The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run graphify CLI commands, such as graphify query and graphify summary, against the local project environment to retrieve workspace metadata.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from a local workspace file (.graphify/graph.json) through the outputs of the graphify tool.
Ingestion points: Content is read from the .graphify/graph.json file as described in the instructions.
Boundary markers: The instructions do not define delimiters or provide specific instructions to ignore potential commands embedded within the knowledge graph data.
Capability inventory: The skill has the capability to execute shell commands via the graphify CLI tool.
Sanitization: No explicit validation or filtering is applied to the data retrieved from the knowledge graph before it is processed by the agent.

graphify-map