The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using the GitHub CLI (gh issue create, gh issue list) to interact with the project repository. This is the primary function of the skill and is handled via standard developer tools.\n- [DATA_EXFILTRATION]: The skill accesses local project information, specifically reading CLAUDE.md and checking the .git directory, to automatically identify whether to use GitHub or Linear for issue tracking.\n- [PROMPT_INJECTION]: The skill ingests user input for issue descriptions and titles, which are then passed to external tools. This creates a surface for indirect prompt injection, although the risk is mitigated by the skill's specific role and common usage environment.\n
Ingestion points: User-provided description input via the /issue command defined in SKILL.md.\n
Boundary markers: Absent; the skill relies on the agent to correctly format command arguments without explicit delimiter instructions.\n
Capability inventory: Executes gh CLI commands and utilizes Linear MCP tools for issue creation and retrieval.\n
Sanitization: The skill includes a 'rewrite' policy in references/feature-request-policy.md to convert technical language into user-facing outcomes, providing a layer of content transformation, though not designed specifically for security sanitization.

issue