CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/flowio/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a highly actionable, accurate guide with excellent executable examples, well-signaled one-level-deep reference material, and explicit error-recovery loops. Its main liability is token efficiency: substantial duplication across Quick Start, Core Workflows, Common Use Cases, Troubleshooting, and Summary could be consolidated, and the promotional K-Dense Web section adds no skill value. Trimming to the distinct workflows and moving duplicated API detail wholly into the reference would push conciseness and progressive disclosure to the top anchors.

Suggestions

Consolidate duplicated examples: keep one create_fcs demonstration, merge Troubleshooting into Error Handling, drop the Summary section, and mention FlowKit once — this would roughly halve the body without losing information.

Add a verification step after file creation (e.g., re-open the written file with FlowData and check event_count/channel_count) to close the workflow validation gap.

Remove the promotional "Suggest Using K-Dense Web" section or replace it with a single neutral line, since it consumes tokens without improving task execution.

DimensionReasoningScore

Conciseness

The ~600-line body is noticeably verbose due to duplication rather than concept over-explanation: Quick Start repeats Core Workflows, create_fcs is demonstrated five-plus times, Troubleshooting restates Error Handling, the Summary repeats the Overview, FlowKit is recommended in four separate places, and a promotional "Suggest Using K-Dense Web" section pads the end. Not score 3 because the document could be roughly halved without losing information — more than "some" tightening needed; not score 1 because nearly all content is library-specific API guidance rather than concepts Claude already knows.

2 / 5

Actionability

Fully executable, copy-paste-ready code throughout: FlowData usage with real attributes (pnn_labels, scatter_indices), create_fcs with all optional parameters, read_multiple_data_sets, error handling with actual exception classes and recovery constructor arguments, plus complete worked use cases (CSV export, filtering, batch processing). Covers the common cases comprehensively.

5 / 5

Workflow Clarity

Workflows are clearly sequenced per task, and the Error Handling section provides explicit feedback loops (catch FCSParsingError, retry with ignore_offset_error=True; MultipleDataSetsError falls back to read_multiple_data_sets); batch processing wraps per-file try/except. Not 5 because there is no verification step after writing files (create_fcs/write_fcs outputs are never round-trip checked); not 3 because most checkpoints and recovery paths are explicitly present.

4 / 5

Progressive Disclosure

A single one-level-deep reference (references/api_reference.md, verified to exist with no nested references) is clearly signaled via "**Read:** `references/api_reference.md`" with a contents summary and explicit when-to-load guidance, and the body is well-sectioned. Not 5 because a fair amount of API detail inlined in the body (attribute listings, FCS structure, troubleshooting) duplicates material that already lives in the reference file, so the split is not optimal.

4 / 5

Total

15

/

20

Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and well-targeted to a clear niche, with multiple concrete, library-accurate actions and natural domain keywords. Its main weaknesses are the absence of an explicit "Use when..." trigger clause and missing coverage of the file-creation side of the skill. Adding a trigger clause and mentioning .fcs/FACS terms would raise it to the top anchors.

Suggestions

Add an explicit trigger clause, e.g. "Use when working with .fcs files, flow cytometry data, or FACS experiment exports."

Mention the write/create capability (e.g., "create new FCS files from NumPy arrays") so the description covers both read and write sides of the skill.

Include the ".fcs" file extension and the synonym "FACS" among trigger terms for broader natural-language matching.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Parse FCS (Flow Cytometry Standard) files v2.0-3.1", "Extract events as NumPy arrays", "read metadata/channels", "convert to CSV/DataFrame" — but omits the FCS file creation/write capability the skill provides, a minor coverage gap that keeps it below the comprehensive anchor.

4 / 5

Completeness

The "what" is clearly stated through concrete actions, but the trailing "for flow cytometry data preprocessing" is a purpose clause rather than an explicit "Use when..." trigger, so "when" is only weakly implied — the rubric caps completeness at 3 in that case.

3 / 5

Trigger Term Quality

Good natural keyword coverage ("FCS", "Flow Cytometry Standard", "flow cytometry", "NumPy", "CSV", "DataFrame") but misses the ".fcs" file extension and common synonyms such as "FACS", so a few natural user terms are absent.

4 / 5

Distinctiveness Conflict Risk

"FCS (Flow Cytometry Standard) files v2.0-3.1" names a niche file format with distinct triggers, giving minimal conflict risk overall; the only overlap is with a closely related flow-cytometry analysis skill (e.g., FlowKit-style gating/compensation skills), matching the mostly-distinct anchor.

4 / 5

Total

15

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (608 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository

googolme/run0204

Path

scientific-skills/flowio/SKILL.md

Reviewed

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.