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

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/clinpgx-database/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 body is rich in executable, actionable API guidance and references real, well-described bundle files, but it is severely over-inflated: it duplicates the API reference inline, pads with glossaries and category lists, includes a promotional section, and lacks validation checkpoints inside its workflows.

Suggestions

Collapse the nine 'Core Capabilities' endpoint walkthroughs into brief one-line pointers to references/api_reference.md (which already documents the same endpoints), keeping only one or two representative examples inline.

Remove the 'Suggest Using K-Dense Web' promotional section and the 'Key pharmacogenes'/drug-category glossary lists, or move them to a reference file.

Integrate the error-handling and rate-limiting helpers into the workflows themselves (e.g. have Workflow 2's loop use rate_limited_request and check response status before processing).

Dimension	Reasoning	Score
Conciseness	The ~630-line body contains noticeably verbose padding: gene and drug category lists, phenotype/evidence-level glossaries that duplicate references/api_reference.md or assume knowledge Claude already has, a promotional 'Suggest Using K-Dense Web' section, and a time-sensitive 'As of July 2025' note outside any deprecated section. The Core Capabilities section inlines a full API walkthrough that belongs in the reference file.	2 / 5
Actionability	Concrete, executable request snippets with real endpoints appear throughout, plus ready-to-use rate-limiting, retry/backoff, and caching functions. Minor gaps (e.g. the undefined calculate_phenotype_frequencies call in Workflow 4) keep it below fully copy-paste ready.	4 / 5
Workflow Clarity	The five workflows are clearly numbered and sequenced, but validation/error handling lives in a separate section instead of being incorporated as checkpoints — Workflow 2's batch loop issues repeated API calls with no rate limiting or per-request error handling. Not 4 because the checkpoints are not integrated into the workflows themselves.	3 / 5
Progressive Disclosure	Both bundle files (scripts/query_clinpgx.py, references/api_reference.md) exist and are well-signaled with descriptions of their contents and when to consult them, but roughly 450 lines of per-endpoint API examples are inlined in SKILL.md and duplicate api_reference.md — content that should be separate is inline.	3 / 5
	Total	12 / 20 Passed

Description

70%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.

A strong, specific, third-person description that names concrete pharmacogenomics capabilities and a distinct niche. Its main weaknesses are the absence of an explicit 'Use when...' trigger clause and a few missing natural synonyms.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks about gene-drug interactions, pharmacogenomic dosing, CPIC guidelines, or allele function'.

Include common synonyms and user phrasings such as 'PGx', 'drug-gene interactions', 'medication response', and 'pharmacogenetic testing' to broaden trigger coverage.

Mention drug labels and pathways briefly to round out capability coverage without adding length.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — 'Query gene-drug interactions, CPIC guidelines, allele functions' — in third person, but omits other capabilities (drug labels, pathways, variant queries), leaving minor coverage gaps that keep it below the comprehensive anchor.	4 / 5
Completeness	The 'what' is clear and specific, but there is no 'Use when...' clause; the 'when' is only weakly implied by 'for precision medicine and genotype-guided dosing decisions', which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Natural trigger phrases like 'pharmacogenomics', 'CPIC guidelines', 'allele functions', 'genotype-guided dosing', and 'PharmGKB' are present, but common synonyms users might say such as 'PGx', 'drug-gene', or 'medication response' are missing.	4 / 5
Distinctiveness Conflict Risk	ClinPGx/PharmGKB/CPIC pharmacogenomics is a clear niche with distinct domain-specific triggers (allele functions, genotype-guided dosing) and minimal overlap risk with other skills.	5 / 5
	Total	16 / 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 (638 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: googolme/run0204
Path: scientific-skills/clinpgx-database/SKILL.md
Commit: 4902409

Reviewed: 6 days 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.