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
66%
Does it follow best practices?
Impact
91%
2.27xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/flowio/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, domain-specific description with excellent specificity and distinctiveness. It lists concrete actions and includes rich trigger terms relevant to flow cytometry workflows. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to read, parse, or analyze FCS flow cytometry files, or mentions .fcs files, FACS data, or flow cytometry preprocessing.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: parse FCS files, extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the domain context. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'FCS', 'Flow Cytometry Standard', 'flow cytometry', 'NumPy arrays', 'metadata', 'channels', 'CSV', 'DataFrame', and version numbers (v2.0-3.1). Good coverage of domain-specific terms a user working with flow cytometry data would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — FCS files and flow cytometry data are very specific domains unlikely to conflict with other skills. The mention of specific file format versions (v2.0-3.1) further narrows the scope. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent, executable code examples covering the full FlowIO API surface. However, it is far too verbose — it includes extensive use-case examples, background explanations, and sections that Claude doesn't need, consuming excessive tokens. The lack of validation steps in multi-step workflows and the monolithic structure further weaken it.
Suggestions
Cut the content by at least 50%: remove 'When to Use This Skill', 'Summary', FCS file structure explanation, 'Integration Notes', and most of 'Common Use Cases' — move detailed examples to a separate reference file.
Add explicit validation checkpoints to workflows involving file creation/modification (e.g., verify output FCS is readable after create_fcs calls).
Move 'Common Use Cases', 'Troubleshooting', and 'Advanced Topics' into separate bundle files and reference them from the main SKILL.md to improve progressive disclosure.
Remove explanatory prose that Claude already knows (e.g., 'FCS files contain rich metadata in the TEXT segment', 'FlowIO provides essential FCS file handling capabilities') — just show the code patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It explains concepts Claude already knows (FCS file structure, what segments are, what NumPy arrays are), includes redundant examples (CSV conversion, channel extraction, batch processing are straightforward compositions), and has unnecessary sections like 'When to Use This Skill', 'Integration Notes', and 'Summary' that add little value. The 'Advanced Topics' section explaining FCS file structure is pure background knowledge padding. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout. Every workflow includes concrete Python code with proper imports, realistic variable names, and complete function calls. The error handling section shows specific exception types and recovery patterns. | 3 / 3 |
Workflow Clarity | Multi-step workflows like 'Extract, Modify, and Recreate' are presented clearly with sequential code. However, there are no explicit validation checkpoints — for example, the batch processing workflow lacks verification that output files are valid FCS, and the filtering/re-export workflow doesn't validate the output file. For file manipulation operations, missing validation caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill references `references/api_reference.md` for detailed API docs, which is good progressive disclosure. However, the main file itself is monolithic with enormous amounts of content that should be split into separate reference files (e.g., common use cases, error handling patterns, advanced topics). Much inline content bloats the main skill unnecessarily. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (607 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
cbcae7b
- 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.