Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
10451 jax-best-practices mindrally/skills
JAX Best Practices You are an expert in JAX for high-performance numerical computing and machine learning. Core Principles Follow functional programming patterns Use immutability and pure functions Leverage JAX transformations effectively Optimize for JIT compilation Key Transformations jax.jit Use for just-in-time compilation to optimize performance Avoid side effects in jitted functions Use static_argnums for compile-time constants jax.vmap Vectorize operations over batch dimensions Avoid ex...
 74
10452 csharp-developer 404kidwiz/claude-supercode-skills
C Developer Senior C developer with mastery of .NET 8+ and Microsoft ecosystem. Specializes in high-performance web APIs, cloud-native solutions, and modern C language features. Role Definition You are a senior C developer with 10+ years of .NET experience. You specialize in ASP.NET Core, Blazor, Entity Framework Core, and modern C 12 features. You build scalable, type-safe applications with clean architecture patterns and focus on performance optimization. When to Use This Skill Building AS...
 74
10453 memories proompteng/lab
Use the memories helpers to store and retrieve embeddings in a consistent way. Ensure embedding dimension matches the DB schema. Save ``` bun run --filter memories save-memory --task-name bumba-enrich-repo --content "Enrichment facts for services/bumba" --summary "Bumba repo facts" --tags "bumba,enrich" ``` Retrieve ``` bun run --filter memories retrieve-memory --query "enrichFile workflow" --limit 5 ``` Environment - `OPENAI_API_BASE_URL` / `OPENAI_API_BASE` - `OPENAI_EM...
 74
10454 minio vm0-ai/vm0-skills
MinIO Object Storage Use the MinIO API via mc (MinIO Client) or curl to manage S3-compatible object storage for file uploads, downloads, and bucket operations. Official docs: https://min.io/docs/minio/linux/reference/minio-mc.html When to Use Use this skill when you need to: Upload/download files to S3-compatible storage Manage buckets (create, list, delete) Generate pre-signed URLs for temporary file access List and search objects in storage Mirror/sync directories between local and remote...
 74
10455 clippy-advanced laurigates/claude-plugins
Advanced Clippy configuration for comprehensive Rust linting, including custom rules, lint categories, disallowed methods, and IDE integration. Installation ``` Clippy is included with rustup rustup component add clippy Verify installation cargo clippy --version Update clippy with rust toolchain rustup update ``` Basic Usage ``` Run clippy on current project cargo clippy Run on all targets (lib, bins, tests, examples, benches) cargo clippy --all-targets Run with all features ena...
 74
10456 tavily-search jacky1n7/openclaw-skill-tavily-search
Tavily Search Web search optimized for AI agents using Tavily API. Usage ./scripts/search "your search query" Scripts Script Usage scripts/search <query> Search the web scripts/search "latest AI news" --format json JSON output Environment export TAVILY_API_KEY = "your-api-key" Get API key: https://tavily.com/ Example ./scripts/search "Claude AI latest features" Returns: Search results optimized for AI context
 74
10457 retention-engine shipshitdev/library
Retention Engine - Customer Lifetime Value Maximizer Overview You are a retention strategist specializing in Alex Hormozi's retention and ascension frameworks. You help indie founders stop the bleeding from churn, maximize customer lifetime value (LTV), and build recurring revenue machines. Your job is to execute retention systems—not just advise—by diagnosing churn causes and designing complete ascension paths. Hormozi's Core Principle: "Acquiring customers is expensive. Keeping them is profi...
 74
10458 medusa alinaqi/claude-bootstrap
*Load with: base.md + typescript.md* For building headless e-commerce with Medusa - open-source, Node.js native, fully customizable. Sources: [Medusa Docs](https://docs.medusajs.com) | [API Reference](https://docs.medusajs.com/api/store) | [GitHub](https://github.com/medusajs/medusa) Why Medusa | Open Source | Self-host, no vendor lock-in, MIT license | Node.js Native | TypeScript, familiar stack, easy to customize | Headless | Any frontend (Next.js, Remix, mobile) | Modular | Use...
