Writes copy-ready image prompts with the right model, quality level, and aspect ratio for your request.
Turns Claude into a motion designer that builds Remotion (React) videos with strict craft rules and a mandatory render-and-inspect verification loop.
Takes a video plus an SRT and either burns the subtitles into the pixels with libass or soft-muxes a togglable track, and can mix a dub over the original audio in a single ffmpeg pass.
Turns Chinese text into two-host conversational podcast audio using Volcengine's Podcast AI model.
Analyzes an article, script, or topic and auto-generates matching illustrations, slide infographics, and cover images via Gemini, Excalidraw, and Mermaid.
Generates a complete 30-40s vertical "A vs B" explainer video — 12-line script, Vietnamese TTS voiceover, and HyperFrames MP4 render.
Generates a complete 30-40s vertical "X vs Y" explainer video with a 12-line script, Vietnamese TTS voiceover, and HyperFrames rendering.
Turns a video into a structured understanding index — scenes, ASR transcript, per-scene VLM observations, silence windows, a fused timeline and a writing brief.
Turns a timestamped narration.json into per-segment TTS audio that fits each time window, plus tts_meta.json placement metadata.
Final-stage skill that lays narration audio over the source video, ducks the original sound, generates and burns subtitles, and normalizes loudness into a deliverable recap.
Turns a single baseline character image into an identity-locked, transparent 14-frame game animation sequence.
A Python/Pillow skill that crops an image to 50% from the center and rotates it 90 degrees clockwise in one command.
Asks 3-4 targeted questions about your video needs, then recommends the best 1-3 of 16 AI video models with clear reasoning.
Converts an AI video prompt from one model's writing style into the target model's best-practice format (Sora, Kling, Veo, Wan, Hailuo and more).
Generates Kling 3.0 (Kuaishou) video prompts by auto-selecting one of three writing formulas based on your request.
Analyzes videos, frame sequences, spritesheets and Spine assets to build a reusable 2D motion knowledge base inside your project.
Audits and rescales a 2D character/prop baseline image with transparent action margin before motion generation.
Diagnoses 12 common Seedance 2.0 video generation failures and rewrites the prompt to fix them.
Writes compact 30–55 word prompts that follow HappyHorse 1.0's strict rules, including native audio-activation phrases.
Art-direction skill for achieving clean anime cel-shaded looks in Blender.