome: assign guides, detect effective perturbations, test expression/composition, rank responding cell types, compare perturbations, predict responses, or annotate mechanisms. Preserve the user's chosen method and experimental design.
  2. Inspect the selected Python environment, pertpy version, AnnData/MuData modalities, matrix provenance, and relevant metadata. Read setup and data when installation, input preparation, or compatibility needs attention.
  3. Map actual columns to perturbation, exact control label, sample/replicate, cell type, and any batch, dose, or time covariates. A column named batch is not automatically a biological replicate. Check controls exist in each analysis stratum.
  4. Select the relevant reference below. Use existing project decisions; resolve genuinely missing scientific choices before fitting the dependent model. Continue inspection and implementation that does not depend on those choices.
  5. Run a small representative check before an expensive fit. Verify output locations, group sizes, skipped groups, and diagnostic warnings. Report the method, representation/layer, contrast direction, independent sample counts, seed where supported, package version, and output paths.

Choose the workflow

Question Pertpy entrypoint Read
Which guides are present in each cell? pt.pp.GuideAssignment Guides and efficacy
Which guide-bearing cells respond, or how strongly? pt.tl.Mixscape, pt.tl.Mixscale Guides and efficacy
Which genes change between conditions? pt.tl.PyDESeq2, EdgeR, simple DE tests Expression and abundance
Which neighborhoods or cell-type proportions change? pt.tl.Milo, Sccoda, Tasccoda Expression and abundance
Which cell types respond most strongly? pt.tl.Augur Distances and prioritization
How different are cell populations? pt.tl.Distance, DistanceTest Distances and prioritization
How do perturbations relate, combine, or vary with dose? PseudobulkSpace, CentroidSpace, DistanceSpace Spaces and prediction
Can a response be predicted or matched to controls? pt.tl.Scgen, Cinemaot Spaces and prediction
What mechanisms, gene sets, or multicellular programs are implicated? pt.md, pt.tl.Enrichment, Dialogue Annotation and programs

Read the full file on GitHub · 48 lines

Files

What ships with it

8 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.

Changes

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.

  1. yesterday First seen · 48 lines · 40 tokens per session scan A c44c85fa3d98

Subscribe to this mod's changes

pertpy is a skill published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 1,144 once invoked, about $0.0002 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 2026-11-13.

Data and AIScientific
Related

pertpy compared with skills from other repositories

pertpy next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pertpyCHENyiru3/AI-Skills-CollectionsSkill23d agoMITA40Claude Code, Codex
arboretoK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA55Claude Code, Codex
deepspot-mK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA70Claude Code
torchdrugK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA64Claude Code
pyhealthK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA84Claude Code, Codex
nemo-mbridge-perf-expert-parallel-overlapNVIDIA/skillsSkill4.0kyesterdayApache-2.0A56Claude Code
evo2aipoch/open-scienceSkill5.5ktodayApache-2.0A83Claude Code, Codex