clinpgx-database

Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/clinpgx-database/SKILL.md

Quality

Content

61%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 is highly actionable with extensive executable examples and clear file-based references, but it is verbose for an API wrapper and the batch workflow lacks validation checkpoints. Tightening repeated boilerplate and adding response checks would lift the lower dimensions.

Suggestions

Replace the repeated full URL in each example with the BASE_URL constant to cut substantial tokens and reduce drift.

Add response validation to the batch gene-panel workflow (check status_code / handle 429 per iteration) so workflow clarity can exceed the batch-operation cap.

Move the per-endpoint example bulk into references/api_reference.md, keeping only a representative quick-start example inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful but noticeably padded for an API skill — the full base URL is repeated in nearly every code block instead of using the defined BASE_URL, and several sections restate endpoint capability lists that overlap the separate api_reference.md.	3 / 5
Actionability	Concrete, mostly copy-paste-ready Python examples cover the common query cases, though some field accesses (e.g., pair['cpicLevel'], allele['name'], annotation['phenotype']) appear speculative relative to the real API schema.	4 / 5
Workflow Clarity	Five numbered workflows are clearly sequenced, but the batch gene-panel workflow (Workflow 2) lacks response validation/checkpoints, and per the rubric missing validation in batch operations caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Real bundle files exist and are well-signaled one level deep (scripts/query_clinpgx.py and references/api_reference.md each get a descriptive pointer section), though a large amount of per-endpoint reference material is still inlined in SKILL.md.	4 / 5
	Total	14 / 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 third-person with strong domain keywords, but it omits an explicit 'when to use' trigger clause, which caps completeness. It is clearly distinguishable from generic data skills.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g., 'Use when querying pharmacogenomic gene-drug pairs, CPIC dosing guidelines, or allele function data.'

Include legacy synonyms users may still say (e.g., 'PharmGKB') alongside ClinPGx to improve trigger-term coverage.

Mention additional capabilities surfaced in the body (drug labels, variant/clinical annotations) to round out the action list.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Access ClinPGx pharmacogenomics data", "Query gene-drug interactions, CPIC guidelines, allele functions" — with only minor coverage gaps (e.g., drug labels/variants omitted from the description).	4 / 5
Completeness	The "what" is clearly stated but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Contains domain-natural keywords ("pharmacogenomics", "gene-drug interactions", "CPIC guidelines", "allele functions", "genotype-guided dosing") with good coverage, though synonyms and the "PharmGKB" legacy term are only partially represented.	4 / 5
Distinctiveness Conflict Risk	Names a specific database (ClinPGx/PharmGKB successor) with a distinct niche, carrying only minor overlap risk with broader genetics or biomedical skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (636 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/clinpgx-database/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.