neo4j-gds-skill

Neo4j Graph Data Science (GDS) embedded plugin via Python client or Cypher — covers GraphDataScience, gds.v2 plugin endpoints, gds.version, native projection, Cypher projection, graph catalog operations, stream/stats/mutate/write modes, memory estimation, PageRank, Louvain, WCC, FastRP, KNN, Node Similarity, ML pipelines, and cleanup. Use for Aura Pro, self-managed, local, or offline Neo4j DBMS with the GDS plugin installed. Does NOT cover Aura Graph Analytics GDS Sessions, AuraGraphDataScience, GdsSessions, gds.graph.project.remote, or AuraDB Cypher API projection/session management — use neo4j-aura-graph-analytics-skill. Does NOT handle Cypher authoring — use neo4j-cypher-skill. Does NOT cover driver setup — use neo4j-driver-python-skill or other driver skill.

Quality

96%

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

Quality

Content

92%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.

A dense, actionable reference with strong workflow scaffolding and clean progressive disclosure into two real reference files. The main weakness is mild redundancy from repeated routing disclaimers and duplicated notes that could be trimmed.

Suggestions

Collapse the repeated 'AGA Sessions → neo4j-aura-graph-analytics-skill' disclaimers into the single 'When NOT to Use' block; reference it once instead of restating per-section.

Dedupe the undirected-projection / Leiden-undirected note — it appears in both the projection and Louvain sections; state it once.

Move the inline graphdatascience 1.x↔2.0 and GDS-server compatibility detail into references/ (or a short 'Compatibility / migration' subsection) to keep the Pre-flight section lean.

Dimension	Reasoning	Score
Conciseness	Mostly lean, executable content with little explanation of concepts Claude already knows, but the routing disclaimer 'AGA Sessions → neo4j-aura-graph-analytics-skill' is repeated ~6 times and the undirected/Leiden note is duplicated, while a dense inline version-compatibility block could be condensed.	4 / 5
Actionability	Copy-paste-ready Cypher and Python examples cover the common cases — projection, every execution mode, each core algorithm, and the FastRP→KNN pipeline — with concrete, specific calls rather than pseudocode.	5 / 5
Workflow Clarity	A 7-step Full Workflow with explicit validation checkpoints (plugin pre-flight, memory estimate, stream-to-verify → mutate → write pattern, ask-confirmation before write-cypher), a Common Errors recovery table, and a closing checklist — no destructive-operation validation gap.	5 / 5
Progressive Disclosure	SKILL.md is a well-sectioned overview pointing one level deep to real bundle files — references/algorithms.md and references/graph-projection.md (both present) — clearly signaled inline and in a References section, with bulk catalog material split out.	5 / 5
	Total	19 / 20 Passed

Description

100%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 highly specific, well-scoped description that answers what and when with concrete trigger terms and explicit sibling-skill boundaries. It avoids fluff and over-claims throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities — 'native projection, Cypher projection, graph catalog operations, stream/stats/mutate/write modes, memory estimation, PageRank, Louvain, Wcc, FastRP, KNN, Node Similarity, ML pipelines, and cleanup' — giving comprehensive coverage rather than vague domain naming.	5 / 5
Completeness	Explicitly answers both what (the enumerated operations) and when ('Use for Aura Pro, self-managed, local, or offline Neo4j DBMS with the GDS plugin installed'), with concrete trigger phrases and explicit negative-scope redirects.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage for the domain: 'Neo4j Graph Data Science', 'GDS', 'PageRank', 'Louvain', 'FastRP', 'KNN', plus synonyms ('Python client or Cypher') that a user needing this skill would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche with minimal conflict risk: three 'Does NOT cover ... use <sibling-skill>' clauses carve it apart from aura-graph-analytics, cypher, and driver skills.	5 / 5
	Total	20 / 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: neo4j-contrib/neo4j-skills
Path: neo4j-gds-skill/SKILL.md
Commit: a3627d2

Reviewed: 4 days 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.