← ClaudeAtlas

comfy-promptlisted

Write production-grade prompts for ComfyUI Cloud (cloud.comfy.org) and local ComfyUI blueprints. Provides MCSLA prompt structure (Model · Camera · Subject · Look · Action), cinematic vocabulary, model routing across BFL Flux, OpenAI DALL-E, Stability SD3, Ideogram, xAI Grok, ByteDance Seedance, Pika, Runway, Vidu, Recraft, Reve, Google nano-banana, plus the 60+ local blueprints in ~/ComfyUI/blueprints/. Use this skill when the user asks to: - Write or refine an image/video prompt for Comfy - Pick the right model for a generation - Get a cinematic prompt with proper camera/motion vocabulary - Match a genre (action, product, horror, portrait, landscape, sci-fi, etc.) - Improve a weak prompt - Generate a still image, video, edit, or upscale via Comfy Pairs with `comfyui-cli` skill — this writes the prompt, comfyui-cli executes it.
404kidwiz/comfy-prompt-skill · ★ 1 · AI & Automation · score 68
Install: claude install-skill 404kidwiz/comfy-prompt-skill
# Comfy Prompt Skill Sister skill to `comfyui-cli`. This writes the prompt. `comfyui-cli` runs it. **Language rule:** Reply in whatever language the user writes in. --- ## HARD RULES — pre-delivery checklist Run this checklist BEFORE sending any prompt response. The failure mode it prevents: producing prompts that look correct because of training-data shape rather than verified Comfy model parameters. **Confirm in order:** 1. **Routing line first.** First line names model + path (cloud/local) + workflow. Example: `Routing: cloud → flux-pro (text-to-image, sync, 1024×1024)`. Missing routing line = response incomplete. 2. **Model exists and is verified.** Cloud model must appear in the cloud-models list in frontmatter, OR be a real file in `/Users/dawizkidmal/ComfyUI/blueprints/`. If user names a model not in either list, say so and offer the closest match. NEVER invent model names. NEVER claim Higgsfield/Runway-app/Pika-app names map without checking the table in `model-guide.md`. 3. **MCSLA structure intact on video prompts.** Model · Camera · Subject · Look · Action. Five layers, every video prompt, unless user explicitly opts out. 4. **Camera/motion vocabulary verified.** Camera preset names come from `vocab.md`. If user names one not in the file, say so and ask for clarification. 5. **Negative constraints appended.** Pull from `shared/negative-constraints.md`. Do not paraphrase — use file phrasing. 6. **Aspect ratio uses correct flag