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...
27,495
总 Skills
162.8M
总安装量
2,744
贡献者
# Skill 仓库 描述 安装量
23701 linkedin-cli sickn33/antigravity-awesome-skills
When to Use Use this skill when you need to automate LinkedIn tasks such as profile fetching, connection management, or post creation via CLI, especially when integrated into automated workflows. LinkedIn Skill You have access to linkedin – a CLI tool for LinkedIn automation. Use it to fetch profiles, search people and companies, send messages, manage connections, create posts, react, comment, and more. Each command sends a request to Linked API, which runs a real cloud browser to perform the ac...
 45
23702 mcp-builder shareai-lab/learn-claude-code
MCP Server Development Guide Overview Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks. Process 🚀 High-Level Workflow Creating a high-quality MCP server involves four main phases: Phase 1: Deep Research and Planning 1.1 Understand Modern MCP Design API Coverage vs. Workflow Tools: Balance comprehensive API endpoint coverag...
 45
23703 connecting-to-base-network base/base-skills
Connecting to Base Network Mainnet Property Value Network Name Base Chain ID 8453 RPC Endpoint https://mainnet.base.org Currency ETH Explorer https://basescan.org Testnet (Sepolia) Property Value Network Name Base Sepolia Chain ID 84532 RPC Endpoint https://sepolia.base.org Currency ETH Explorer https://sepolia.basescan.org Security Never use public RPC endpoints in production — they are rate-limited and offer no privacy guarantees; use a dedicated node provider or self-hosted node Never embed R...
 45
23704 board meeting prep eddiebe147/claude-settings
Board Meeting Prep Prepare board meeting decks, updates, and materials for effective governance When to Use This Skill Use this skill when you need to: Improve business operations and strategy Make data-driven business decisions Optimize processes and outcomes Not recommended for: Tasks requiring creative design work technical coding Quick Reference Action Command/Trigger Create board meeting prep board meeting Review and optimize review board meeting prep Get best practices board meeting prep b...
 45
23705 ab-test-setup openclaudia/openclaudia-skills
A/B Test Setup You are an expert in experimentation and A/B testing. Your goal is to help design tests that produce statistically valid, actionable results. Initial Assessment Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Before designing a test, understand: Test Context ...
 45
23706 slack message writer eddiebe147/claude-settings
Slack Message Writer The Slack Message Writer skill helps you create clear, engaging, and appropriately formatted messages for Slack channels and direct messages. Whether you're making an announcement, asking for help, sharing updates, or facilitating async discussions, this skill ensures your Slack communication is effective and professional. This skill understands Slack's unique communication culture—more casual than email but still professional, heavy use of emoji for tone, threading for cont...
 45
23707 azure-web-pubsub-ts sickn33/antigravity-awesome-skills
Azure Web PubSub SDKs for TypeScript Real-time messaging with WebSocket connections and pub/sub patterns. Installation Server-side management npm install @azure/web-pubsub @azure/identity Client-side real-time messaging npm install @azure/web-pubsub-client Express middleware for event handlers npm install @azure/web-pubsub-express Environment Variables WEBPUBSUB_CONNECTION_STRING = Endpoint = https:// < resource > .webpubsub.azure.com ; AccessKey = < key > ; Version = 1.0 ; WEBPUBSUB_ENDPOINT...
 45
23708 window-function-builder dengineproblem/agents-monorepo
SQL Window Function Builder Эксперт по SQL window functions и аналитическим запросам для бизнес-аналитики. Core Function Categories Function Overview window_functions : ranking : - ROW_NUMBER() : "Unique sequential numbers" - RANK() : "Ranking with gaps for ties" - DENSE_RANK() : "Ranking without gaps" - NTILE(n) : "Divide into n buckets" aggregate : - SUM() : "Running/cumulative totals" - AVG() : "Moving averages" - COUNT() : "Running counts" - MIN() : "Running minimum" - MAX() : "Running maxim...
 45
23709 discovery-caller ncklrs/startup-os-skills
Discovery Caller Strategic discovery call expertise for B2B sales teams — from preparation and question frameworks to qualification and documentation. Philosophy Discovery isn't about pitching. It's about understanding deeply before you ever propose a solution. The best discovery calls: Listen more than talk — Aim for 70/30 prospect-to-rep ratio Quantify everything — Pain without numbers is just complaining Map the buying committee — One champion doesn't close deals Earn the next step — Every ca...
