primekg

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

Quality

64%

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 ./skills/primekg/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is well-structured with executable, copy-paste-ready examples tied to a real bundled script and appropriately shallow references, but it carries minor redundancy (duplicate data paths, marketing prose) and lacks validation/feedback checkpoints in its workflow.

Suggestions

Remove the duplicate/hardcoded data path from the Overview and keep a single canonical path in the Resources section to tighten token efficiency.

Add a brief validation step to the workflow, e.g. check that `search_nodes` returns a result and confirm the node ID before calling `get_neighbors`.

Trim the Overview's marketing prose to only the facts Claude needs (node/edge counts and relationship types).

Dimension	Reasoning	Score
Conciseness	Sections are organized and code examples are lean, but the Overview includes marketing-style prose ("integrates over 20 primary databases and high-quality scientific literature into a single resource") and the data path is stated twice in two different formats (a Windows path in the Overview and a WSL path in Resources), so it is mostly efficient but could be tightened.	2 / 3
Actionability	Each workflow step provides fully executable, copy-paste-ready code importing real functions from the bundled script (e.g. `from scripts.query_primekg import search_nodes`) with concrete arguments and documented return shapes, matching the anchor for fully executable code with specific examples.	3 / 3
Workflow Clarity	The Core Workflow lists a clear 1-2-3 sequence (search, get neighbors, analyze context), but there are no validation or feedback checkpoints (e.g. handling an empty search result or an invalid ID before calling get_neighbors), fitting the anchor for steps present but checkpoints missing or implicit.	2 / 3
Progressive Disclosure	The body is a well-organized overview with clearly signaled one-level-deep references to the single bundle file ("scripts/query_primekg.py: Core functions for searching and querying"), and the ~80-line content does not need further splitting, matching the anchor for a clear overview with well-signaled shallow references.	3 / 3
	Total	10 / 12 Passed

Description

57%

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 a distinct niche (PrimeKG) and names concrete data types, but it states only a single action and lacks any explicit "Use when..." trigger guidance, leaving both specificity and completeness at the mid level.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about drug repurposing, disease-gene associations, or multiscale biological relationships involving PrimeKG."

Expand beyond the single verb "Query" to list concrete actions such as search, retrieve neighbors, summarize disease context, and find drug-disease paths.

Include natural trigger-term variations users would say ("drug repurposing", "drug-target", "protein-protein interactions", "knowledge graph") to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("Precision Medicine Knowledge Graph (PrimeKG)") and concrete data types ("genes, drugs, diseases, phenotypes"), but offers only a single action verb ("Query") rather than multiple distinct concrete actions, matching the anchor that names domain and some actions but is not comprehensive.	2 / 3
Completeness	Clearly states what the skill does ("Query the Precision Medicine Knowledge Graph ... for multiscale biological data") but contains no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant natural terms ("genes, drugs, diseases, phenotypes", "biological data", "knowledge graph"), but omits common variations a user might say such as "drug repurposing", "drug-target", "protein", or "protein-protein interactions", fitting the anchor for some keywords but missing common variations.	2 / 3
Distinctiveness Conflict Risk	The named resource "PrimeKG" is a clear niche unlikely to overlap with other skills, and the listed biological entities further narrow its scope, matching the anchor for a clear niche with distinct triggers.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/primekg/SKILL.md
Commit: 757b63b

Reviewed: about 11 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.