guardian-agent

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.

Use when encountering a bug, failing test, broken integration, or unexpected behavior, before proposing fixes.

Use when implementing or changing code behavior, before writing production code.

Use when the user asks for an implementation plan or when a coding task is large enough that it should be decomposed before editing.

Use when about to claim work is complete, fixed, or passing, or before committing or handing off results.

Toolkit for testing local web applications and browser workflows with MCP browser tools. Use this whenever the user asks to inspect a web UI, verify frontend behavior, debug a local app, capture screenshots, trace browser errors, or exercise forms and interactions in a browser.

Use when the task needs investigation first, especially to compare code paths, trace behavior, or synthesize findings before implementation.

Guide for building high-quality MCP (Model Context Protocol) servers and tool suites. Use this whenever the user asks to build, design, refactor, review, or evaluate an MCP server, expose an API through MCP, or improve tool naming, schemas, pagination, auth, or error handling.