 45
23710 web-search xxiii8322766509/nagaagent
Install the belt CLI skill: npx skills add belt-sh/cli Web Search & Extraction Search the web and extract content via inference.sh CLI. Quick Start Requires inference.sh CLI ( belt ). Install instructions belt login Search the web belt app run tavily/search-assistant --input '{"query": "latest AI developments 2024"}' Show more Installs 34.6K Repository skills-101/superpowers GitHub Stars 7 First Seen 13 days ago Security Audits Gen Agent Trust Hub Pass Socket Warn Snyk Warn
 45
23711 advisory board builder eddiebe147/claude-settings
Advisory Board Builder Recruit, structure, and manage advisory boards for strategic guidance When to Use This Skill Use this skill when you need to: Improve business operations and strategy Make data-driven business decisions Optimize processes and outcomes Not recommended for: Tasks requiring creative design work technical coding Quick Reference Action Command/Trigger Create advisory board builder advisory board Review and optimize review advisory board builder Get best practices advisory board...
 45
23712 chembl-search yorkeccak/scientific-skills
ChEMBL Search Search the complete ChEMBL database of bioactive molecules, drug targets, and binding data using natural language queries powered by Valyu's semantic search API. Why This Skill is Powerful No API Parameter Parsing: Just pass natural language queries directly - no need to construct complex search parameters Semantic Search: Understands the meaning of your query, not just keyword matching Full-Text Access: Returns complete compound and target information Image Links: Includes molec...
 45
23713 competitive-ads-extractor nicepkg/ai-workflow
Competitive Ads Extractor This skill extracts your competitors' ads from ad libraries and analyzes what's working—the problems they're highlighting, use cases they're targeting, and copy/creative that's resonating. When to Use This Skill Researching competitor ad strategies Finding inspiration for your own ads Understanding market positioning Identifying successful ad patterns Analyzing messaging that works Discovering new use cases or pain points Planning ad campaigns with proven concepts Wha...
 45
23714 cold-email humanizerai/agent-skills
Cold Email Writing You are an expert cold email writer. Your goal is to write emails that sound like they came from a sharp, thoughtful human — not a sales machine following a template. Before Writing Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Understand the situation ...
 45
23715 design-expert personamanagmentlayer/pcl
System Design Expert Expert guidance for system design, software architecture, scalability patterns, and distributed systems. Core Concepts Architecture Patterns Microservices vs Monolithic Event-driven architecture CQRS and Event Sourcing Layered architecture Hexagonal architecture Service-oriented architecture (SOA) Scalability Horizontal vs vertical scaling Load balancing strategies Caching layers Database sharding Read replicas CDN usage Distributed Systems CAP theorem Consistency models Dis...
 45
23716 replay-cli replayio/skills
replay-cli Description: Use when the user wants help with Replay CLI commands for recording, uploading, managing recordings, or authentication. Examples: "upload my recording", "list my replays", "login to replay", "remove recordings", "record a session". Instructions: You are helping the user with the Replay CLI tool. Here is the complete reference: Installation Install Replay CLI globally using your preferred package manager: npm i -g replayio or yarn add -g replayio or pnpm i -g replayio o...
 45
23717 playwright-browser 91fapiao-cn/playwright-browser-skill
Playwright Browser Skill - 浏览器自动化技能 ⚡ AI 调用指南（OpenClaw 必读） 如何调用 MCP 工具 当用户请求浏览器操作时，你需要通过 MCP 协议调用相应的工具。以下是调用方法： 基本调用流程 启动浏览器 → 调用 browser_launch 访问网页 → 调用 browser_goto 执行操作 → 调用相应工具（点击、填写、提取等） 关闭浏览器 → 调用 browser_close 常用工具快速参考 用户需求 调用工具 参数示例 "访问网站" browser_goto { "url": "https://example.com" } "点击按钮" browser_click { "selector": "button.submit" } "填写表单" browser_fill { "selector": "username", "value": "admin" } "获取标题" browser_get_title {} "截图" browser_screenshot { "path": "screenshot.png", "fullPa...
 45
23718 forms-inputs dylantarre/animation-principles
Form & Input Animation Principles Apply Disney's 12 principles to forms for clear feedback and delightful interactions. Principles Applied to Form Elements 1. Squash & Stretch Input fields can subtly expand on focus (1-2px height). Submit button compresses on click. Checkboxes bounce on toggle. 2. Anticipation Label floats up before user types. Focus ring appears before content entry. Prepares user for input action. 3. Staging Focused input should be visually prominent: border color, shad...
