wanshuiyin/align-agentic-loop-image-generation · skills_codex/reference-art-loop-codex/SKILL.md

reference-art-loop-codex skillA

ALIGN — Agentic Loop Image GeneratioN. Paint a subject in the craft of a reference artwork as executable p5.js, Canvas, SVG or another mark-based medium, replay that craft's real order of work, and improve it through pixel-only independent Codex subagent review. The reference fixes the craft; the subject may be the reference's own scene (千里江山图 → p5.js) or another (清明上河图 → 武汉). Not for one-shot raster image generation.

Latest version
mdr add wanshuiyin/align-agentic-loop-image-generation/reference-art-loop-codex@git:20260905.c8089f4
Exact content
mdr add wanshuiyin/align-agentic-loop-image-generation/reference-art-loop-codex@sha256:4e9f914c642d5604
Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_u7ckwi7wubbwujco.svg)](https://markdownregistry.com/a/art_u7ckwi7wubbwujco)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260905.c8089f4 latest2026-09-05 c8089f4 59,403 BA view

Audit of the latest version

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

Source

GitHub

wanshuiyin/align-agentic-loop-image-generation · 4 stars · license MIT · pushed 2026-09-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_u7ckwi7wubbwujco
GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/align-agentic-loop-image-generation/reference-art-loop-codex
GET https://markdownregistry.com/api/v1/blob/4e9f914c642d560445b507372423b624d993c2327cc557af3ec52007782676ea