The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to clone the flowtrace repository directly from the vendor's GitHub account (github.com/AIScientists-Dev/Flowtrace.git) to obtain the necessary CLI tool.
[COMMAND_EXECUTION]: The skill involves executing various shell commands, including a local installation script (./scripts/install.sh) from the vendor's repository and multiple flowtrace subcommands for trace initialization, run management, and starting a local visualization server on port 3000.
[PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface as it processes arbitrary 'source' materials like prose, chat logs, or runbooks to build DAG structures.
Ingestion points: The skill instructions in SKILL.md direct the agent to read and 'lift' content from external source documents.
Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the source documents.
Capability inventory: The agent can execute shell commands, perform file system operations, and access the network via git.
Sanitization: The skill does not define any sanitization or validation logic for the external text data before it is processed by the agent.

make-trace