Guide for creating new skills, improving existing skills, and evaluating skill quality. Use this whenever the user wants to turn a workflow into a skill, revise a skill, improve triggering behavior, or add evals and benchmarks for a skill.
Use when reviewing a diff, PR, or patch for bugs, regressions, missing tests, architecture risk, security risk, or reviewability concerns before merge.
Use when starting a repo-grounded task, switching subsystems, or when output quality drops and the agent needs tighter project context from rules, specs, relevant files, examples, and current errors.
Use when implementing or reviewing framework-specific code that should be verified against current official docs, versioned guidance, or source-cited examples rather than memory.
Use when the user explicitly asks Guardian to launch or check an external coding assistant such as Codex, Claude Code, Gemini CLI, or Aider.
Use when the request is about a repo, codebase, implementation, bugfix, or backend-owned coding session that should stay anchored to the active workspace.
Use when addressing code review or QA feedback, especially when the feedback is unclear, broad, or technically questionable.
Use when the user is reviewing a security alert, posture change, suspicious network behavior, firewall issue, or combined monitoring output.