The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the redmine-pp-cli and redmine-pp-mcp tools from the vendor's official GitHub repository and npm registry using go install and npx.
[COMMAND_EXECUTION]: The skill operates by executing commands via the redmine-pp-cli binary to manage Redmine resources and perform network operations.
[DYNAMIC_EXECUTION]: The skill includes an "automatic learning" system that generates and stores command choreographies ("playbooks") in local JSON files. These playbooks are dynamically replayed by the agent to handle recurring tasks.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Redmine servers (such as issue details and wiki pages) which may be controlled by third parties, creating a potential surface for indirect instructions.
Ingestion points: Data enters the agent context through CLI commands like issues-json get-issues and news get.
Boundary markers: The instructions do not provide explicit delimiters or warnings to ignore embedded instructions within the fetched data.
Capability inventory: The agent has access to bash and a powerful CLI tool capable of network requests, webhook delivery, and resource deletion.
Sanitization: No explicit sanitization or filtering of the external Redmine content is described.

pp-redmine