lore-field-repair
Guided workflow for diagnosing and fixing harness bugs in deployed instances
浏览和安装 Killer-Skills 目录中的数千个 AI Agent 技能。支持 Claude Code、Windsurf、Cursor 等。
这个技能目录把可安装的 AI Agent 技能集中在一起,方便你按搜索、分类、主题和官方来源快速筛选,并直接安装到 Claude Code、Cursor、Windsurf 等环境。
Guided workflow for diagnosing and fixing harness bugs in deployed instances
TypeScript framework for building AI agents — multi-provider (Anthropic, OpenAI, Google), tool calling, permissions, hooks, streaming, and CLI coding assistant
本地化技能摘要: Tina4 Python # Tina4 App Developer Guide You are an expert Tina4 application developer. It covers framework, jinja2, migrations workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
The bump AI agent skill automates version management, updating documentation and creating GitHub releases, helping developers to efficiently manage their codebase and collaborate with their team.
Infrastructure deployment for VPS, Docker, and cloud platforms. Activates for deploy, setup server, docker, coolify, VPS, SSH, nginx, production, hosting requests.
This AI agent skill enables practical workflows for training and inference on AI models remotely over SSH, leveraging GPU acceleration for faster performance.
本地化技能摘要: An adaptation of caveman — short common words, trust context, say just enough, be laconic. It covers ai-assistant, anthropic, brevity workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
Bud AI Foundry - A comprehensive inference stack for compound AI deployment, optimization and scaling. Bud Stack provides intelligent infrastructure automation, performance optimization, and seamless model deployment across multi-cloud/multi-hardware environments.
Tiny Framework for accessibility and sustainability, not only for MODX or Kirby CMS.
Backend budget tracking patterns for AI generation. Awareness-based tracking (not blocking), tool timeouts, per-tool rate limits, token estimates, context window management, truncation strategies, search quality detection. Triggers on budget, tool timeout, rate limit, token estimate, truncation, context window, search quality, diminishing returns.
Decide whether terminal remains in Core and implement either hidden background execution or polished advanced terminal mode with explicit UX and reliability standards.
Prompt-as-Code for Enterprise AI. Standardize, audit, and deploy instructions across any AI coding assistant.