The Agent Skills Directory

[SAFE]: The skill's primary function is to organize development tasks into 'vertical slices' or tickets. It follows a structured process involving context gathering, user clarification, and draft approval before performing any write operations.
[DATA_EXPOSURE]: The skill accesses local project files such as docs/agents/issue-tracker.md and writes to a work/ directory. These actions are within the expected scope for a development-focused agent tool and do not involve sensitive system paths or credentials.
[EXTERNAL_DOWNLOADS]: The skill integrates with well-known issue tracking platforms like GitHub and Linear. It fetches issue content and publishes new tickets based on user-provided identifiers and URLs, which is standard functionality for the described purpose.
[PROMPT_INJECTION]: The skill uses explicit instructions to structure the agent's behavior (e.g., <vertical-slice-rules>, <local-ticket-template>). These are internal formatting constraints and do not attempt to bypass safety filters or override system-level instructions.
[COMMAND_EXECUTION]: The skill mentions external commands like /setup-work and /implement, which appear to be part of the agent's expected toolset for implementation workflows.

to-tickets