nintendadev/unikit-ai · skills/unikit-improve/SKILL.md

unikit-improve skillA

Refine an existing implementation plan with a second iteration. Re-analyzes the codebase for gaps, missing tasks, and wrong dependencies. Use after /unikit-plan or to improve a /unikit-fix plan, or when the user says "improve the plan", "what's wrong with the plan", or "update the plan from research". Optional +check flag validates refinements via a fresh-context subagent.

Latest version
mdr add nintendadev/unikit-ai/unikit-improve@v2.5
Exact content
mdr add nintendadev/unikit-ai/unikit-improve@sha256:f1c3d77c98081ece
Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_tosttjwyqf6blmtg.svg)](https://markdownregistry.com/a/art_tosttjwyqf6blmtg)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v2.5 latest2026-09-05 6c24386 53,798 BA view · diff
v2.52026-08-25 40bbe37 51,725 BA view · diff
v2.52026-08-25 a9a2b58 50,575 BA view · diff
v2.52026-08-23 15332e2 47,142 BA view · diff
v2.52026-08-23 7fb5c29 47,027 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.

Source

GitHub

nintendadev/unikit-ai · 16 stars · license MIT · pushed 2026-09-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tosttjwyqf6blmtg
GET https://markdownregistry.com/api/v1/resolve?ref=nintendadev/unikit-ai/unikit-improve
GET https://markdownregistry.com/api/v1/blob/f1c3d77c98081ece2f0aeddf517939e85d49b1a6fe892730b43dcdd3fc48d6c9