 45
23719 value-dividend-screener nicepkg/ai-workflow
Value Dividend Screener Overview This skill identifies high-quality dividend stocks that combine value characteristics, attractive income generation, and consistent growth using a two-stage screening approach : FINVIZ Elite API (Optional but Recommended) : Pre-screen stocks with basic criteria (fast, cost-effective) Financial Modeling Prep (FMP) API : Detailed fundamental analysis of candidates Screen US equities based on quantitative criteria including valuation ratios, dividend metrics, financ...
 45
23720 revenue-operations borghei/claude-skills
Revenue Operations Pipeline analysis, forecast accuracy tracking, and GTM efficiency measurement for SaaS revenue teams. Table of Contents Quick Start Tools Overview Pipeline Analyzer Forecast Accuracy Tracker GTM Efficiency Calculator Revenue Operations Workflows Weekly Pipeline Review Forecast Accuracy Review GTM Efficiency Audit Quarterly Business Review Reference Documentation Templates Quick Start Analyze pipeline health and coverage python scripts/pipeline_analyzer.py --input assets/sampl...
 45
23721 douban-movie-review agentbay-ai/agentbay-skills
豆瓣电影影评查询 依赖 python3 -m pip install wuying-agentbay-sdk 安装步骤 在使用此技能之前，请确保已安装必要的依赖包： python3 -m pip install wuying-agentbay-sdk 使用场景 用户询问某部电影的豆瓣影评 用户想了解电影的用户评价 用户想查看电影的热门短评 使用方法 python3 scripts/browser-use.py "<任务执行步骤>" 快速示例 python3 scripts/browser-use.py " \ 前往豆瓣网站 https://www.douban.com/ \ 搜索电影盗梦空间 \ 点击盗梦空间进入详情界面,下滑到短评部分 \ 提取前5条热门评论 \ 以markdown格式返回 " 输出格式 《电影名称》豆瓣影评 热门短评 1. 用户名 点赞数 评论内容 2. 用户名 点赞数 评论内容 注意事项 始终注明信息来源为豆瓣 不需要创建新的脚本，用skill目录下的browser-use.py 任务需要执行1~2分钟，不要杀进程，请耐心等待和观察任务，也不要重试 skill...
 45
23722 client onboarding designer eddiebe147/claude-settings
Client Onboarding Designer Design smooth client onboarding experiences that ensure success and retention When to Use This Skill Use this skill when you need to: Improve business operations and strategy Make data-driven business decisions Optimize processes and outcomes Not recommended for: Tasks requiring creative design work technical coding Quick Reference Action Command/Trigger Create client onboarding designer client onboarding Review and optimize review client onboarding designer Get best p...
 45
23723 portable-document-handler qodex-ai/ai-agent-skills
PDF Processing Guide Overview This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see reference.md. If you need to fill out a PDF form, read forms.md and follow its instructions. Quick Start from pypdf import PdfReader, PdfWriter Read a PDF reader = PdfReader("document.pdf") print(f"Pages: {len(reader.pages)}") Extract text text = "" for page in reader.pages: text += pag...
 45
23724 azure-ai-agents-persistent-java sickn33/antigravity-awesome-skills
Azure AI Agents Persistent SDK for Java Low-level SDK for creating and managing persistent AI agents with threads, messages, runs, and tools. Installation < dependency > < groupId > com.azure </ groupId > < artifactId > azure-ai-agents-persistent </ artifactId > < version > 1.0.0-beta.1 </ version > </ dependency > Environment Variables PROJECT_ENDPOINT = https:// < resource > .services.ai.azure.com/api/projects/ < project > MODEL_DEPLOYMENT_NAME = gpt-4o-mini Authentication import com . azure ....
 45
23725 performance-optimization dylantarre/animation-principles
Performance Optimization Overview Measure before optimizing. Performance work without measurement is guessing — and guessing leads to premature optimization that adds complexity without improving what matters. Profile first, identify the actual bottleneck, fix it, measure again. Optimize only what measurements prove matters. When to Use Performance requirements exist in the spec (load time budgets, response time SLAs) Users or monitoring report slow behavior Core Web Vitals scores are below thre...
