ia-planning

What problem does it solve?

This Skill prevents AI coding agents from jumping straight into implementation without deciding what “done” means, how to verify it, and what scope boundaries to respect.

Core Features & Use Cases

• File-persisted planning: Creates and uses a .plan/ working state so key decisions and progress survive context resets.
• Goal quality gate: Forces measurable success criteria and explicit stop/ask points before planning.
• Context window discipline: Treats conversation context as volatile memory and writes important plan artifacts to disk.
• Test discovery for real projects: Detects existing test landscapes to plan verification against current conventions.
• Structured, phase-based plan template: Produces concrete, phase-sized tasks with verifiable acceptance checks.
• Guardrails against plan drift: Requires deviation documentation and traceability from completed tasks (including commit SHA recording).

Quick Start

Ask the agent to produce an implementation plan for a feature that touches multiple files and has ambiguous scope, and ensure it first gates success criteria with a measurable verification step.