 74
10459 shiny-bslib-theming posit-dev/skills
Theming Shiny Apps with bslib Customize Shiny app appearance using bslib's Bootstrap 5 theming system. From quick Bootswatch themes to advanced Sass customization and dynamic color mode switching. Quick Start "shiny" preset (recommended starting point): page_sidebar ( theme = bs_theme ( ) , "shiny" preset by default — polished, not plain Bootstrap ... ) Bootswatch theme (for a different visual style): page_sidebar ( theme = bs_theme ( preset = "zephyr" ) , or "cosmo", "minty", "darkly", etc. ....
 74
10460 pexels-media troykelly/claude-skills
Source high-quality, royalty-free images and videos from Pexels for design work, placeholders, or content creation. Prerequisites This skill requires the `PEXELS_API_KEY` environment variable to be set. ``` Check if API key is available echo $PEXELS_API_KEY ``` If not set, obtain a free API key from [Pexels API](https://www.pexels.com/api/). API Base URLs - Photos: `https://api.pexels.com/v1/` - Videos: `https://api.pexels.com/videos/` Authentication All requests require the Author...
 74
10461 jscodeshift pproenca/dot-skills
Facebook/Meta jscodeshift Best Practices Comprehensive best practices guide for jscodeshift codemod development, designed for AI agents and LLMs. Contains 40 rules across 8 categories, prioritized by impact from critical (parser configuration, AST traversal) to incremental (advanced patterns). Each rule includes detailed explanations, real-world examples, and specific impact metrics. When to Apply Reference these guidelines when: Writing new jscodeshift codemods for code migrations Debugging...
 74
10462 ffuf-claude-skill sickn33/antigravity-awesome-skills
Ffuf Claude Skill Overview Web fuzzing with ffuf When to Use This Skill Use this skill when you need to work with web fuzzing with ffuf. Instructions This skill provides guidance and patterns for web fuzzing with ffuf. For more information, see the source repository .
 74
10463 call-summary anthropics/knowledge-work-plugins
/call-summary If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md . Process call notes or a transcript to extract action items, draft follow-up communications, and update records. Usage /call-summary <notes or transcript> Process these call notes: $ARGUMENTS If a file is referenced: @$1 How It Works ┌─────────────────────────────────────────────────────────────────┐ │ CALL SUMMARY │ ├────────────────...
 74
10464 artifacts-builder shajith003/awesome-claude-skills
Artifacts Builder To build powerful frontend claude.ai artifacts, follow these steps: Initialize the frontend repo using scripts/init-artifact.sh Develop your artifact by editing the generated code Bundle all code into a single HTML file using scripts/bundle-artifact.sh Display artifact to user (Optional) Test the artifact Stack : React 18 + TypeScript + Vite + Parcel (bundling) + Tailwind CSS + shadcn/ui Design & Style Guidelines VERY IMPORTANT: To avoid what is often referred to as "AI slop", ...
 74
10465 graalvm mindrally/skills
GraalVM You are an expert in Java programming, GraalVM native builds, Quarkus framework, Micronaut framework, Jakarta EE, MicroProfile, Vert.x for event-driven applications, Maven, JUnit, and related Java technologies. Code Style and Structure Write clean, efficient, and well-documented Java code optimized for GraalVM native compilation Follow framework-specific conventions (Quarkus, Micronaut, Spring Native) while ensuring GraalVM compatibility Use descriptive method and variable names follow...
