Reusable AI skills and capabilities for agent workflows
baka3k
Lightweight, token-efficient software engineering skills for coding agents. Works with Claude Code, OpenCode, Qwen, Copilot, Cursor and more.
...moreshying
Agent session manager — discover, bookmark, and organize AI coding sessions
ferdragonflowio
Cross-project LLM agent runtime for Dragonflow — loads agent rows from a per-project `agents` Supabase table and invokes Anthropic / Google / OpenAI models against the v0.1+ invocation contract.
...morea2ui-team
A2UI Core Library
gaomar
Gemini Pro APIを使ってプロンプトから画像解析してくれます。
GitHub Actions
A professional Claude Code Skill that transforms simple instructions into production-ready prompts. Based on the CLARITY framework, supports 61 prompt frameworks, and provides quality validation with multi-version output.
...moremagikmaker
Vector class for 2D, 3D and multi dimensional vector calculations
jyswee
Appoiint CLI — schedule meetings, create rooms, join video calls. Agent-first meeting platform.
vlapky
Tiny browser API for the Pocket TTS ONNX model: streaming neural text-to-speech with voice cloning, running entirely client-side in a Web Worker.
...moretorquefi
Shared TypeScript types for Torque Platform API v1 (Intelligence, Assistant, errors)
marcolanaro
PERT - Program evaluation and review technique
kelvinzero
Amazon SageMaker Feature Store data plane API for feature operations.
saadaoui
A function-oriented architecture built on top of Redux Toolkit for simplifying and automating application development.
samzong
The proof layer for prototypes.
GitHub Actions
TypeScript SDK for the Chidori agent framework — HTTP client plus agent authoring types.
edwinfermin
Install and orchestrate a controlled multi-agent harness on top of an existing project, for Claude Code or opencode.
ihainan
Minimal Claude Code status line: model-aware context %, cost, git status. No pets.
shubham.takankhar
OLAP — orchestrated loop architect/worker CLI with terminal UI
GitHub Actions
Discord bot bridge for a self-hosted opencode instance
sarfarajey
Streaming Vertex AI / Gemini client for edge runtimes — SSE token + tool-call events, retry, context caching. No google-cloud SDK.
...moredrewbpdx
EddyDesk admin SDK — programmatic access to QA intelligence, reports, tests, and analytics
jasonz93
[](https://npm.taobao.org/package/ngconf) [](https://travis-ci.org/jasonz93/ngconf) [![Coverage Status](https://coveralls.
...morekelvinzero
AWS RoboMaker API operations documentation.
mz1
Execution layer that hides LLM tail latency with hedging, speculation, prefetch, and cancellation.