Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

CellAgent · majiayu000 | DecimalAI

scienceby majiayu000

CellAgent

majiayu000/cellagent

Source majiayu000/claude-skill-registry ↗License MIT

description: LLM-driven multi-agent framework for automated single-cell analysis.

SkillScore77Maintained

Automatic

Research pack

Last verified 8/19/2026

What it changes

Passed 13 of 17 test cases with the skill, and 2 of 17 without it.

Without skill14%

With skill77%

Checks it passed that the model alone missed

The command passes a goal option.
The execution command includes a goal argument.
The command uses `python3 Skills/Genomics/Single_Cell/CellAgent/repo/main.py`.

and 13 more in the full report

15 fixed2 passed either way4 still failing1 broke

Pass-rate lift: +64 pp
Tokens: -36%
Agent turns: 0%
Response time: -67%

Model gemini-3.6-flashMeasured 8/19/2026v117 of 22 cases passed with skill · 17 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/majiayu000-cellagent/SKILL.md https://app.decimal.ai/s/majiayu000-cellagent/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-cellagent, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/majiayu000-cellagent/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-cellagent

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-cellagent/SKILL.md https://app.decimal.ai/s/majiayu000-cellagent/SKILL.md

Raw file: /s/majiayu000-cellagent/SKILL.md ↗ · machine-readable summary at /s/majiayu000-cellagent.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 15

Prompt

We acquired cardiac single-nucleus data stored at `/datasets/cardiac_snrna.h5ad`. Instead of using an interactive Jupyter notebook with Scanpy, we want to launch the automated multi-agent single-cell pipeline. Show the exact CLI command.

What was checked, without and with the skill
Checked	Without skill	With skill
The CLI command targets `python3 Skills/Genomics/Single_Cell/CellAgent/repo/main.py`.	Missed	Passed
The command includes the file path `/datasets/cardiac_snrna.h5ad`.	Passed	Passed

case-08 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md56 linessingle file

---name: cell_agent description: LLM-driven multi-agent framework for automated single-cell analysis. keywords:

scRNA-seq
scanpy
annotation
autonomous
bioinformatics measurable_outcome: Achieves >85% accuracy in cell type annotation compared to manual curation on standard benchmarks. license: MIT metadata: author: Artificial Intelligence Group version: "1.0.0" compatibility:
system: Python 3.9+ allowed-tools:
run_shell_command
read_file ---"

CellAgent

CellAgent is a multi-agent system capable of autonomously handling the entire single-cell RNA-seq (scRNA-seq) analysis pipeline. It simulates a team of biological experts to process data, annotate cells, and perform downstream analysis.

When to Use This Skill

Automated Annotation: When you have raw scRNA-seq data and need cell type labels without manual curation.
Complex Workflows: For multi-step analysis (QC -> Clustering -> Annotation -> DE Analysis).
Data Integration: When merging multiple datasets (e.g., from different batches).

Core Capabilities

Planning: Decomposes analysis goals into executable steps.
Tool Execution: Generates and runs Python code for Scanpy/Seurat.
Self-Correction: detects errors in execution and attempts to fix them.

Workflow

Input: User query + scRNA-seq data (H5AD).
Planner: The Planning Agent breaks the task into sub-tasks.

Track record

Benchmark

13 / 17

test cases passed, vs 2 / 17 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

majiayu000 / claude-skill-registry

skills/agent/cellagent/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

cellagent-annotationCell taggerClose match+27 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

CellAgent

When to Use This Skill

Core Capabilities

Workflow

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills