yuxin-kang/yuxin-agent-skills

A reusable agent skill for turning Play-tested reinforcement learning runs into factual, reproducible, baseline-aware experiment records.

2Stars on the repository
4Mods indexed here, across every type
7d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

experiment-record

01

yuxin-kang/yuxin-agent-skills

Skill Codex

Record or update a Leo Lab experiment after the user has Play-tested a policy and supplied the actual result plus a run, job, checkpoint, W&B, or experiment identifier. Always compare the current experiment with its prior baseline, including reward/training parameters, environment I/O, and network architecture, then…

not rated 2 7d ago A 98 tokens

yuxin-kang/yuxin-agent-skills

Skill Codex

Find, screen, deduplicate, and summarize newly released robotics papers for daily or ad-hoc research digests. Use when asked for the latest robotics, humanoid, legged locomotion, loco-manipulation, robot learning, perception, sim-to-real, whole-body control, or safety papers; when maintaining a recurring paper watch…

not rated 2 7d ago A 106 tokens

pocketmux-send-file

03

yuxin-kang/yuxin-agent-skills

Skill Codex

Send an image or supported file from the Pocketmux host computer to a connected Pocketmux phone app through the authenticated owner-only outbox. Use when the user asks to send, push, or deliver a local photo, video, PDF, Markdown, text, data, or log file to their mobile app.

not rated 2 7d ago A 67 tokens

image-to-drawio

04

yuxin-kang/yuxin-agent-skills

Skill Claude CodeCodex

An image-to-diagram reconstruction tool for turning PNG or JPG research, architecture, and flowchart images into editable draw.io diagrams. draw.io is a diagram editor.

not rated 2 7d ago A 84 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: