wanshuiyin/align-agentic-loop-image-generation · skills/method-figure-loop/SKILL.md

method-figure-loop skillA

ALIGN for paper figures — draw a method-overview figure as an executable p5.js program that replays its own construction in named stages, exports SVG, and improves through pixel-only cross-model review whose gate is 'explain the method back from the figure alone, and is it worth looking at'. The method sets the relationships the figure must show, the chosen visual identity sets how its marks look, a composition source lends arrangements; the method may be the source's own (意临) or yours in its ar

Latest version
mdr add wanshuiyin/align-agentic-loop-image-generation/method-figure-loop@git:20260905.c8089f4
Exact content
mdr add wanshuiyin/align-agentic-loop-image-generation/method-figure-loop@sha256:4751408585505028
Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_v2bpxs3jfb2d4a5m.svg)](https://markdownregistry.com/a/art_v2bpxs3jfb2d4a5m)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260905.c8089f4 latest2026-09-05 c8089f4 59,923 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_v2bpxs3jfb2d4a5m
GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/align-agentic-loop-image-generation/method-figure-loop
GET https://markdownregistry.com/api/v1/blob/47514085855050289f1460d9b7c7e6dec4958d73f17fc8be9c1ee09b8d47ab11