 74
10466 forgotten-elements-reminder wordflowlab/novel-writer-skills
遗忘元素提醒器 核心功能 防止长篇小说常见问题： 角色突然消失（"配角A去哪了？"） 情节线被遗忘（"那个伏笔后来呢？"） 伏笔没回收（"前文说的宝藏呢？"） 解决方案：后台监控，主动提醒已经很久未出现的元素。 监控内容 1. 角色出场频率 监控：character-state.json中的所有角色 阈值：10章未出现 提醒示例： ⚠️ 角色提醒： "配角李明"已经10章未出现（上次：第5章） - 是否应该安排他再次出场？ - 还是这个角色的故事已结束？ 2. 情节线进度 监控：plot-tracker.json中的活跃情节线 阈值：12章无进展 提醒示例： ⚠️ 情节线提醒： "寻找父亲仇人"情节线已12章无进展 - 上次推进：第8章 - 当前状态：pending - 建议：安排相关情节或标记为暂停 3. 伏笔回收 监控：在前文埋下的重要伏笔 阈值：20章未回收 提醒示例： ⚠️ 伏笔提醒： 第3章提到"神秘盒子"，至今未揭秘（已过23章） - 读者可能已经忘记 - 建议：尽快回收或在对话中提及 提醒时机 写作前提醒 执行 `/write` 时，如果检测到遗忘元素...
 74
10467 quickbooks membranedev/application-skills
Quickbooks Quickbooks is a popular accounting software used by small businesses to manage their finances. It helps with tasks like invoicing, payroll, and tracking expenses. Many small business owners and accountants use Quickbooks to keep their books in order. Official docs: https://developer.intuit.com/app/developer/qbo/docs/develop/overview Quickbooks Overview Account Bill Bill Payment Company Info Customer Invoice Payment Product Purchase Sales Receipt Tax Agency Transfer Working with Quickb...
 74
10468 todo-management adaptationio/skrillz
todo-management provides systematic task tracking throughout skill development. It manages task states, provides real-time progress updates, identifies blockers, and ensures momentum is maintained from start to finish. Purpose: Track progress systematically, maintain visibility into work status, identify issues early, and ensure completion. Value: Prevents work from being forgotten, provides clear progress visibility, enables course correction, and maintains momentum through completion. When ...
 74
10469 skills-security-check toolsai/skills-security-check
Skill: Skills-Security-Check CRITICAL INSTRUCTION FOR AI AGENTS: You are NOT just a command-runner. You are the Lead Security Analyst . This tool provides the data , but YOU provide the intelligence . ⚡️ The 3-Step Agentic Workflow (MANDATORY) You MUST follow this loop whenever using this skill: Step 1: Run the Scanner (Data Collection) Execute the scanner to generate the raw data and "Audit Prompts". python3 scripts/scan_skills.py --root /path/to/target/projects This command will generate *_aud...
 74
10470 research-expert cin12211/orca-q
Research Expert You are a specialized research expert designed for efficient, focused information gathering with structured output. Core Process 1. Task Analysis & Mode Detection Recognize Task Mode from Instructions Detect the expected research mode from task description keywords: QUICK VERIFICATION MODE (Keywords: "verify", "confirm", "quick check", "single fact") Effort: 3-5 tool calls maximum Focus: Find authoritative confirmation Depth: Surface-level, fact-checking only Output: Brief confir...
 74
10471 mf-integrate module-federation/core
MF Scaffold — Add Module Federation to an Existing Project Step 1: Detect project Call the mf-context Skill (pass $ARGUMENTS ) to collect MFContext. If no bundler can be detected (no rsbuild.config , rspack.config , webpack.config , modern.config , next.config , vite.config found), this is likely a new project. Tell the user: This looks like a new project. Run the following command to scaffold a full Module Federation project: npm create module-federation@latest Then stop. If MF is already confi...
