CtrlK
BlogDocsLog inGet started
Tessl Logo

flowio

Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.

75

2.27x
Quality

66%

Does it follow best practices?

Impact

91%

2.27x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/flowio/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

82%

42%

FCS File Catalog Tool for Multi-Experiment Archive

Memory-efficient metadata extraction

Criteria
Without context
With context

uv install command

100%

0%

only_text parameter used

100%

100%

pnn_labels access

0%

100%

pns_labels access

0%

100%

event_count and channel_count

0%

100%

Standard metadata keywords

100%

100%

scatter_indices access

0%

100%

fluoro_indices access

0%

100%

time_index access

0%

100%

Error handling present

0%

0%

FlowKit recommendation

100%

100%

100%

77%

Flow Cytometry Data Normalization and Export Pipeline

FCS file creation and data modification

Criteria
Without context
With context

create_fcs import and use

0%

100%

opt_channel_names parameter

0%

100%

metadata dict passed to create_fcs

25%

100%

preprocess=False for modification

0%

100%

Extract-modify-recreate pattern

50%

100%

Original metadata preserved

30%

100%

pns_labels preserved

0%

100%

pnn_labels as channel names

0%

100%

FCS 3.1 float output acknowledged

50%

100%

uv install used

0%

100%

Output file produced

100%

100%

92%

33%

Robust FCS Ingestion Service for Heterogeneous File Sources

Error handling and multi-dataset support

Criteria
Without context
With context

FCSParsingError import

100%

100%

DataOffsetDiscrepancyError import

100%

100%

MultipleDataSetsError import

0%

100%

ignore_offset_discrepancy recovery

50%

100%

FCSParsingError recovery

50%

100%

read_multiple_data_sets used

83%

100%

nextdata_offset mechanism

50%

100%

Distinct except blocks

0%

100%

Result output produced

100%

100%

uv install used

0%

0%

read_multiple_data_sets iterates all datasets

100%

100%

Repository
K-Dense-AI/claude-scientific-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.