volcano-plot-labeler

Analyze data with `volcano-plot-labeler` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.

Quality

39%

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/volcano-plot-labeler/SKILL.md

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 content pairs solid, mostly-executable technical guidance (CLI, parameters, algorithm) with a large volume of generic process boilerplate and broken cross-references. It is actionable but verbose and weakly organized for navigation.

Suggestions

Collapse the redundant process sections (Output Requirements, Output Contract, Error Handling, Input Validation, Validation and Safety Rules, Response Template) into a single concise section to remove padding.

Replace the placeholder 'See `## Features` above for related details' cross-references (which point to later sections) with direct links to the actual reference file, e.g. 'See [references/runtime_checklist.md](references/runtime_checklist.md)'.

Fix the non-executable examples: correct the `python scripts/main.py --input "<sentence>"` audit command to use a CSV path, and either package the module or replace the `from volcano_plot_labeler import label_volcano_plot` import with a path that matches the bundled `scripts/main.py`.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded with overlapping templated sections (Output Requirements, Output Contract, Error Handling, Input Validation, Validation and Safety Rules, Response Template all restate scope/assumption/fallback guidance) plus empty 'See `## Features` above for related details' cross-references, much of it process boilerplate Claude already knows.	2 / 5
Actionability	It provides mostly executable guidance — a CLI invocation matching the real `scripts/main.py` argparse interface, a parameters table, and concrete algorithm steps — with minor gaps such as the non-packaged `from volcano_plot_labeler import label_volcano_plot` import and a malformed `--input "<sentence>"` audit command that would fail since --input expects a CSV path.	4 / 5
Workflow Clarity	A sequenced Workflow and validation checkpoints exist (py_compile Quick Check, non-destructive smoke check, Input Validation), but they are generic templated guidance rather than operation-specific checks (e.g. verifying CSV columns exist or confirming the output PNG was written), leaving checkpoints implicit.	3 / 5
Progressive Disclosure	Real bundle files exist (`scripts/main.py`, `references/runtime_checklist.md`) and are referenced generically by directory, but they are not signaled by filename or linked, substantial boilerplate is inlined that could live in separate files, and several 'See `## X` above' cross-references point to sections that appear later in the document, hurting navigation.	3 / 5
	Total	12 / 20 Passed

Description

28%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 a generic templated sentence that names the tool but omits its concrete capability and any usage trigger, leaning on boilerplate process language instead. It is weak on specificity, trigger terms, and completeness.

Suggestions

State the concrete capability, e.g. 'Identify and label the top 10 most significant genes in volcano plots using a repulsion algorithm to prevent label overlap.'

Add an explicit trigger clause such as 'Use when generating or annotating volcano plots from differential-expression results (CSV/TSV with log2FoldChange, p-value, and gene columns).'

Drop the generic 'reproducible workflow, explicit validation, and structured outputs' padding in favor of domain-specific terms users would actually say.

Dimension	Reasoning	Score
Specificity	The description only offers the generic action 'Analyze data with `volcano-plot-labeler`'; the actual capability (labeling the top 10 significant genes in volcano plots via a repulsion algorithm) is never stated, and 'reproducible workflow, explicit validation, and structured outputs' are process qualities rather than concrete actions.	2 / 5
Completeness	It gives a vague 'what' ('Analyze data with ...') and includes no 'Use when ...' trigger clause, matching the anchor for a vague 'what' with no 'when'.	2 / 5
Trigger Term Quality	The only keywords are the generic phrase 'Analyze data' and the skill name itself; natural user phrasings such as 'volcano plot', 'label genes', or 'significant genes' that a user would actually say are absent.	2 / 5
Distinctiveness Conflict Risk	The named tool `volcano-plot-labeler` is niche, but the templated 'Analyze data with X using a reproducible workflow ...' framing is shared across many data-analysis skills, creating moderate overlap risk.	3 / 5
	Total	9 / 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/volcano-plot-labeler/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.