 74
10472 contract-review-pro cslawyer1985/contract-review-pro
Contract Review Pro - 专业合同审核 Skill 📋 Skill 概述 Contract Review Pro 是一个专业的合同审核辅助工具，基于《合同审核方法论体系》（整合5本专业著作）的核心理论，为律师和企业法务提供快速、标准、深入的合同审核服务。 核心功能 合同类型指引：快速查询各类合同的审核要点、风险点和检查清单 合同详细审核：对具体合同进行逐条审核，生成法律意见书和批注版合同 特色优势 ✅ 理论扎实：基于三观四步法、三维审查法等专业方法论 ✅ 风险分级：致命、重要、一般、轻微四级风险管理 ✅ 灵活配置：支持快速（5-10分钟）、标准（30-60分钟）、深度（1-2小时）三种审核模式 ✅ 专业输出：生成符合律师标准的法律意见书和批注版合同（修订模式） ✅ 场景适配：专门服务于律师快速审核和企业法务日常审核 🚀 使用方法 方式一：查询合同类型指引 当您需要了解某类合同的审核要点时： 用户：买卖合同的审核要点是什么？ Skill：[输出买卖合同的完整审核指引，包括： - 核心风险点 - 重点条款审核 - 审核检查清单] 方式二：审核具体合...
 74
10473 positioning-angles shipshitdev/library
Positioning Angles - Find Your Unique Angle Overview Act as a positioning strategist. Help users find the marketing angle that transforms "why isn't this selling" into "we can't keep up with demand." Guide them through market stage matching, mechanism discovery, angle selection, and testing. Core Principle: "One angle will outperform others 3-10x. Test, don't guess." Role: Find angles. Name mechanisms. Differentiate positioning. When This Activates This skill auto-activates when: User says...
 74
10474 distributed-llm-pretraining-torchtitan davila7/claude-code-templates
No SKILL.md available for this skill. [View on GitHub ](https://github.com/davila7/claude-code-templates)
 74
10475 document-summarizer ntaksh42/agents
Document Summarizer Skill ドキュメント要約スキルは、長文のドキュメントを効率的に要約し、重要なポイントを抽出します。 概要 このスキルを使用すると、技術文書、ビジネスレポート、学術論文、コードドキュメントなど、様々な種類のドキュメントを自動的に要約できます。要約レベルや出力形式を柔軟に指定可能です。 主な機能 多様なドキュメント形式 : Markdown、PDF、テキスト、HTML、コードファイル 要約レベル選択 : 要点のみ/標準/詳細の3段階 柔軟な出力形式 : 箇条書き、段落形式、エグゼクティブサマリー、Q&A形式 ドキュメントタイプ別最適化 : 技術文書、ビジネス文書、学術論文、コードに対応 キーポイント抽出 : 重要な情報を自動的にハイライト セクション別要約 : 長文を章ごとに分割して要約 多言語対応 : 日本語、英語、その他の言語 HTMLレポート生成 : 美しくフォーマットされた要約レポート 使用方法 基本的な使い方 以下の技術文書を要約してください： [ドキュメントの内容を貼り付け] 要約レベル: 標準 出力形式: 箇条書き ファイルからの要...
 74
10476 mailchimp-automation composiohq/awesome-claude-skills
Mailchimp Automation via Rube MCP Automate Mailchimp email marketing workflows including campaign creation and sending, audience/list management, subscriber operations, segmentation, and performance analytics through Composio's Mailchimp toolkit. Toolkit docs : composio.dev/toolkits/mailchimp Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Mailchimp connection via RUBE_MANAGE_CONNECTIONS with toolkit mailchimp Always call RUBE_SEARCH_TOOLS first to get current tool ...
 74
10477 architecture-decisions jwilger/agent-skills
Architecture Decisions Value: Communication -- architecture decisions grounded in verified research ensure every contributor understands not just why a choice was made, but that the reasoning reflects reality. Decisions based on assumptions are decisions waiting to fail. Purpose Teaches the agent to move architecture decisions through a strict four-phase lifecycle: research dependencies first, draft from verified findings, hold for review, merge only with explicit authorization. Prevents decisio...
 74
10478 pr-create posit-dev/skills
PR Creator Skill Get changes into a PR, monitor CI, fix any failures, and notify the user when the PR is ready for review. The user may already have commits ready on a feature branch, or may have uncommitted changes, or both. Adapt the workflow to the current state. Task List Integration CRITICAL: Use Claude Code's task list system for progress tracking and session recovery. Use TaskCreate, TaskUpdate, and TaskList tools throughout execution. Task Hierarchy [Main Task] "Create PR: [branch-name]"...
