The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill programmatically generates several Python scripts to facilitate project setup, including provision_aura.py for database creation, generate.py for synthetic data, and import.py for data loading. These scripts are executed within a local virtual environment to finalize the application environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill includes functionality to construct Knowledge Graphs from external data sources, which presents a surface for indirect prompt injection.\n
Ingestion points: Documents (PDF, MD, TXT) and CSV files stored in the data/ directory are processed by the SimpleKGPipeline and pandas during the load stage.\n
Boundary markers: The instructions do not specify the use of boundary markers or delimiting wrappers for ingested content.\n
Capability inventory: The agent has access to powerful tools including Bash for command execution, Write for file creation, and WebFetch for external data retrieval.\n
Sanitization: No specific sanitization or filtering logic was identified for data processed by the LLM during entity extraction.\n- [EXTERNAL_DOWNLOADS]: The skill retrieves necessary binaries and datasets from external vendor-controlled sources.\n
Evidence: Downloads the neo4j-mcp binary from the official Neo4j GitHub repository and fetches demo datasets from vendor domains such as data.neo4j.com.\n- [COMMAND_EXECUTION]: The skill performs environment configuration using system-level commands.\n
Evidence: Uses Bash to run docker for database containerization, pip for installing Python dependencies, and chmod to grant execution permissions to project binaries.

neo4j-getting-started-skill