The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several CLI tools to interact with the environment and external services.
Evidence: Executes GitHub CLI commands (gh issue view, gh pr view, gh pr list, gh pr create) to manage repository data (SKILL.md, Sections 3.1, 5.2, 5.3).
Evidence: Uses custom tools codex exec for task execution and mkoutput for file generation (SKILL.md, Sections 2.2, 3.2).
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by ingesting and acting upon untrusted data from external platforms.
Ingestion points: Data enters the agent context through gh issue view, gh pr view, and Jira API calls, as well as reading local files via memo <path> (SKILL.md, Section 3.1).
Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands when the fetched content is passed to subagents or planning phases.
Capability inventory: The agent has the capability to write files (mkoutput), execute tasks (codex exec), and create pull requests (gh pr create).
Sanitization: No sanitization or filtering logic is present to ensure that fetched issue or PR descriptions do not contain malicious instructions that could manipulate the agent's workflow.

orchestrator