The Agent Skills Directory

[SAFE]: The skill follows security best practices by instructing the agent to use IF NOT EXISTS for all database schema changes and recommending user confirmation before performing write operations.
[EXTERNAL_DOWNLOADS]: The skill references documentation and training materials from official Neo4j sources and the author's GitHub repository. These sources include neo4j.com, graphacademy.neo4j.com, and github.com/neo4j-contrib.
[INDIRECT_PROMPT_INJECTION]: The skill creates an ingestion surface for potentially untrusted data by reading database schema metadata.
Ingestion points: Database schema visualizations, constraints, and indexes retrieved via get-schema and read-cypher (SKILL.md).
Boundary markers: The skill does not explicitly define markers to encapsulate tool output within the instructions.
Capability inventory: The skill utilizes write-cypher for schema modifications and has access to the Bash tool (SKILL.md).
Sanitization: No explicit sanitization of database metadata is implemented before the agent processes the schema information.

neo4j-modeling-skill