metyatech

Use this skill to verify deployments after code changes to globally linked packages, running services, daemons, or scheduled tasks, especially when changes affect a globally installed CLI or a running service. Avoid using it for general development, CI setup, or initial deployments.

Use when designing or reviewing a user-facing GUI to reduce first-use cognitive load, clarify the primary path, improve discoverability and feedback, prevent errors, ensure accessibility, and ground decisions in established HCI and usability theory.

Use for executing shell commands or external processes requiring platform-aware procedures, federated identity handoff to a real browser session, agent-browser session retry, privilege elevation fallback paths, or destructive file deletion safety. Triggers when invariants in the `command-execution` rule module need procedural how-to detail.

Use this skill when setting up or configuring code quality tools (formatters, linters, type checkers, dependency scanners) for a repository, or when adding visual accessibility automation or security baseline scanning. Do not use it for general coding or when tools are already configured.

Use when preparing a release, publishing a package, bumping a version, or configuring public repository metadata. Also use when verifying a published package. Do not use for general development or non-release tasks.

Use for writing tests, designing test coverage, handling defect fixes, root-cause analysis, CI verification, or configuring commit-time hooks. Also for creating test matrices or choosing between unit/integration/E2E tests, but not for general development or linting setup.

Design and build systems manageable by both humans and AI agents. Use this skill when a request implies joint operation, editing, or maintenance by humans and AI, requiring inference of various system components.

Use when designing, building, or reviewing a command-line interface (CLI) tool. It provides a checklist of standard CLI conventions and should not be used for non-CLI applications.

Use when addressing PR review feedback, re-requesting reviews, handling GitHub review bot re-reviews (Codex, Copilot), or managing GitHub notifications. Do not use for creating new PRs or general development.

Provides reference data and procedures for dispatching sub-agents in parallel, covering model inventory, parameter details, prompt templates, routing, quota fallback logic, and platform-specific workarounds. Use this skill when dispatching sub-agents and requiring the full model inventory or detailed procedures.

Autonomous meta-orchestrator that continuously discovers work, dispatches agents, reviews results, and manages the full lifecycle across the user's workspace. Use when the user wants hands-off autonomous operation.