open-targets-db

Query the Open Targets Platform to retrieve targets, diseases, or evidence records when you need target-disease association data and evidence-based scores for therapeutic discovery.

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 ./scientific-skills/Evidence Insight/open-targets-db/SKILL.md

Quality

Content

52%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 skill provides a real, runnable script and clear usage examples with sensible file separation, but it is weighed down by large amounts of generic boilerplate and by documented options (`--fields`, `--type evidence`) that the shipped script does not actually support.

Suggestions

Remove or collapse the generic boilerplate sections (When Not to Use, Required Inputs, Output Contract, Validation and Safety Rules, Failure Handling, Completion Checklist, Scope Reminder) that are not specific to querying Open Targets.

Reconcile the documented interface with the script: either implement `--fields` and an `evidence` query type in `scripts/query_opentargets.py`, or remove those options from the body so examples are copy-paste accurate.

Move the inputs/outputs and scoring-model detail into `references/api_reference.md` and keep SKILL.md a lean overview pointing to it.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded with several generic boilerplate sections (When Not to Use, Required Inputs, Recommended Workflow, Deterministic Output Rules, Output Contract, Validation and Safety Rules, Failure Handling, Completion Checklist, Scope Reminder) that add no Open Targets-specific value, plus a conceptual scoring explanation Claude does not need.	2 / 5
Actionability	The primary command (`python scripts/query_opentargets.py --id ... --type target`) is executable and the script exists, but documented features do not match the actual script: `--fields` is not implemented and `--type evidence` is listed as supported while the script only accepts target/disease/search.	3 / 5
Workflow Clarity	The single query action is unambiguous from the Example Usage and a Quick Validation checkpoint (`--help`) is provided; the generic Recommended Workflow is boilerplate but does not obscure the concrete path, leaving only minor gaps.	4 / 5
Progressive Disclosure	Good one-level-deep structure: SKILL.md is an overview pointing to a real `references/api_reference.md` and a real `scripts/query_opentargets.py`, both clearly signaled; minor gaps because the API reference is thin and some API detail (inputs/outputs/scoring) is still inlined in the body.	4 / 5
	Total	13 / 20 Passed

Description

73%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 description that names a concrete platform and actions with an embedded trigger clause; its main weakness is the second-person phrasing and a trigger that is integrated into the sentence rather than a separate explicit "Use when" clause.

Suggestions

Rewrite the trigger in third person with a standalone "Use when..." clause, e.g. "Use when retrieving target-disease associations or evidence-based scores from the Open Targets Platform for therapeutic discovery."

Add common synonyms/extensions users might say (e.g. "Ensembl gene IDs", "EFO IDs", "GWAS/ClinVar/ChEMBL evidence") to broaden trigger-term coverage.

Drop the second-person "when you need" to avoid the voice penalty and tighten specificity.

Dimension	Reasoning	Score
Specificity	Names the Open Targets domain and concrete actions ("retrieve targets, diseases, or evidence records" plus "target-disease association data and evidence-based scores"), which would anchor at 4, but the second-person clause "when you need" triggers the -1 voice penalty per guidelines.	3 / 5
Completeness	Clearly states what ("Query the Open Targets Platform to retrieve targets, diseases, or evidence records") and embeds an explicit when clause ("when you need target-disease association data and evidence-based scores for therapeutic discovery"), though the trigger is embedded rather than a standalone "Use when..." clause and could be more granular.	4 / 5
Trigger Term Quality	Good keyword coverage of domain terms a biomedical user would actually say ("Open Targets Platform", "targets", "diseases", "evidence", "target-disease association", "therapeutic discovery"), with only minor natural synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Naming a specific platform ("Open Targets Platform") with domain-specific triggers (target-disease association, evidence-based scores) gives it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	16 / 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/Evidence Insight/open-targets-db/SKILL.md
Commit: 63c61d3

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.