The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of the twg (Teamwork Graph) command-line interface to gather data across various surfaces like Jira issues, pull requests, and organization structures. It includes instructions for locating the binary in standard user directories on macOS, Linux, and Windows.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize data from external, user-controllable sources such as Jira issue descriptions, pull request comments, and Confluence pages. This content may contain instructions that could theoretically attempt to influence the agent's output during the synthesis phase.
Ingestion points: twg work query, twg pull-requests query, and twg projects query commands (referenced in SKILL.md and references/personal-work-summary.md).
Boundary markers: The instructions do not explicitly mandate the use of delimiters or warnings to the model when processing these external data points.
Capability inventory: The agent has the capability to execute the local twg CLI tool and generate summaries.
Sanitization: No specific sanitization or filtering of the retrieved artifact content is mentioned in the instructions.

twg-status-rollups