Agent Skills · Design & Media
Curated skills for Claude, Cursor and other AI agents. Copy one prompt to install.
Extracts scripts into character asset tables, art settings, and GPT-image 2 prompts.
Use the Chibird Mancang API to generate images and videos, with parameter overrides, polling, history, and point consumption hints.
Convert Chinese or natural-language requests into paste-ready English image prompts for ChatGPT's web UI, covering generation, editing, multi-image references, and exact text without performing image generation.
Transcribe audio and video files with FunASR using SenseVoice or Nano models, with support for common audio formats.
A local CLI for Dreamina image and video generation, including credit checks, async submission, result queries, and task history review.
An AI-guided workflow for Chinese video dubbing and subtitles that configures iFlytek or edge-tts, splits audio, generates SRT, and composes the final video.
After consent and paid clone activation, freeze a reusable voice_id, then synthesize, poll, and deliver labeled series episodes with real duration and billing.
Build a repeatable dynamic sticker pipeline for IP characters, covering briefs, benchmarking, keyframes, GIF compositing, transparency QA, and submission packaging.
Generate printable bead mosaic patterns from a photo or text, with style setup, pixel image generation, color quantization, and BOM export.
Turns short scene ideas or existing prompts into coherent cinematic xianxia environments with locked aspect ratios, scale, color, light, and route controls.
Generates vertical brand posters for Chinese holidays and solar terms via the Doubao SeedImage API, with persisted API key and brand settings.
Generate and validate JianYing drafts from storyboard JSON with narrated commentary, original-sound preservation, timing checks, and draft inspection.