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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/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 content is highly actionable with executable code and sensible structure, but it is verbose and repetitive, inlines material that belongs in the referenced API doc, and runs batch workflows without validation checkpoints. Trimming redundant workflows and moving endpoint detail to the reference would meaningfully raise quality.

Suggestions

Collapse the 5 example workflows into 1-2 representative ones and point the rest to references/api_reference.md to cut redundancy.

Add explicit validation checkpoints to batch workflows (e.g., check response.status_code, handle empty/missing fields before accessing them).

Move the per-endpoint parameter and response-field inventories into references/api_reference.md, keeping only one illustrative example per capability in SKILL.md.

Relocate the "As of July 2025" PharmGKB-redirect note into a clearly marked deprecation/notes subsection so time-sensitive content does not penalize conciseness.

Dimension	Reasoning	Score
Conciseness	At ~630 lines the body is noticeably verbose: the 5 workflows largely re-demonstrate the same requests.get patterns already shown in the 9 capability sections, and lists of pharmacogenes/drug categories add length without proportional new guidance; a time-sensitive "As of July 2025" date sits in main content rather than a deprecation section, further penalizing conciseness.	2 / 5
Actionability	Provides concrete, copy-paste-ready Python with real base URL, endpoints, and params across all capability sections, plus reusable rate-limiting/error-handling/caching helpers; minor gaps stem from assumed response field names (e.g., cpicLevel, pmid, evidenceLevel) that are not validated against the actual schema.	4 / 5
Workflow Clarity	Five numbered workflows give a clear sequence, but batch operations (e.g., Workflow 2 looping a gene panel, Workflow 4 over populations) lack in-workflow validation/verification checkpoints (no status checks, empty-result handling, or verify steps), capping workflow clarity at 3 per the batch-operations rule.	3 / 5
Progressive Disclosure	Two real bundle files (scripts/query_clinpgx.py, references/api_reference.md) are referenced in dedicated, clearly signaled one-level-deep sections, but a large volume of endpoint reference material (9 capability sections with params and response-field inventories) is inlined in SKILL.md that overlaps what the separate api_reference.md is meant to hold, leaving organization only partially resolved.	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.

The description is specific and highly distinctive with good domain trigger terms, but it omits an explicit "Use when..." clause, leaving the activation context only weakly implied and capping completeness. Adding a concrete trigger sentence would lift it into the top tier.

Suggestions

Append an explicit trigger clause, e.g. "Use when querying pharmacogenomics data, CPIC guidelines, or genotype-guided dosing recommendations."

Consider adding a couple more natural trigger terms users say (e.g., "drug labels", "pharmacogenetics", "CYP450 metabolism") to broaden keyword coverage.

Tighten the purpose framing so the closing phrase reinforces a use case rather than reading as a generic goal statement.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions ("Query gene-drug interactions, CPIC guidelines, allele functions") plus purpose framing, but the trailing "for precision medicine and genotype-guided dosing decisions" is goal context rather than additional discrete capabilities, leaving minor coverage gaps versus a fully comprehensive list.	4 / 5
Completeness	Provides a clear "what" (access ClinPGx data, query gene-drug interactions/guidelines/alleles) but lacks an explicit "Use when..." trigger clause; the "for precision medicine..." phrase only weakly implies when, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Strong domain keyword coverage (ClinPGx, PharmGKB, CPIC guidelines, allele functions, gene-drug interactions, genotype-guided dosing) that a pharmacogenomics user would naturally say, though a few common variations (e.g., "drug labels", "pharmacogenetics", "CYP450") are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clearly distinct niche (ClinPGx pharmacogenomics, PharmGKB successor, CPIC guidelines, genotype-guided dosing) with highly specific triggers and minimal overlap risk against general database or biology skills.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/clinpgx-database/SKILL.md
Commit: 3a6c3a9

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.