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。
Transforms an academic paper into deep, multi-layered understanding. Use when asked to explain a paper, break down a research paper, understand an arXiv paper, or build intuition for a technical concept from a...
Generates a rigorous experiment design given a hypothesis. Use when asked to design experiments, plan experiments, create an experimental setup, or figure out how to test a research hypothesis. Covers controls,...
Guides you through implementing a research paper step-by-step from scratch. Use when asked to implement a paper, code up a paper, reproduce research results, or build a model from a paper. Focuses on building u...
Create, configure, and deploy Hugging Face Spaces for showcasing ML models. Supports Gradio, Streamlit, and Docker SDKs with templates for common use cases like chat interfaces, image generation, and model comp...
Generates images using Google Gemini 3 Pro API. Use when asked to create, generate, or design images for slides, presentations, or visual content.
Use when starting any conversation - establishes how to find and use beadpowers skills
Integrate and embed OpenAI ChatKit UI into TypeScript/JavaScript frontends (Next.js, React, or vanilla) using either hosted workflows or a custom backend (e.g. Python with the Agents SDK). Use this Skill whenev...
Design, implement, and debug a custom ChatKit backend in Python that powers the ChatKit UI without Agent Builder, using the OpenAI Agents SDK (and optionally Gemini via an OpenAI-compatible endpoint). Use this...
Build AI agents with OpenAI Agents SDK + Model Context Protocol (MCP) for tool orchestration. Supports multi-provider backends (OpenAI, Gemini, Groq, OpenRouter) with MCPServerStdio. Use this skill for conversa...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing one) that extends the agent's abilities with specialized knowledge, workflows, or tool...
Token-efficient documentation search using Serena Document Index. 90%+ token savings vs reading full files. Use BEFORE reading README.md or docs/ files. Triggers on architecture questions, pattern lookups, and...
Token-efficient codebase exploration using MCP servers (Serena, Context7, JetBrains, Claude-mem). Reduces token usage by 80-90% through structured queries. Use ALWAYS before reading files to minimize context wi...
Token-efficient context gathering and synthesis from multiple sources (memory, docs, web). Orchestrates MCP tools to build comprehensive context before analysis or interviews. Use when starting discovery, resea...
Save notes, ideas, and content directly to Notion database. Use when Claude needs to persist conversation insights, trading notes, research findings, or any content to Notion for later reference. Triggers on ph...
Use when an agent encounters a blocking decision or when proceeding without user input could lead to wasted work - helps Claude determine when to block and request user input versus making reasonable assumption...
You MUST use this skill when the user asks you to setup a claude code project. You should also suggest it if there is no CLAUDE.md or when starting work on an empty codebase.
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
This skill should be used when the user asks to "coordinate document writing", "manage doc writers", "create a design document with multiple writers", "orchestrate documentation", "delegate doc sections", "cos...
This skill should be used when the user asks about "coordinate coding agents", "orchestrate agent team", "manage multiple agents", "vibekanban workflow", "task delegation to agents", "agent swarm coordination",...
Repository orientation and which Codex skills to use for each area (go-lcpd, protocol spec, docs, openai-serve, ExecPlans).
Develop apps/openai-serve (Go). Keep OpenAI gateway behavior correct and avoid logging prompts/outputs.
Contract-based MapReduce worker for executing a task (may be broad) under optional hint_paths, producing a narrative report. Use when an orchestrator invokes a map worker (llm_query role) many times in parallel...
協調多個 AI 模型（ChatGPT、Gemini、Codex、QWEN、Claude）進行三角驗證，確保「Specification == Program == Test」一致性。過濾假警報後輸出報告，大幅減少人工介入時間。
Creates PhD-grade expert agents when no suitable agent exists. Produces highly specialized agents with deep domain expertise.
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。