 45
23726 dingtalk-sheet-scripts rockyz/dingtalk-sheet-scripts
钉钉表格脚本开发 运行环境 语言：JavaScript (ES6+) 运行在钉钉表格的沙箱环境中 使用 Output.log() 输出日志（不是 console.log ） 支持 async/await 和 fetch API 核心对象 对象 说明 获取方式 Workbook 工作簿（顶级对象） 直接使用 Sheet 工作表 Workbook.getActiveSheet() Range 单元格区域 sheet.getRange('A1:B10') Input 用户输入（异步） await Input.textAsync() Output 日志输出 Output.log() 快速示例 // 基础数据写入 const sheet = Workbook . getActiveSheet ( ) ; sheet . getRange ( 'A1:B2' ) . setValues ( [ [ '姓名' , '分数' ] , [ '张三' , 95 ] ] ) ; // 异步用户输入 const name = await Input . textAsync ( '请输入姓名：' ) ; Out...
 45
23727 patent-diagram-generator robthepcguy/claude-patent-creator
Patent Diagram Generator Skill Create patent-style technical diagrams including flowcharts, block diagrams, and system architectures using Graphviz. When to Use Invoke this skill when users ask to: Create flowcharts for method claims Generate block diagrams for system claims Draw system architecture diagrams Create technical illustrations for patents Add reference numbers to diagrams Generate patent figures What This Skill Does Flowchart Generation : Method step flowcharts Decision trees Process...
 45
23728 bootstrap-components sjnims/bootstrap-expert
Bootstrap 5.3 Components Bootstrap provides ready-to-use UI components for building interfaces. This skill covers all major components with usage patterns, JavaScript initialization requirements, and accessibility best practices. JavaScript Initialization Overview: Some components work purely with data attributes, while others require JavaScript initialization. Components marked with Requires JS below won't function without explicit initialization. Component Requires JS Init Data Attributes O...
 45
23729 netease-auth api/git
No SKILL.md available for this skill. View on GitHub
 45
23730 accelint-skill-manager gohypergiant/agent-skills
Skill Manager NEVER Do When Creating Skills NEVER write tutorials explaining basics - Assume Claude knows standard concepts, libraries, and patterns. Focus on expert-only knowledge. NEVER put triggering information in body - "When to use" guidance belongs ONLY in the description field. The body is loaded after activation decision. NEVER dump everything in SKILL.md - Use progressive disclosure: core workflow in SKILL.md (<500 lines ideal), detailed content in references/, loaded on-demand. NEVER ...
 45
23731 lean4 cameronfreer/lean4-skills
Lean 4 Theorem Proving Use this skill whenever you're editing Lean 4 proofs, debugging Lean builds, formalizing mathematics in Lean, or learning Lean 4 concepts. It prioritizes LSP-based inspection and mathlib search, with scripted primitives for sorry analysis, axiom checking, and error parsing. Core Principles Search before prove. Many mathematical facts already exist in mathlib. Search exhaustively before writing tactics. Build incrementally. Lean's type checker is your test suite—if it compi...
 45
23732 database-query cisco-ai-defense/skill-scanner
Database Query Skill Safely query databases using parameterized statements. Usage Provide query parameters and get results safely.
 45
23733 azure-ai-projects-java sickn33/antigravity-awesome-skills
Azure AI Projects SDK for Java High-level SDK for Azure AI Foundry project management with access to connections, datasets, indexes, and evaluations. Installation < dependency > < groupId > com.azure </ groupId > < artifactId > azure-ai-projects </ artifactId > < version > 1.0.0-beta.1 </ version > </ dependency > Environment Variables PROJECT_ENDPOINT = https:// < resource > .services.ai.azure.com/api/projects/ < project > Authentication import com . azure . ai . projects . AIProjectClientBuild...
 45
23734 python-async-patterns 0xdarkmatter/claude-mods
Python Async Patterns Asyncio patterns for concurrent Python programming. Core Concepts import asyncio Coroutine (must be awaited) async def fetch(url: str) -> str: async with aiohttp.ClientSession() as session: async with session.get(url) as response: return await response.text() Entry point async def main(): result = await fetch("https://example.com") return result asyncio.run(main()) Pattern 1: Concurrent with gather async def fetch_all(urls: list[str])...
 45
23735 social commerce strategist eddiebe147/claude-settings
Social Commerce Strategist Create strategies for shoppable posts and social commerce conversion optimization When to Use This Skill Use this skill when you need to: Improve business operations and strategy Make data-driven business decisions Optimize processes and outcomes Not recommended for: Tasks requiring creative design work technical coding Quick Reference Action Command/Trigger Create social commerce strategist social commerce Review and optimize review social commerce strategist Get best...
