CtrlK
BlogDocsLog inGet started
Tessl Logo

upset-plot-converter

Convert complex Venn diagrams with more than 4 sets to clearer Upset.

48

Quality

60%

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/Data Analysis/upset-plot-converter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 core Usage, Input, and Output sections are genuinely useful and executable, but they are buried in a large amount of generic template boilerplate that adds no value. The workflow and file references are template-generated rather than tailored to the actual conversion task, with at least one dangling reference.

Suggestions

Remove the template boilerplate sections (Key Features, Dependencies, Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template) and keep only Usage, Input, Output, Quick Check, Workflow, and Error Handling.

Fix the broken references: create the referenced requirements.txt (or remove the reference), and correct the import path to match the flat scripts/main.py layout instead of "skills.upset_plot_converter.scripts.main".

Replace the generic Workflow steps with task-specific steps that include a validation checkpoint, e.g. verify the output PNG was written and that at least one intersection met min_subset_size before declaring success.

DimensionReasoningScore

Conciseness

The body is heavily padded with template boilerplate ("Scope-focused workflow aligned to:...", "`matplotlib`: `unspecified`", three "See `## ...` above for related details" fillers, Risk Assessment, Security Checklist, Lifecycle Status with "Next Review Date: 2026-03-06", Response Template) and the Notes section explains concepts Claude already knows ("When Venn diagrams exceed 4 sets, they become difficult to read"). It sits between 'severely verbose' and 'mostly efficient' but noticeably below the midpoint, since the Usage/Input/Output core is direct and complete.

2 / 5

Actionability

The Usage section gives complete, concrete Python examples for both input forms, and the referenced functions (convert_venn_to_upset, upset_from_lists) exist in scripts/main.py, with runnable commands ("python -m py_compile scripts/main.py"). Minor gaps keep it below 5: the import path "from skills.upset_plot_converter.scripts.main import ..." does not match the flat scripts/main.py bundle layout, and requirements.txt is referenced but does not exist.

4 / 5

Workflow Clarity

A 5-step Workflow with fallback checkpoints ("If execution fails or inputs are incomplete, switch to the fallback path") and a per-failure Error Handling section exist, but the steps are generic template text ("Confirm the user objective", "Return a structured result") with no task-specific validation such as verifying the output PNG was created or that intersections were non-empty.

3 / 5

Progressive Disclosure

The single bundle file scripts/main.py is clearly referenced, but organization is weak: a broken reference to a nonexistent requirements.txt, duplicated Dependencies vs Requirements sections (pandas appears only in one), confusing self-references ("See `## Prerequisites` above" pointing to a later section), and a non-portable cd "20260318/scientific-skills/..." example path.

3 / 5

Total

12

/

20

Passed

Description

53%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 states a clear, distinct purpose but stops at one sentence. It lacks any 'when to use' trigger guidance and misses natural synonyms like 'Upset plot' and 'set intersections', leaving all-round mediocre discoverability.

Suggestions

Append a trigger clause, e.g. "Use when the user mentions Venn diagrams with more than 4 sets, set intersections, or asks for an Upset plot."

Add natural synonyms and variations: "Upset plot", "set intersections", "set overlap", "intersection visualization".

Mention concrete capabilities and output (accepts dicts of sets or lists, renders a PNG Upset plot with configurable subset filters) to raise specificity.

DimensionReasoningScore

Specificity

"Convert complex Venn diagrams with more than 4 sets to clearer Upset" names the domain and a single conversion action, matching the anchor for 1-2 concrete actions without comprehensive coverage. It does not reach 4 because no inputs, output format, or parameters are mentioned.

3 / 5

Completeness

The 'what' is clear (convert >4-set Venn diagrams to Upset plots) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"Venn diagrams", "sets", and "Upset" are natural terms users would say, but common variations and synonyms are missing ("Upset plot", "set intersections", "set overlap", "intersection visualization"), matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The niche is distinct (Venn-to-Upset conversion for more than 4 sets) with minimal conflict risk against other skills, fitting 'mostly distinct; minor overlap risk' — it could still overlap with generic plotting or data-viz skills since no explicit triggers distinguish it.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
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.