MCP App StoreMCP App Store
from comfyui-expert50
Guided conversational interview that extracts a user's creative vision and synthesizes model-specific image prompts, negatives, recommended settings, and a pipe
This skill conducts a short, guided conversation (4-7 exchanges) to clarify a user's creative idea, then generates a complete, model-appropriate image prompt package: positive prompt, negative prompt, a recommended settings table, and a brief pipeline recommendation tailored to ComfyUI workflows and multiple model families (SDXL, SD1.5, FLUX, Wan/video). It also includes decision rules for model selection and example interview flows.
Invoke when a user has an image idea but lacks detailed prompt wording or settings — e.g., "help me write a prompt", "I want to create...", or when refining a concept for character, scene, product, abstract, or short video generation. Use it to produce ready-to-run prompts and clear next steps (refine prompt, build workflow, or save a character profile).
Best-suited to Claude Code / session-scoped ComfyUI agents and other assistant runtimes that can run conversational prompt engineering and output structured prompts for downstream generation engines (SDXL, SD1.5, FLUX, Wan/video).
A well-crafted conversational skill that guides users through a structured interview to produce model-specific image/video prompts for ComfyUI. The SKILL.md is thorough with clear triggers, branching logic by creation type, model selection rules, and output format templates. No scripts are bundled — it's purely prompt-driven. Clean frontmatter, good separation of concerns, and specific decision rules make it easy for an agent to follow.
No security concerns — no scripts, no network calls, no shell commands. The skill is entirely instructional content for guiding agent behavior. Architecture is solid with clear frontmatter, well-structured sections, and progressive disclosure. Usefulness is moderate: niche audience (ComfyUI users) but solves a real workflow problem well.
Seedance Prompt — Short
Build, validate, and compress short-form Seedance 2.0 prompts (30–100 words) using a layered compression engine and @Tag delegation for quad-modal (T2V/I2V/V2V/
Prompt Engineering Patterns
A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat
Runway Prod Checklist
Production checklist and SDK patterns for integrating Runway (AI video/image generation) into production workflows.
Filtrix Video Gen (MCP)
Submit and manage text- or image-to-video generation jobs via Filtrix's Remote MCP API, including polling and downloading completed videos.
Copilot Instructions Blueprint Generator
Generates a technology-agnostic blueprint for creating copilot-instructions.md files that align Copilot output with a project's exact architecture, versions, an
MUAPI Photo Pack Generator (Identity-Lock)
Generate themed photo packs from a single reference image while preserving the exact facial identity and enforcing identity-lock guardrails.
Codex Image — OAuth Image Generation
Generate images via the Codex CLI using OAuth (no API key). Handles argument parsing, save paths, and error messages for gpt-image-2 generation.
ListenHub — Podcast / TTS / Explainer
Create podcasts, explainer videos, TTS, and AI images using ListenHub scripts; run the provided shell scripts to generate, check status, and download outputs.