 74
10479 scrum-master 404kidwiz/claude-supercode-skills
Scrum Master Expert Advanced agile practitioner specializing in data-driven team development, psychological safety facilitation, and high-performance sprint execution. Combines traditional Scrum mastery with modern analytics, behavioral science, and continuous improvement methodologies for sustainable team excellence. Table of Contents Capabilities Input Requirements Analysis Tools Methodology Templates & Assets Reference Frameworks Implementation Workflows Assessment & Measurement Best Practice...
 74
10480 start anthropics/knowledge-work-plugins
Start Command If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md . Initialize the task and memory systems, then open the unified dashboard. Instructions 1. Check What Exists Check the working directory for: TASKS.md — task list CLAUDE.md — working memory memory/ — deep memory directory dashboard.html — the visual UI 2. Create What's Missing If TASKS.md doesn't exist: Create it with the standard template (see task-management skill). Place it in the cu...
 74
10481 design-game opusgamelabs/game-creator
Design Game Run a UI/UX design pass on an existing game to improve visuals, atmosphere, and game feel. No design experience needed — this command analyzes your game and applies proven visual patterns. Instructions Analyze the game at $ARGUMENTS (or the current directory if no path given). First, load the game-designer skill to get the full design vocabulary and patterns. Step 1: Audit Read package.json to identify the engine Read src/core/Constants.js for the current color palette and config Rea...
 74
10482 accessibility engineer daffy0208/ai-dev-standards
Accessibility Engineer Build for everyone - accessibility is not optional. Core Principle Accessibility is a civil right, not a feature. 1 in 4 adults in the US has a disability. Accessible design benefits everyone: Blind users (screen readers) Low vision users (zoom, high contrast) Deaf users (captions) Motor disabilities (keyboard-only) Cognitive disabilities (clear language) Temporary disabilities (broken arm) Situational limitations (bright sunlight, noisy environment) WCAG Compliance Levels...
 74
10483 sharp-edges sickn33/antigravity-awesome-skills
Sharp Edges Analysis Evaluates whether APIs, configurations, and interfaces are resistant to developer misuse. Identifies designs where the "easy path" leads to insecurity. When to Use Reviewing API or library design decisions Auditing configuration schemas for dangerous options Evaluating cryptographic API ergonomics Assessing authentication/authorization interfaces Reviewing any code that exposes security-relevant choices to developers When NOT to Use Implementation bugs (use standard code r...
 74
10484 earnings-trade-analyzer tradermonty/claude-trading-skills
Earnings Trade Analyzer - Post-Earnings 5-Factor Scoring Analyze recent post-earnings stocks using a 5-factor weighted scoring system to identify the strongest earnings reactions for potential momentum trades. When to Use User asks for post-earnings trade analysis or earnings gap screening User wants to find the best recent earnings reactions User requests earnings momentum scoring or grading User asks about post-earnings accumulation day (PEAD) candidates Prerequisites FMP API key (set FMP_API_...
 74
10485 sciomc yeachan-heo/oh-my-claudecode
Research Skill Orchestrate parallel scientist agents for comprehensive research workflows with optional AUTO mode for fully autonomous execution. Overview Research is a multi-stage workflow that decomposes complex research goals into parallel investigations: Decomposition - Break research goal into independent stages/hypotheses Execution - Run parallel scientist agents on each stage Verification - Cross-validate findings, check consistency Synthesis - Aggregate results into comprehensive report ...
 74
10486 camofox-browser yelban/camofox-browser-skills
Camofox Browser - Anti-Detection Browser Automation Stealth browser automation via Camoufox (Firefox fork). C++ level fingerprint spoofing — undetectable by JavaScript-based bot checks. REST API wrapper using curl . Installation First use automatically downloads and installs the Camoufox browser (~300MB, one-time). No manual setup required — just run any camofox command. Quick Start camofox open https://example.com Open URL (auto-starts server) camofox snapshot Get page elements with @refs cam...
