preflight
Preflight
Meta — Methodology. Surface your assumptions, then lock down success criteria before building.
Core Question: "What would I silently get wrong if I just started coding?"
Critical Gates — Read First
- Never skip Phase 1 for non-trivial tasks — even if the user says "just build it," hidden assumptions are the #1 cause of rework. Ask the questions.
- FAILURE clauses are the key innovation — they prevent the builder from taking shortcuts they'd otherwise rationalize. Every contract MUST have specific failure conditions.
- 5 questions, not 20 — the constraint forces prioritization. Ask the questions where a different answer would MOST change your approach.
- Wait for answers before Phase 2 — never generate the contract from assumptions alone.
Philosophy
The most expensive agent failures are silent assumption failures — confidently building the wrong thing because you assumed REST when they meant GraphQL, or assumed a new file when they wanted to extend an existing one. Preflight makes assumptions visible and fixable before they're expensive.
The FAILURE clause front-loads reasoning about what "done" means. Without it, agents silently cut corners they'd avoid if failure modes were explicit.
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 `.agents/skill-artifacts/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.
79discover
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).
76agent-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 Not for implementation (use system-architecture).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).
57fresh-eyes
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 agents-panel).
16