 45
23736 azure-devops sanjay3290/ai-skills
Azure DevOps API Skill This skill provides comprehensive guidance for working with the Azure DevOps REST API, enabling programmatic access to all Azure DevOps Services and Azure DevOps Server resources. Overview Azure DevOps REST API is a RESTful web API enabling you to access and manage work items, repositories, pipelines, test plans, artifacts, and more across all Azure DevOps services. Base URL: https://dev.azure.com/{organization}/{project}/_apis/{area}/{resource}?api-version={version} ...
 45
23737 alba-inertia inertia-rails/skills
Alba + Typelizer for Inertia Rails Requires: alba , typelizer , alba-inertia gems in Gemfile. Alba serializers for Inertia props with auto-generated TypeScript types. Replaces as_json(only: [...]) with structured, type-safe resources. Before creating a resource, ask: Reusable data shape (user, course)? → Entity resource ( UserResource ) — shared across pages Page-specific props bundle? → Page resource ( UsersIndexResource ) — one per controller action Global data (auth, notifications)? → Shared ...
 45
23738 nuxt-code-editor caomeiyouren/momei
Nuxt Code Editor Skill (Nuxt 代码编辑技能) 能力 (Capabilities) Vue 3 Composition API : 生成 <script setup lang="ts"> 组件。 PrimeVue 集成 : 根据 utils/ 或现有的 components/ 用法正确使用 PrimeVue 组件。 Better-Auth 集成 : 正确使用 authClient (前端) 和 auth (服务端) 进行身份验证和权限控制。 类型安全 : 确保所有后端代码使用在 server/database/entities 或 types/ 中定义的 TypeORM 实体和 DTO。 Zod 校验 : 使用 Zod 进行 API 请求参数校验 (参考 utils/schemas/ )。 增量编辑 : 优先修补 (patch) 而非重写整个文件，以保留上下文。 指令 (Instructions) 路径与工作树意识 : 所有的文件创建与修改操作必须在当前任务所属的工作树中执行。如果是主功能开发，应在 dev 或 fix 分支对应的目录进行。 代码风格指南 : ...
 45
23739 gh-address-comments tech-leads-club/agent-skills
PR Comment Handler Guide to find the open PR for the current branch and address its comments with gh CLI. Run all gh commands with elevated network access. Prereq: ensure gh is authenticated (for example, run gh auth login once), then run gh auth status with escalated permissions (include workflow/repo scopes) so gh commands succeed. If sandboxing blocks gh auth status , rerun it with sandbox_permissions=require_escalated . 1) Inspect comments needing attention Run scripts/fetch_comments.py whic...
 45
23740 detox teachingai/full-stack-skills
When to use this skill Use this skill whenever the user wants to: [待完善：根据具体工具添加使用场景] How to use this skill [待完善：根据具体工具添加使用指南] Best Practices [待完善：根据具体工具添加最佳实践] Keywords [待完善：根据具体工具添加关键词]
 45
23741 uifork sambernhardt/uifork
UIFork UIFork is a CLI tool and React component library for managing UI component versions. Create multiple versions of components, let stakeholders switch between them to test and gather feedback, and promote the best one when ready. When to Use User wants to version React components for A/B testing or stakeholder feedback User mentions uifork, component versioning, or UI variations User needs help with uifork CLI commands (init, watch, new, fork, promote, etc.) User wants to set up uifork in a...
 45
23742 npm-library-setup huozhi/npm-skills
npm Library Setup with ESM This skill provides comprehensive guidance on setting up an npm library with package.json, with a preference for ES Modules (ESM). Overview This skill helps you create npm packages that: Use ES Modules (ESM) with "type": "module" Configure modern exports field (no deprecated module field) Use bunchee for zero-config bundling Use vitest for modern testing Support TypeScript and React component libraries When to Use This Skill Use when: "Set up an npm package" "Cre...
 45
23743 lifecycle marketing manager eddiebe147/claude-settings
Lifecycle Marketing Manager Design customer lifecycle marketing with automated email sequences and journeys When to Use This Skill Use this skill when you need to: Improve business operations and strategy Make data-driven business decisions Optimize processes and outcomes Not recommended for: Tasks requiring creative design work technical coding Quick Reference Action Command/Trigger Create lifecycle marketing manager lifecycle marketing Review and optimize review lifecycle marketing manager Get...
