#llm

Grokkable Output

Agent skill that makes AI replies parseable in one pass — verdict first, prose over fake structure, claims that trace to evidence

Humanizer RU

Русский Humanizer: Agent Skill и линтер читаемости для LLM-агентов

Dart SDK Skills

Agent skills for Dart & Flutter SDK versioning, language features, widget migrations, and minSdk lookups

HTML Artifact Kit

A model-agnostic design kit and Agent Skill for polished, portable, self-contained HTML artifacts.

Agent Orchestra

一个可移植的多 agent 协作 skill，适用于 3 个及以上 AI agent。它能够自动识别 agent 的工具、权限和专长，分配协调者、实现者、验证者等角色；通过...

The llm-anthropic plugin version 0.27 updates compatibility with Anthropic's v1.0.0 Python library, which changes its underlying HTTP client...

Unlazy

Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget...

Kamaaina

Kamaʻāina — an AI Development Kit for local-first AI on consumer hardware

Ghostwriter

Draft messages that read as you wrote them, not as a model did.

Prompt Studio

here you can create prompts for your own purpose on point which need mimimal changes