Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.

All skills

38,472 Skills

Search uses this published catalog; rankings and counts are snapshots.

Finance

Crypto Rl

sadighian

Deep Reinforcement Learning toolkit: record and replay cryptocurrency limit order book data & train a DDQN agent

Price unconfirmed
Marketing & sales

ebay-product-data

scavio-ai

eBay product data API: search live listings with price, condition, bids, units sold, watchers, shipping and seller feedback, read one listing in full with item specifics, shipping, returns and auction state, and pull a seller's feedback score, items sold and location. 3 endpoints

Price unconfirmed
Design & UI

Ui

stackzero-labs

Collection of components to build e-commerce sites and commerce apps. Built for React, Next.js, Tailwind CSS and shadcn/ui.

Price unconfirmed
Development

gui

svd-ai-lab

Cross-driver GUI actuation for CAE solvers running under sim-cli. Use to click buttons, fill fields, dismiss dialogs, and capture window screenshots against GUI-capable driver windows through `sim exec`.

Price unconfirmed
Education

Easegen Front

taoofagi

Easegen is an open-source digital human course creation platform offering comprehensive solutions from course production and video management to intelligent quiz generation.Easegen 是一个开源的数字人课程制作平台,提供从课程制作、视频管理到智能出题的全方位解决方案。

Price unconfirmed
Video & audio

bggg-tiktok-capcut

binggandata

通用 CapCut 草稿生成与 AI 视频检查 skill。用于把本地 AI 视频套用现有 CapCut 草稿模板, 生成可在 CapCut 首页显示并可编辑的新草稿;也用于提取模板样式、验证草稿结构、抽帧检查 AI 痕迹、规划修复窗口和做本地 RIFE 补帧。

Price unconfirmed
Video & audio

tiktok-gemini-video-workflow

binggandata

将飞书多维表格中的产品图和爆款视频自动处理为 TikTok 带货视频:优先处理人工标记的返工任务,再认领新任务,拆解画面/文字/声音钩子,生成1–2段脚本、九宫格分镜和视频提示词,按单个或多个已授权Google账号路由Gemini/Flow额度,完成生成、续接、下载、消除可见星形水印、检查并后期补齐必要文字钩子,最后回传待验收成品。用于用户提到爆款复刻、TikTok带货视频、Gemini/Flow生视频、多Google账号、Chrome账号切换、额度轮询与日志、屏幕文字钩子、字幕缺失或乱码、人工验收返工、尾帧续接、九宫格分镜、视频去水印或飞书任务轮询时。

Price unconfirmed
AI & knowledge

GroundingLMM

mbzuai-oryx

[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.

Price unconfirmed
Design & UI

api-error-handling

secondsky

Implements standardized API error responses with proper status codes, logging, and user-friendly messages. Use when building production APIs, implementing error recovery patterns, or integrating error monitoring services.

Price unconfirmed
Development

Tuya Home Assistant

tuya

Home Assistant integration for controlling Powered by Tuya (PBT) devices using Tuya Open API, maintained by the Home Assistant Community and Tuya Developer Team.

Price unconfirmed
Hardware & IoT

3D Mem

UMass-Embodied-AGI

[CVPR 2025] Source codes for the paper "3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning"

Price unconfirmed
Documents

Image Text Localization Recognition

whitelok

A general list of resources to image text localization and recognition 场景文本位置感知与识别的论文资源与实现合集 シーンテキストの位置認識と識別のための論文リソースの要約

Price unconfirmed
Finance

fda-catalyst-analysis

agentii-ai

Dated FDA catalyst calendar (PDUFA target dates, AdCom meetings, device decisions, trial readouts, earnings) with AdCom-style scrutiny outcome framing and historical-case grounding. The FDA decision is the strongest stock catalyst in med.medicines_biotech — use this skill to enum

Price unconfirmed

Catalog captured:2026-11-21