variant-pathogenicity-predictor

Integrate REVEL, CADD, PolyPhen scores to predict variant pathogenicity.

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/variant-pathogenicity-predictor/SKILL.md

Quality

Content

53%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 body is well-structured with a clearly signaled single script reference, but it carries notable generic boilerplate and—most critically—documents a CLI that does not match the actual main.py, undermining actionability and workflow clarity.

Suggestions

Reconcile the Usage/Parameters sections with scripts/main.py: the real flags are --revel/--cadd/--polyphen/--demo, not --variant/--vcf/--gene/--scores.

Surface the actual prediction logic (CADD normalization to /30, the 0.4/0.3/0.3 composite weighting, and the 0.9/0.7/0.3/0.1 classification thresholds) so the workflow is concrete rather than generic process prose.

Trim generic meta-sections (Response Template, Output Requirements, Lifecycle Status, Audit-Ready Commands which duplicates Quick Check) to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	Core domain sections (Usage, Parameters, Integrated Scores, Output) are reasonably tight, but several generic meta-process sections (Key Features, Implementation Details, Output Requirements, Response Template, Lifecycle Status) pad the document without adding domain value.	3 / 5
Actionability	Concrete commands and parameters are listed, but the documented flags (--variant/--vcf/--gene/--scores) do not match the actual script's CLI (--revel/--cadd/--polyphen/--demo), so the flagship examples fail as written.	3 / 5
Workflow Clarity	A numbered Workflow sequence is present, but it is generic meta-process (confirm/validate/run/return) rather than the computational steps, and it lacks explicit output-validation or feedback checkpoints.	3 / 5
Progressive Disclosure	Well-organized into clear sections with the single bundle script (scripts/main.py) clearly signaled and only one level deep; minor organization gaps come from the generic boilerplate sections.	4 / 5
	Total	13 / 20 Passed

Description

66%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 specific and names concrete tools plus a natural trigger phrase, but it omits any explicit 'when to use' guidance, capping completeness at 3. It is otherwise a solid, distinguishable description.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases like 'when classifying a variant as pathogenic or benign' or 'when the user provides REVEL, CADD, or PolyPhen scores'.

Include common synonyms and file formats (e.g. VCF, variant classification, ACMG criteria) to broaden trigger-term coverage.

Mention SIFT/MutationTaster in the description, since the skill body integrates them too.

Dimension	Reasoning	Score
Specificity	Names concrete actions and specific tools ('Integrate REVEL, CADD, PolyPhen scores to predict variant pathogenicity'), which is more than a generic domain mention but stops short of a comprehensive multi-action list.	4 / 5
Completeness	Provides a clear 'what' but no 'Use when...' or equivalent trigger clause; per the rubric, a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes a natural domain phrase users would say ('predict variant pathogenicity') plus specific tool names (REVEL, CADD, PolyPhen), though a few synonyms and file formats (e.g. 'variant classification', VCF) are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (variant pathogenicity with named scoring tools) and is mostly distinct, with only minor overlap risk against closely related genomics skills.	4 / 5
	Total	15 / 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/variant-pathogenicity-predictor/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.