neo4j-agent-memory-skill

Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model, MemoryClient/MemorySettings, the memory MCP server, or any of the framework integrations (LangChain, PydanticAI, CrewAI, AWS Strands, Google ADK, Microsoft Agent Framework, OpenAI Agents, LlamaIndex). Also use when the user mentions the hosted service at memory.neo4jlabs.com, NAMS, the Neo4j Agent Memory Service, the `nams_` API key prefix, or the hosted MCP endpoint. Also use when writing documentation, blog posts, tutorials, PRDs, or code samples for the project, when comparing agent memory approaches, or when positioning graph-native memory against vector-only approaches — even if the user doesn't explicitly name the package.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./neo4j-agent-memory-skill/SKILL.md

Quality

Content

63%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 a dense, actionable reference with strong executable code/commands and explicit verification guidance, weakened mainly by redundant checklist sections and the absence of any bundle-file progressive disclosure for a long document. Consolidating the three overlapping checklists and splitting examples/positioning into references/ would lift the weaker dimensions.

Suggestions

Consolidate the three overlapping checklists ('Common Corrections to Watch For', 'Quick Authoritative-Facts Checklist', and the final 'Checklist') into one authoritative verification checklist to remove redundancy.

Move the canonical examples list, positioning language, and related-projects detail into references/ files (e.g. EXAMPLES.md, POSITIONING.md) and link to them from SKILL.md so the overview stays lean.

Replace the OpenAI Agents '...' import placeholder with the real import path and add an executable ExtractionConfig/DeduplicationConfig snippet to the Entity Extraction Pipeline section.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and high-value (API quickstart, MCP one-liners, positioning language, do/don't lists), but ~428 lines contain noticeable redundancy — three overlapping checklists ('Common Corrections to Watch For', 'Quick Authoritative-Facts Checklist', final 'Checklist') and a 'Resources' section repeating URLs already given in 'Project at a Glance' — that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready Python async quickstart, executable uvx/CLI MCP commands, concrete Claude Code/Desktop registration configs for both self-hosted and hosted, and per-framework import paths; minor gaps include the OpenAI Agents import shown as '...' and the Entity Extraction Pipeline being descriptive without executable config code.	4 / 5
Workflow Clarity	The authoring workflow has explicit validation checkpoints — the top 'Verify authoritative state before writing' callout, NAMS 're-check the live service' guidance, and verification checklists — but the validation is diffuse rather than a tight numbered validate→fix→retry sequence, leaving minor gaps versus a fully sequenced loop.	4 / 5
Progressive Disclosure	Section headers and tables are well organized and cross-skill references (excalidraw, neo4j-styleguide, neo4j-labs-brand, diataxis) are clearly signaled, but the skill is a 428-line monolith with no bundle files (references/, scripts/, assets/ absent), so content that could be split out — canonical examples list, positioning language, related-projects table — is inlined rather than one level deep.	3 / 5
	Total	14 / 20 Passed

Description

91%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 is a strong, explicit trigger-rich statement that clearly answers both what the skill covers and when to use it, with comprehensive natural keyword coverage. Its only weakness is minor overlap risk with neighboring Neo4j skills on the broader 'agent memory' phrasing.

Dimension	Reasoning	Score
Specificity	Names the package, hosted service, POLE+O model, MemoryClient/MemorySettings, MCP server, and the full framework-integration list as concrete reference scope, plus concrete authoring use cases (docs, blog posts, tutorials, PRDs, code samples, comparisons, positioning); minor gaps versus a fully enumerated capability list keep it just below the top anchor.	4 / 5
Completeness	Explicitly states the 'what' ('Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS)') and gives multiple explicit 'Use this skill whenever...' / 'Also use when...' trigger clauses with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and identifiers — 'neo4j-agent-memory', 'agent memory with Neo4j', 'context graphs', 'POLE+O', 'MemoryClient/MemorySettings', 'NAMS', 'nams_ API key prefix', 'hosted MCP endpoint', and all eight framework names — covering common variations a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Has a clear niche anchored on the distinct 'neo4j-agent-memory' package name and 'nams_' prefix with minimal conflict risk, but broader phrases like 'agent memory with Neo4j' and 'context graphs' create minor overlap risk with adjacent Neo4j skills (neo4j-driver, neo4j-cypher, neo4j-graphrag).	4 / 5
	Total	18 / 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-agent-memory-skill/SKILL.md
Commit: a9a5e78

Reviewed: 6 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.