 74
10487 ddg-search sundial-org/awesome-openclaw-skills
DuckDuckGo Search Skill This skill provides the ability to perform web searches using DuckDuckGo. Usage To use this skill, provide a search query. The skill will return relevant results from DuckDuckGo. Scripts search.py : Executes the DuckDuckGo search and returns the results.
 74
10488 agent-folder-init shipshitdev/library
Agent Folder Init Create a comprehensive .agent/ folder structure for AI-first development workflows. Purpose This skill scaffolds a complete AI agent documentation system including: Session tracking (daily files) Task management Coding standards and rules Architecture decision records Security checklists SOPs for common workflows Agent config folders (.claude, .codex, .cursor) with commands, rules, and agents When to Use Use this skill when: Starting a new project that will use AI coding ...
 74
10489 qa-reviewer shipshitdev/library
QA Reviewer: Systematic Work Verification Purpose Structured framework for reviewing AI agent work before finalizing changes. Catches bugs, verifies accuracy, ensures completeness, validates solutions match requirements. Why this exists: AI agents can introduce subtle bugs, miss requirements, or make incorrect assumptions. When to Use User says "check your work" or "review this" After completing complex multi-step implementations Before committing major refactors When modifying commands or sk...
 74
10490 summarize mitsuhiko/agent-stuff
Turn “things” (URLs, PDFs, Word docs, PowerPoints, HTML pages, text files, etc.) into Markdown so they can be inspected/quoted/processed like normal text. markitdown can fetch URLs by itself; this skill mainly wraps it to make saving + summarizing convenient. For PDF inputs, use the markitdown[pdf] extra (or the wrapper below, which now does this automatically). When to use Use this skill when you need to: pull down a web page as a document-like Markdown representation convert binary docs (PDF/D...
 74
10491 github-copilot-cli-expert rysweet/amplihack
Comprehensive knowledge of GitHub Copilot CLI - the terminal-native AI coding assistant. Note: Command syntax and model availability may change. Run `/help` in Copilot CLI for current options. Purpose This skill provides expert guidance on: - Installing and updating GitHub Copilot CLI - All slash commands and keyboard shortcuts - Custom agents, skills, and MCP server configuration - Security, permissions, and trusted directories - Integration with GitHub workflows (PRs, issues, Actions)...
 74
10492 mapbox-mcp-runtime-patterns mapbox/mapbox-agent-skills
Mapbox MCP Runtime Patterns This skill provides patterns for integrating the Mapbox MCP Server into AI applications for production use with geospatial capabilities. What is Mapbox MCP Server? The Mapbox MCP Server is a Model Context Protocol (MCP) server that provides AI agents with geospatial tools: Offline Tools (Turf.js): Distance, bearing, midpoint calculations Point-in-polygon tests Area, buffer, centroid operations Bounding box, geometry simplification No API calls, instant results Mapbox ...
 74
10493 building-storefronts medusajs/medusa-claude-plugins
Medusa Storefront Development Frontend integration guide for building storefronts with Medusa. Covers SDK usage, React Query patterns, and calling custom API routes. When to Apply Load this skill for ANY storefront development task, including: Calling custom Medusa API routes from the storefront Integrating Medusa SDK in frontend applications Using React Query for data fetching Implementing mutations with optimistic updates Error handling and cache invalidation Also load building-with-medus...
 74
10494 agent-evaluation mlflow/skills
Agent Evaluation (AI Agent Evals) Based on Anthropic's "Demystifying evals for AI agents" When to use this skill Designing evaluation systems for AI agents Building benchmarks for coding, conversational, or research agents Creating graders (code-based, model-based, human) Implementing production monitoring for AI systems Setting up CI/CD pipelines with automated evals Debugging agent performance issues Measuring agent improvement over time Core Concepts Eval Evolution: Single-turn → Multi-turn →...
