comic-blind-comparison-review

SKILLWorkflowcommunity
v0.0.0wanshuiyinMITUpdated 1mo agoSource →

Phase-1 comic-author step (post-final eval) — a DOUBLE-BLIND A/B of two FINAL whole comics: our cross-model-audited progressive render (the comic-author + comic-director output) vs a naive single-shot baseline. A single sealed coin-flip hides which is which; two cross-model reviewers (Codex + Gemini

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
48Repo stars
1Clients
1Formats
1mo agoLast update
Skill
Authorwanshuiyin
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

Phase-1 comic-author step (post-final eval) — a DOUBLE-BLIND A/B of two FINAL whole comics: our cross-model-audited progressive render (the comic-author + comic-director output) vs a naive single-shot baseline. A single sealed coin-flip hides which is which; two cross-model reviewers (Codex + Gemini) score both on a fixed rubric reading only a SHARED blind spec (intent + ART_BIBLE); only AFTER bot

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.