CtrlK
BlogDocsLog inGet started
Tessl Logo

primekg

Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological data including genes, drugs, diseases, phenotypes, and more.

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/primekg/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 well-structured with executable examples and a clear workflow, but lacks validation/error-handling checkpoints for query operations and has minor duplication between the capabilities list and workflow sections. Adding error-handling guidance and an example for path-finding would close the gaps.

Suggestions

Add validation checkpoints: tell Claude to check for empty search results and handle the {'error': 'Disease not found'} return from get_disease_context before proceeding.

Provide an executable example for find_paths (drug-disease paths), which is promised in capabilities but never demonstrated.

Reconcile the data path inconsistency (body cites a Windows path 'C:\Users\eamon\...' while the script defaults to data/PrimeKG/kg.csv) and reference the PRIMEKG_DATA env var consistently.

DimensionReasoningScore

Conciseness

Mostly efficient with executable code blocks and no padding of basic concepts, though the 'Key capabilities' bullets partially duplicate the Core Workflow sections and could be trimmed.

4 / 5

Actionability

Three concrete, copy-paste-ready Python examples with imports, arguments, and sample return values; falls short of 5 because 'find_paths' / drug-disease path finding is promised in capabilities but has no executable example.

4 / 5

Workflow Clarity

A clear sequenced workflow (search → neighbors → disease context) with ordering guidance, but no validation or error-handling checkpoints despite the underlying functions returning errors (e.g. 'Disease not found') on missing data.

3 / 5

Progressive Disclosure

Well-organized sections with the single bundle file (scripts/query_primekg.py) clearly signaled in Resources and verified to exist; the API detail lives appropriately in the script. Minor gap: no explicit 'see query_primekg.py for full API' pointer beyond the Resources bullet.

4 / 5

Total

15

/

20

Passed

Description

65%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 clearly identifies the skill's niche and data types but lacks an explicit 'when to use' trigger clause and only describes a single action. Adding a 'Use when...' phrase with concrete trigger terms would raise completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when exploring drug-disease relationships, drug repurposing candidates, or disease-gene associations.'

List the distinct query actions the skill performs (search nodes, retrieve neighbors, summarize disease context, find paths) rather than the single verb 'Query'.

Include natural synonyms and data-file terms users might say (e.g. 'knowledge graph', 'drug repurposing', 'PrimeKG', 'kg.csv').

DimensionReasoningScore

Specificity

Names the domain (PrimeKG, multiscale biological data) and enumerates concrete data types (genes, drugs, diseases, phenotypes), but uses only a single action verb ('Query... for') rather than listing several distinct actions.

3 / 5

Completeness

Has a clear 'what' (query PrimeKG for biological data) but no 'Use when...' trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Contains relevant domain keywords (PrimeKG, knowledge graph, genes, drugs, diseases, phenotypes) a bioinformatics user would say, but misses natural synonyms and file/data trigger phrases.

4 / 5

Distinctiveness Conflict Risk

Names a specific, unique resource (Precision Medicine Knowledge Graph / PrimeKG), giving it a clear niche with minimal conflict risk against other skills.

5 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
Reviewed

Table of Contents

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.