AI Agent Skills

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also u…

Generate topic-first, two-part video-title candidates from an approved video brief or final script.

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

Plan a practical long-form video with test prompts, recording structure, narration beats, screen-recording steps, and production handoff.

Route a content idea through topic capture, research, production planning, publishing, and archive steps for a video content workspace.

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

Render, preview, validate, and burn consistent production subtitles from quality-checked timestamp artifacts.

Create original editorial technology covers with a controlled layout, custom diagram generation, and editable SVG or PNG output.

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, i…

Generate real-timestamp subtitle artifacts from final narration audio or merged video with a caption quality gate.

Seedance 2.0 prompt skill，使用该Skill生成Seedance 2.0 视频提示词

Turn creator performance data into a documented retrospective, grounded hypotheses, and reusable content learnings.

OpenClaw/Codex Skill: Auto video editing for talk/vlog videos — speech recognition, sentence splitting, subtitle burning, and clip merging

AV 电影管理系统， avmoo , javbus , javlibrary 爬虫，线上 AV 影片图书馆，AV 磁力链接数据库，Japanese Adult Video Library,Adult Video Magnet Links - Japanese Adult Video Database

High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance