skill-router
Skill Router — Orchestrator
Productivity — Utility. Analyzes user goals, recommends optimal skill teams, and coordinates multi-phase workflows across the skill ecosystem.
Core Question: "Given this goal and the current artifact state, what's the fastest path to the outcome?"
Critical Gates — Read First
- The router coordinates, it does NOT execute. It recommends which skills to run and in what order. The user invokes each skill. The router validates results between phases.
- Always check artifact state first. Fresh artifacts mean you can skip skills. Stale artifacts (>30d) mean you should re-run.
- Respect the dependency graph. Never recommend a downstream skill when its upstream artifact is missing. Trace backward to find the root blocker.
- Interactive skills need user presence.
plan-intervieweruses AskUserQuestion — flag it in the plan so the user knows to be available. - Templates are starting points, not mandates. Modify pre-built workflows based on actual artifact state. Skip phases where fresh artifacts exist.
Inputs Required
- Goal (string): What the user wants to accomplish — natural language description
- Mode (string, optional):
status|suggest(default) |orchestrate
Output
More from hungv47/meta-skills
task-breakdown
Decomposes a spec or architecture into buildable tasks with acceptance criteria, dependencies, and implementation order for AI agents or engineers. Produces `skills-resources/meta/tasks.md`. Not for clarifying unclear requirements (use discover) or designing architecture (use system-architecture). For code quality checks after building, see fresh-eyes.
81discover
Conversational discovery — adapts from quick scoping (3-5 questions) to deep interviews (multi-round). Talk until we're clear, then build. Produces inline decisions; optionally saves spec.md or scope contract. Not for multi-perspective debate (use agents-panel). Not for decomposing work (use task-breakdown). Not for diagnosing a known metric decline or root-causing a problem (use diagnose).
78agent-room
Multi-agent discussion rooms — debate or poll a problem from multiple perspectives. Standalone or invoked by other skills as a sub-routine. Mode=debate: N agents argue in rounds, converge. Mode=poll: N agents independently analyze, aggregate by consensus. Not for implementation (use system-architecture). Not for verification (use review-chain). For clarifying requirements first, see discover. For decomposing work after a decision, see task-breakdown.
67review-chain
Post-implementation quality check via fresh-eyes review. Chain: Implement → Review (independent agent) → Resolve (if issues). Max 2 rounds. Auto-triggers for security-sensitive and data-mutation code. Not for code refactoring (use code-cleanup). Not for decision analysis (use agent-room).
61navigate
Artifact status + multi-phase orchestration. Scan what exists, check freshness, compose and track complex workflows across sessions. Not for skill routing (the agent does that proactively).
57agents-panel
Multi-agent discussion rooms — debate or poll a problem from multiple perspectives. Standalone or invoked by other skills as a sub-routine. Mode=debate: N agents argue in rounds, converge. Mode=poll: N agents independently analyze, aggregate by consensus. Not for implementation (use system-architecture). Not for verification (use fresh-eyes). For clarifying requirements first, see discover. For decomposing work after a decision, see task-breakdown.
17