AI Agent Skills

Show the same prompt across several interfaces, then assemble the results into a launch reel. Supply real examples that support the capability being shown.

Condense a lesson or process into an illustrated note with a clear reading order. Choose one central idea and a small set of supporting labels.

Explain a lesson, procedure or data finding with a chalkboard composition. Use a clear hierarchy and a small set of illustrations to support one takeaway.

Turn project records into a browsable offline graph of entities and relationships. Keep the original paths available so readers can trace the supporting evidence.

Combine paper tones, warm collage and large headlines into an editorial presentation. Choose photographs and supporting text for a consistent visual story.

CreatorMotion · Opposing Side Labels is a video workflow available on Skillry. Its source catalog highlights Create Broll Animation · Minimalist · Editorial · Typographic. Compare the public examples with your brief before choosing this skill.

Free Chinese and Latin font assets for covers, image typography and video titles. 34 entries with source and license records. A supporting design resource, not an installable Agent Skill.

This is the official implementation of Multi-Agent PPO (MAPPO).

Trading Environment(OpenAI Gym) + PPO(TensorForce)

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (ad…

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SA…

Build a reproducible local rough-cut workflow for talking-head or narrated screen-recording videos with transcript review gates.

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