upset-plot-converter

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

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/upset-plot-converter/SKILL.md

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 content delivers fully executable, copy-paste-ready usage examples backed by a real bundle script, with a clear workflow and good section structure. Its weakness is conciseness: significant boilerplate template sections and concept re-explanation pad the body unnecessarily.

Suggestions

Remove or collapse the boilerplate template sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template, Output Requirements) that do not advance the conversion task, or move them to a reference file.

Cut concept re-explanations Claude already knows (e.g., what an Upset plot's x-axis/bars show, why >4-set Venn diagrams are hard) and keep only usage-relevant notes.

Add an explicit verify-output checkpoint to the workflow (e.g., confirm the PNG was written and inspect intersection sizes) to push workflow_clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body re-explains concepts Claude already knows ("The x-axis shows set intersections as dot patterns", "Bar heights represent the size of each intersection", "When Venn diagrams exceed 4 sets, they become difficult to read") and carries substantial boilerplate padding (Risk Assessment table, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template), fitting 'Noticeably verbose; several unnecessary explanations or padded sections'; above 1 (the core usage code is genuinely useful) and below 3 (the padding is pervasive, not occasional).	2 / 5
Actionability	The Usage section gives copy-paste-ready, executable Python importing the real module functions `convert_venn_to_upset` and `upset_from_lists` with concrete set/list data and `output_path` arguments, and the bundle `scripts/main.py` exists with matching signatures, fitting 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.	5 / 5
Workflow Clarity	A clear sequenced workflow (confirm objective → validate scope → run packaged script → structured result → fallback) with explicit checkpoints ("stop early if unsupported assumptions", fallback path) and a py_compile validation, fitting 'Clear sequence with most checkpoints present; minor validation gaps'; above 3 (checkpoints are explicit, not implicit) and below 5 (no tight validate→fix→retry loop on the generated artifact).	4 / 5
Progressive Disclosure	The skill has a single real bundle file (`scripts/main.py`) with no references/assets directories, and the body is organized into clear, well-signaled sections with the script path consistently referenced, fitting 'Good structure; most content is appropriately placed; references mostly clear; minor organization gaps'; above 3 (structure is solid, not buried) and below 5 (inlined boilerplate sections add minor organizational noise).	4 / 5
	Total	15 / 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 is clear and distinctive about a niche task (Venn-to-Upset conversion) but stops at a single action with no 'Use when' trigger guidance. Completeness and trigger-term coverage are capped by the missing explicit when-clause.

Suggestions

Add a 'Use when...' clause naming natural trigger phrases (e.g., 'Use when visualizing set intersections across more than 4 sets, or when Venn diagrams become unreadable').

Broaden trigger terms with synonyms and file extensions users might say (e.g., 'Upset plot', 'set intersections', '.csv input').

List one or two more concrete actions to lift specificity from a single 'Convert' action toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Convert ... Venn diagrams with more than 4 sets to clearer Upset" names the domain and one concrete action but offers no comprehensive set of actions, matching the anchor for 'Names domain and 1-2 concrete actions, but not comprehensive'; it is above score 2 (action is concrete, not generic) and below score 4 (only one action, not several).	3 / 5
Completeness	The description gives a clear 'what' (convert Venn to Upset) but no 'Use when...' clause or equivalent 'when' trigger, so per the cap it cannot exceed 3; it is above 2 (the 'what' is clear, not vague) and below 4 (no explicit 'when').	3 / 5
Trigger Term Quality	"Venn diagrams" and "Upset" are genuine domain keywords a user might say, but common variations, synonyms, and file extensions are missing, matching 'Some relevant keywords but missing common variations or synonyms'; above 2 (terms are domain-specific, not generic) and below 4 (coverage is thin).	3 / 5
Distinctiveness Conflict Risk	"Convert complex Venn diagrams with more than 4 sets to clearer Upset" targets a clear niche with low overlap risk, fitting 'Mostly distinct; minor overlap risk'; it is above 3 (distinct, not broadly overlapping) and just below 5 (the short description lacks the fuller trigger phrasing of the 5 anchor).	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/upset-plot-converter/SKILL.md
Commit: f5ef65b

Reviewed: ~10 hours ago

Table of Contents

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.