 74
10495 social-growth-engineer giulioco/skills
Social Growth Engineer This skill embodies the complete knowledge base of organic viral app growth through social media. It's built from analyzing 100+ successful app launches and growth campaigns that generated billions of views and millions in monthly revenue through TikTok, Instagram Reels, and YouTube Shorts. When to Use This Skill Invoke this skill when the user asks about: Growth & Strategy How to grow an app organically without paid ads Launching a new consumer app Scaling from 0 to 1...
 74
10496 getting-started-guide wordflowlab/novel-writer-skills
新用户入门引导 激活条件 当用户说出以下内容时自动激活： "我想写小说" "我要开始一个新项目" "怎么使用novel-writer" "从哪里开始" 七步方法论引导 欢迎消息 👋 欢迎使用Novel Writer Skills！ 我注意到你要开始一个新的小说项目。 Novel Writer使用系统化的七步方法论，帮助你从想法到完稿。 让我带你快速了解流程： 第1步：/constitution - 创建创作宪法 第2步：/specify - 定义故事规格 第3步：/clarify - 澄清模糊点（5个问题） 第4步：/plan - 制定创作计划 第5步：/tasks - 分解任务清单 第6步：/write - 执行章节写作 第7步：/analyze - 质量验证分析 想要详细了解每一步吗？还是直接开始第1步？ 步骤详解（根据需要提供） 【第1步：/constitution】 创建你的创作宪法 - 这是最高原则。 - 核心价值观（你想传达什么？） - 质量标准（什么算好的章节？） - 禁忌红线（不能写什么？） 为什么重要：后续所有创作都要符合宪法。 【第2步：/spec...
 74
10497 godot-mcp-scene-builder thedivergentai/gd-agentic-skills
MCP Scene Builder High-level agentic interface for low-level Godot MCP tools to build scenes from scratch. NEVER Do in MCP Scene Building NEVER skip design phase — Jumping straight to mcp_godot_add_node without planning hierarchy = spaghetti scenes. ALWAYS draft node tree first. NEVER assume scene exists before adding nodes — mcp_godot_add_node on non-existent scene = error. Must call mcp_godot_create_scene FIRST. NEVER use absolute paths in MCP calls — texturePath="C:/Users/..." breaks on other...
 74
10498 python-testing mindrally/skills
Python Testing Patterns Comprehensive testing strategies for Python applications using pytest, TDD methodology, and best practices. When to Activate Writing new Python code (follow TDD: red, green, refactor) Designing test suites for Python projects Reviewing Python test coverage Setting up testing infrastructure Core Testing Philosophy Test-Driven Development (TDD) Always follow the TDD cycle: RED : Write a failing test for the desired behavior GREEN : Write minimal code to make the test pass R...
 74
10499 spring-ai teachingai/full-stack-skills
Spring AI 开发指南 概述 Spring AI 是 Spring 官方提供的 AI 应用开发框架，简化了与各种大语言模型（LLM）的集成，包括 OpenAI、Anthropic、Azure OpenAI 等。 核心功能 1. 项目创建 依赖： <dependency> <groupId>org.springframework.ai</groupId> <artifactId>spring-ai-openai-spring-boot-starter</artifactId> </dependency> 或使用 Gradle： dependencies { implementation 'org.springframework.ai:spring-ai-openai-spring-boot-starter' } 2. Chat Client 配置： spring: ai: openai: api-key: ${OPENAI_API_KEY} chat: options: ...
 74
10500 geo-optimizer b-open-io/prompts
GEO Optimizer Generative Engine Optimization (GEO) for AI search visibility. What is GEO? GEO is NOT traditional SEO. AI search engines (ChatGPT, Perplexity, Claude, Gemini) work fundamentally differently: They fetch raw HTML - Many don't render JavaScript They have size limits - Crawlers abandon pages >1MB HTML They evaluate confidence - Hedged language ("maybe", "possibly") ranks 3x lower than confident assertions They need machine-readable metadata - AgentFacts/NANDA protocol for AI agent...
 74