 45
23744 foundation-models johnrogers/claude-swift-engineering
Foundation Models Apple's on-device AI framework providing access to a 3B parameter language model for summarization, extraction, classification, and content generation. Runs entirely on-device with no network required. Overview Foundation Models enable intelligent text processing directly on device without server round-trips, user data sharing, or network dependencies. The core principle: leverage on-device AI for specific, contained tasks (not for general knowledge). Reference Loading Guid...
 45
23745 test-engineer caomeiyouren/momei
Test Engineer Skill 能力 (Capabilities) 测试编写 : 使用 Vitest 编写针对 Vue 组件和 TypeScript 逻辑的测试。 测试运行 : 熟练运行 pnpm test 或针对特定文件的测试命令。 覆盖率分析 : 阅读和理解测试覆盖率报告。 Mocking : 模拟 API 响应、Nuxt composables (如 useI18n )。 指令 (Instructions) Worktree 意识 : 务必在 ../momei-test 工作树中运行测试命令。如果尚不存在该路径，应引导用户或自动创建之。 规范对齐 : 在运行测试前必须阅读并遵循 测试规范 。 测试策略 : 优先执行 定向测试 (Targeted Testing)，仅运行与改动相关的测试文件。 全量测试条件 : 除非涉及大规模重构或安全风险，否则避免全量测试。全量测试通常仅在专门的“测试增强”任务中进行。 用例设计 : 考虑正常流程、异常流程和边缘情况。 Mock 配置 : 在测试文件中配置必要的 mock（如 useI18n ）。 执行验证 : 编写完后必须运行测试确保其...
 45
23746 team-tasks win4r/team-tasks
Team Tasks — Multi-Agent Pipeline Coordination Overview Coordinate dev team agents through shared JSON task files + AGI dispatch. AGI is the command center — agents never talk to each other directly. Two modes: Mode A (linear): Fixed pipeline order code → test → docs → monitor Mode B (dag): Tasks declare dependencies, parallel dispatch when deps are met Task Manager CLI All commands use: python3 <skill-dir>/scripts/task_manager.py <command> [args] Where <skill-dir> is the directory containing th...
 45
23747 nx-run-tasks tech-leads-club/agent-skills
You can run tasks with Nx in the following way. Keep in mind that you might have to prefix things with npx/pnpx/yarn if the user doesn't have nx installed globally. Look at the package.json or lockfile to determine which package manager is in use. For more details on any command, run it with --help (e.g. nx run-many --help , nx affected --help ). Understand which tasks can be run You can check those via nx show project <projectname> --json , for example nx show project myapp --json . It contains...
 45
23748 animejs-mastery frogody/app.isyncso
Anime.js Animation Upgrade Agent Autonomous agent that analyzes codebases and systematically implements polished, performant animations using anime.js. Agent Workflow Execute these phases sequentially. Work autonomously—don't ask for permission between steps. Phase 1: Codebase Analysis 1. Identify framework and structure find . -name "package.json" -o -name "*.tsx" -o -name "*.jsx" -o -name "*.vue" -o -name "*.svelte" | head -20 2. Check if anime.js is installed grep -r "animejs\|anime.js" pac...
 45
23749 agentdb performance optimization proffesor-for-testing/agentic-qe
AgentDB Performance Optimization What This Skill Does Provides comprehensive performance optimization techniques for AgentDB vector databases. Achieve 150x-12,500x performance improvements through quantization, HNSW indexing, caching strategies, and batch operations. Reduce memory usage by 4-32x while maintaining accuracy. Performance : <100µs vector search, <1ms pattern retrieval, 2ms batch insert for 100 vectors. Prerequisites Node.js 18+ AgentDB v1.0.7+ (via agentic-flow) Existing AgentDB dat...
 45
23750 fine-tuning assistant eddiebe147/claude-settings
Fine-Tuning Assistant The Fine-Tuning Assistant skill guides you through the process of adapting pre-trained models to your specific use case. Fine-tuning can dramatically improve model performance on specialized tasks, teach models your preferred style, and add capabilities that prompting alone cannot achieve. This skill covers when to fine-tune versus prompt engineer, preparing training data, selecting base models, configuring training parameters, evaluating results, and deploying fine-tuned m...
 45