GitHub
starship
Cross-shell prompt configuration and installation guide.
☆ 0查看技能
devops llm ai AI 技能
发现 devops llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
分类目录: devops llm ai
devops llm ai 清除筛选
全部技能
GitHub
scribe-sys
Generatore di System Prompt e Istruzioni AI (Archetipo OCC).
☆ 0查看技能
GitHub
grading
Grade student submissions with intellectual rigor and pedagogical depth. Produce scores, teach clear thinking and effective writing, and provide actionable feedback.
☆ 0查看技能
GitHub
handover-session
AIモデル間や作業セッション間での円滑な引継ぎのためのドキュメント・プロンプトを作成する
☆ 0查看技能
GitHub
lessons-extractor
Extracts lessons learned from Claude Code session logs into organized markdown and JSONL files
☆ 0查看技能
GitHub
setup-ralph
Setup the Ralph autonomous AI coding loop - ships features while you sleep
☆ 0查看技能
GitHub
hybrid-architecture
LUTAGU AI 混合架構與模型路由策略。 當用戶詢問 "Hybrid Engine"、"AI 架構"、"模型選擇"、 "MiniMax"、"Gemini"、"Dify" 或 "決策邏輯" 時觸發此 Skill。
☆ 0查看技能
GitHub
ask-user
Pattern for effectively interacting with users to gather information or get decisions. Use when you need user input.
☆ 0查看技能
GitHub
agent-builder
Provides guidance for building and deploying Claude Agent SDK agents and Claude Code Skills. Use when designing agents (dev or non-dev), choosing architectures/tools, or deploying to a VPS.
☆ 0查看技能
GitHub
learning-faq-generator
Generate comprehensive FAQs from common learner questions, analytics, discussion forums, and support tickets. Use for self-service support. Activates on "FAQ", "common questions", "help documentation", or "stud...
☆ 0查看技能
GitHub
prompt-template-designer
Design reusable prompt templates that encode domain-specific patterns for recurring AI tasks. Use when you've executed similar prompts 2+ times and need to capture the pattern as reusable intelligence. NOT for...
☆ 0查看技能
GitHub
ai-runtime-toolkit
AI Runtime工具装备系统，支持8个内部专业工具和10+个外部CLI工具的整合管理，提供工具发现、执行和配置功能，遵循整合优于创造的设计理念
☆ 0查看技能
GitHub
context-engineering-2026
Optimización de prompts mediante Primacy/Recency, higiene de contexto y compresión de tokens.
☆ 0查看技能
GitHub
agent-architecture-patterns
Core architectural patterns for local AI agents (Reflection, Planning, Tool Use, Multi-Agent, Memory).
☆ 0查看技能
GitHub
conversational-refinement
Pattern for building conversational refinement systems (like Genesis). Use when a module needs to gather evidence through natural dialogue to resolve uncertainties or incomplete data.
☆ 0查看技能
GitHub
start-tts
Start the TTS server in HTTP mode for audio generation
☆ 0查看技能
GitHub
create-prompt
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
☆ 0查看技能
GitHub
creating-skills
Claude Agent Skillsを作成・改善するための支援ツール。ベストプラクティスに従ったSKILL.mdの構造化、段階的情報開示、テスト、反復改善をガイド。skillの新規作成や既存skillの改善が必要な時に使用。
☆ 0查看技能
GitHub
exa
Neural web search and code context via Exa AI API. Requires EXA_API_KEY. Use for finding documentation, code examples, research papers, or company info.
☆ 0查看技能
GitHub
ascii-visualizer
Creates beautiful ASCII art visualizations for plans, architectures, workflows, and data. This skill should be used when explaining system architecture, creating implementation plans, showing workflows, visuali...
☆ 0查看技能
GitHub
voice-reply
Generate voice replies using OpenAI TTS API and send audio responses.
☆ 0查看技能
GitHub
building-mcp-servers
Guides creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or...
☆ 0查看技能
GitHub
noisett
AI Brand Asset Generator with 25 commands for image generation, LoRA training, quality pipeline, and history management. Built with AFD principles.
☆ 0查看技能
GitHub
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies. Dispatches multiple Claude agents to investigate and fix independent problems concurrently.
☆ 0查看技能
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。