maiconfz--plan-refiner--plan-refinement

Refines existing markdown plans through interactive or automatic refinement modes.

3|1|Updated May 2, 2026
One-click install
npx skills add https://github.com/agents-repo/registry --skill maiconfz-plan-refiner-plan-refinement-agents-repo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: maiconfz--plan-refiner--plan-refinement
Source: https://github.com/agents-repo/registry/tree/main/.cursor/skills/maiconfz/plan-refiner/maiconfz--plan-refiner--plan-refinement
Command: npx skills add https://github.com/agents-repo/registry --skill maiconfz-plan-refiner-plan-refinement-agents-repo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Draft implementation plans often contain gaps, ambiguities, and unverified assumptions. This Skill takes an already written plan and routes it through a structured refinement pass against the actual repository, producing a clearer, more actionable plan without starting any implementation. ## Core Features & Use Cases - Dual Refinement Modes: Choose interactive mode to answer clarifying questions, or automatic mode to fill gaps with labeled assumptions. - Repository-Grounded Pass: Both modes run a bounded pass over the host repository to validate the plan against real code. - Controlled Iteration: Interactive mode loops up to three Q&A cycles, then hands off remaining open questions and an assumption log. - Use Case: You drafted a migration plan in markdown. Run this Skill in interactive mode to resolve blockers through targeted questions, then write the refined plan back to the original file. ## Quick Start Refine my draft plan at docs/migration-plan.md using interactive mode and write the result back to the same file.

Frequently Asked Questions about maiconfz--plan-refiner--plan-refinement

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I refine an existing implementation plan with AI?▼

Provide your draft plan as markdown text or a workspace file path, then choose interactive or automatic refinement mode. The Skill routes the plan to the matching refiner agent, which validates it against the repository and returns a revised plan.

What is the difference between interactive and automatic plan refinement?▼

Interactive mode asks clarifying questions and loops up to three Q&A cycles before handing off. Automatic mode fills gaps with labeled assumptions in a single pass and never loops, producing an assumption log instead.

Can this Skill draft a new plan from scratch or from a GitHub issue?▼

No. It only refines an already written plan and does not draft first plans or intake GitHub issues. For issue-based planning, it points to the separate github-interactive-issue-implementation-planner package.

Does plan refinement write back to my original plan file?▼

Yes. If the draft plan came from a file path, the refined plan is written back to that same file only. No other host files are modified, and product implementation is never started.

What happens if blockers remain after three clarification cycles?▼

The loop stops after three cycles. The partial refined plan is handed off along with leftover open questions, and only the portions already safe to keep are written back.