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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/clinpgx-database/SKILL.md

Quality

Content

56%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.

Highly actionable content with concrete, executable API examples and clearly sequenced workflows, undermined by significant verbosity and duplication of the bundle's reference and script files. Refactoring SKILL.md into a lean overview with pointers would resolve most of the deficit.

Suggestions

Replace the nine per-endpoint code sections with a short endpoint table and defer examples to references/api_reference.md, keeping only one or two quick-start examples inline.

Delete the inlined rate-limiting, error-handling, and caching code (duplicated from scripts/query_clinpgx.py) and reference the script's functions instead.

Trim the "Key pharmacogenes", "Drug categories", and "Important Notes" list sections to the few entries that add non-obvious value, or move them to the reference file.

Dimension	Reasoning	Score
Conciseness	The ~640-line body is noticeably verbose: nine full per-endpoint code walkthroughs, "Key pharmacogenes" and "Drug categories" list sections, and "Important Notes" prose duplicate material already present in references/api_reference.md and scripts/query_clinpgx.py — the rate-limiting, error-handling, and caching code is reproduced nearly verbatim from the script.	2 / 5
Actionability	Guidance is mostly copy-paste-ready: concrete requests.get calls with real endpoints and parameters for every resource type, plus complete error-handling and caching helpers. Minor gaps remain — Workflow 4 step 3 calls an undefined calculate_phenotype_frequencies function and Workflow 2's filtering snippet assumes response keys that are never verified.	4 / 5
Workflow Clarity	Five workflows present clearly numbered, concrete steps with per-step code, and rate-limit compliance plus retry/backoff guidance is provided. The workflows themselves don't checkpoint response validation (only the separate error-handling section covers it), leaving minor validation gaps; no destructive-op cap applies since these are read-only queries.	4 / 5
Progressive Disclosure	The bundle structure is real and well-signaled (references/api_reference.md and scripts/query_clinpgx.py exist and each is introduced with when to consult it), but content that clearly belongs in those files — the full nine-endpoint API tour with example code — is inlined in SKILL.md rather than summarized with pointers.	3 / 5
	Total	13 / 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 specific, well-scoped description with good natural trigger keywords and strong distinctiveness, weakened mainly by the absence of an explicit "Use when..." clause. Adding trigger conditions and a few synonym terms would lift it to top-tier quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user mentions pharmacogenomics, PGx, gene-drug interactions, CPIC guidelines, genotype-guided dosing, or PharmGKB/ClinPGx."

Include common synonyms users say — "PGx", "drug response", "allele frequency", "drug labels" — in the trigger phrase to improve recall.

Optionally mention drug label and variant annotation queries to round out the capability coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and several concrete third-person actions ("Query gene-drug interactions, CPIC guidelines, allele functions") but omits capabilities the body demonstrates (drug labels, pathways, variant queries), leaving minor gaps in coverage rather than comprehensive coverage.	4 / 5
Completeness	The "what" is clear and concrete, but there is no "Use when..." clause or equivalent explicit trigger guidance; the trailing "for precision medicine and genotype-guided dosing decisions" only weakly implies when to invoke the skill, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Good natural keywords users would actually say — "pharmacogenomics", "CPIC guidelines", "gene-drug interactions", "genotype-guided dosing", "ClinPGx", "PharmGKB" — but common variations like "PGx", "drug response", or "allele frequency" are missing.	4 / 5
Distinctiveness Conflict Risk	The description occupies a clear niche (a pharmacogenomics database) with distinct trigger vocabulary (ClinPGx, CPIC, gene-drug interactions) that is unlikely to fire for the wrong skill.	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 (644 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: 4082a2e

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.