The Agent Skills Directory

[SAFE]: The skill defines a robust three-step process (Shape, Confirm, Create) for generating Jira issues. It explicitly instructs the agent to show proposed values to the user and wait for confirmation before calling the 'createJiraIssue' tool, which effectively prevents unintended API executions.
[SAFE]: Configuration data such as Jira CloudId and User Account IDs are sourced from the local 'CLAUDE.md' file. This is a standard and acceptable practice for managing environment variables in this context and does not involve the exposure of credentials.
[SAFE]: The instructions provide clear constraints on issue types and project keys (e.g., enforcing 'Story' over 'Task'), ensuring that the agent operates within the intended scope and follows project-specific standards.

create-issue