Tessl • The management layer for AI agent skills

SkillPublic

flowio

Reads, inspects, and writes Flow Cytometry Standard (FCS) 2.0, 3.0, and 3.1 files with FlowIO. Use for low-level FCS metadata and channel inspection, NumPy event extraction, multi-dataset files, table export, and FCS 3.1 creation; use FlowKit for compensation, cytometry transforms, gating, or FlowJo workspaces.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%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.

Excellent procedural content: executable, validated workflows covering read, multi-dataset, write, and inspection paths, with a clean one-level-deep reference bundle and a hard-earned catalog of FlowIO 1.4.0 gotchas. The only room for improvement is tightening a few verbose caution passages and the citation boilerplate.

Suggestions

Condense the write_fcs spill/spillover caution paragraphs into a short checklist, keeping the detector-name-vs-PnN matching rule and the validation requirement; the current four-paragraph treatment spends tokens on peripheral detail.

Trim the citation section's procedural prose (fetching, version handling) to the essential instruction and citation, or move the extended citation protocol into a reference file alongside sources.md.

Mention the ".fcs" file extension once in the quick-start examples' context (or in the frontmatter description) so users who name files by extension trigger the skill naturally.

Dimension	Reasoning	Score
Conciseness	The body is dense with FlowIO-specific semantics Claude cannot know (TEXT key "$"-stripping, PnR range masks, the read_multiple_data_sets handle-closing bug), with no generic concept explanations. Not 5: minor trims are possible — the multi-paragraph write_fcs/spill caution and the lengthy citation boilerplate could be tightened; not 3: there is no padding or over-explanation of known concepts.	4 / 5
Actionability	Everything is executable: uv install/version commands, validated quick starts for read, multi-dataset, and create paths, copy-paste inspector CLI invocations with flags, and round-trip assertions ("np.testing.assert_allclose"). Not 4: the code is complete and covers all common cases with built-in validation.	5 / 5
Workflow Clarity	The six-step Operating Workflow sequences inspect-before-load, explicit preprocessing semantics, strict-parsing, privacy, and "Validate writes by reopening them"; code embeds shape checks ("raise ValueError" on $TOT/$PAR mismatch) and round-trip verification, and the Non-Negotiable Checks section acts as a checklist. Not 4: explicit validation checkpoints and feedback loops are present for the destructive write/overwrite path.	5 / 5
Progressive Disclosure	The body is a genuine overview: "Read only the reference needed for the current task" followed by five one-level-deep, per-topic reference files (all verified to exist) and a bundled scripts/inspect_fcs.py, with reference files containing no nested references. Not 4: references are well-signaled with topic labels and content is appropriately split.	5 / 5
	Total	19 / 20 Passed

Description

92%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.

A model description: concrete, third-person, comprehensive capability list with an explicit "Use for…" trigger clause and clear routing that separates FlowIO from the FlowKit analysis package. The only weakness is a couple of missing natural trigger terms (notably the ".fcs" extension).

Dimension	Reasoning	Score
Specificity	Concrete actions cover the full read/inspect/write surface: "Reads, inspects, and writes Flow Cytometry Standard (FCS) 2.0, 3.0, and 3.1 files", "low-level FCS metadata and channel inspection, NumPy event extraction, multi-dataset files, table export, and FCS 3.1 creation" — comprehensive with no vague filler. Not 4: no meaningful coverage gaps remain.	5 / 5
Completeness	Explicitly answers both: what ("Reads, inspects, and writes… files with FlowIO" plus enumerated capabilities) and when ("Use for low-level FCS metadata and channel inspection, NumPy event extraction… FCS 3.1 creation"). Not 4: the when-clause is explicit and enumerated, and it adds negative routing ("use FlowKit for compensation…").	5 / 5
Trigger Term Quality	Strong natural vocabulary ("FCS files", "Flow Cytometry Standard", "gating", "compensation", "FlowJo workspaces", "FlowKit") including domain synonyms users would actually say. Not 5: the ".fcs" file extension and phrases like "flow cytometry data" are missing, matching anchor 4's "a few natural terms missing" rather than the file-extension-inclusive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (low-level FCS file I/O with FlowIO) with distinct triggers and an explicit boundary against the closest overlapping skill ("use FlowKit for compensation, cytometry transforms, gating, or FlowJo workspaces"). Not 4: the main overlap risk is actively disambiguated, leaving minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/flowio/SKILL.md
Revision: 5f2bc03

Reviewed: 26 days ago

Discovery Implementation Validation

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.

flowio

Table of Contents

Is this your skill?