The Agent Skills Directory

[NO_CODE]: The skill consists entirely of high-level process instructions and markdown templates. It does not include any scripts, executable code, or direct shell command invocations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external context such as specifications, issue bodies, and conversation history. While this presents a theoretical attack surface for indirect prompt injection, the skill includes a mandatory human-in-the-loop checkpoint (Step 4: Quiz the user) where the proposed tickets and their logic must be manually approved before any external writing occurs, mitigating the risk of automated malicious actions.

to-tickets