plan-refiner

SKILL.md

This skill implements an iterative plan refinement process that transforms an initial specification into a polished implementation plan through multiple review passes with fresh agent perspective.

Note: Review agents use Context7 (mcpcontext7resolve-library-id → mcpcontext7query-docs) to verify that any package versions, GitHub Actions, APIs, or framework versions mentioned in the plan are current. This prevents recommending outdated versions based on training data.

Fallback: If Context7 MCP tools are unavailable, install the context7 skill which provides equivalent functionality via HTTP API.

Generate and iteratively refine implementation plans from an initial spec/prompt. Takes a specification as input, generates an initial plan, then refines it through multiple review passes (minimum 3) with fresh agent context. User can continue beyond 3 passes until satisfied. Use when turning requirements into polished implementation plans. Source: dreambound/plan-refiner-skill.

View raw