Turn content into reading-friendly slide deck images with style presets and optional PPTX/PDF merge.
スキル
デザイン / メディアのスキル — 3 ページ目
AI エージェント向けのデザイン / メディアスキル。すべて SKILL.md 全文が付いているので、追加する前に何をするスキルなのかを正確に確認できます。
Generate AI cinematic videos — narrative shorts, brand films, music videos — from a single prompt.
Generate images from prompts across OpenAI, Azure, Google, DashScope, Seedream, Jimeng and more, with batch mode.
Turn video URLs or files into structured JSON: transcript, description, summary, speakers, and Q&A via Gemini.
Generate images, videos, and audio via Lovart AI's design agent from natural language prompts, with project and conversation management built in.
Generate Instagram and TikTok videos, carousels, and posts from a single prompt.
Diagnoses the constrained funnel stage, picks the compounding loop, and sizes the channel and experiment program.
Generate research-backed pitch decks, business presentations, and educational slides as PDF or editable PPTX.
Diagnoses GraphQL bugs and hardens schemas, resolvers, and clients against N+1, null propagation, DoS, and cache staleness.
Scored on-page SEO audit of one page with prioritized fixes.
Lore-grounded answers and mythic voice for the Eternal Haven Chronicles universe, drawn from bundled canonical text.
Turn Markdown into WeChat Official Account HTML, covers, infographics, and image posts via the md2wechat CLI.
Files and audits incoming invoices — OCR, duplicate checks, VAT splits, and a searchable local archive.
Route CloudBase scenarios to the right child skill and enforce the prep-then-implement-then-review workflow.
Designs, tracks, and repairs daily habits with completion rates, streaks, and restart plans.
Converts text into speech-ready output for any TTS engine with normalization, prosody, and voice preferences.
Designs, runs, and closes meetings so each one ends with a named decision, owners, and dates.
Generate images via Model Studio DashScope SDK using normalized Qwen Image models
Generate videos from prompts, images, videos, audio, or first/last frames via a CLI for Seedance 2.0.
Create YouTube videos, Shorts, thumbnails, and scripts through the CellCog SDK.
Manage an Instagram account via the Graph API — view profile, publish posts and Reels, and handle comments.
Route image, video, and audio requests to the right dlazy CLI model based on intent.
Generate clickable HTML prototypes from a text prompt — landing pages, mobile apps, dashboards, and wireframes.
Generate and edit images, video, and music through the VAP Media API from inside an agent workflow.