plan

Creates read-only implementation plans for EVA platform work before any code changes.

Updated Jun 8, 2026
One-click install
npx skills add https://github.com/raulisai/eva02 --skill plan-raulisai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: plan
Source: https://github.com/raulisai/eva02/tree/main/apps/eva-core/src/skills/software-development/plan
Command: npx skills add https://github.com/raulisai/eva02 --skill plan-raulisai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It prevents risky or misaligned code changes by producing a structured, actionable implementation plan before any execution, ensuring alignment on approach, scope, and safety requirements in the EVA platform. ## Core Features & Use Cases - Structured Planning Output: Generates a markdown plan covering goal, context, approach, step-by-step tasks, files to change, tests, and risks. - EVA-Specific Safety Checks: Evaluates org_id boundaries, RLS migration needs (014_rls_policies.sql), Approval Engine requirements, and external-service approvals. - Read-Only Operation: Inspects local context without modifying code, data, production systems, or external accounts. - Use Case: Before adding a new multi-tenant API endpoint to the NestJS backend, use this Skill to map out which files change, which migrations are needed, and which tests prove the behavior. ## Quick Start Ask the agent to create an implementation plan for your proposed EVA feature or change before writing any code.

Frequently Asked Questions about plan

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

FAQPage Schema
How do I create an implementation plan before coding?

Invoke the plan skill with a description of your intended change. It inspects local context with read-only commands and outputs a markdown plan with goals, step-by-step tasks, files likely to change, tests, and risks.

What does a good software implementation plan include?

A good plan states the goal, current context and assumptions, proposed approach, step-by-step tasks, files likely to change, test and verification commands, plus risks and open questions. This Skill enforces exactly that structure.

Does the plan skill modify code or run migrations?

No. Planning is strictly read-only under the EVA Runtime Skill Policy. It never changes code, data, production systems, or external accounts unless the user explicitly asks to save a plan file.

When should I use planning instead of direct implementation?

Use planning when the task is broad, touches org_id boundaries or RLS policies, requires the Approval Engine, or involves external services, secrets, or production actions where unaligned execution would be risky.

What EVA-specific checks does the plan include?

The plan identifies where org_id boundaries apply, whether migrations or 014_rls_policies.sql updates are needed, whether the Approval Engine is required, and which unit or e2e tests should prove the behavior.