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...
25,087
总 Skills
109.9M
总安装量
2,605
贡献者
# Skill 仓库 描述 安装量
18601 react-admin marmelab/react-admin
React-Admin Development Guide React-admin is a framework for building single-page applications on top of REST/GraphQL APIs. It builds on top of React Query, react-hook-form, react-router, and Material UI. It provides 150+ components and dozens of hooks. Before writing custom code, always check if react-admin already provides a component or hook for the task. Full documentation: https://marmelab.com/react-admin/doc/ Providers (Backend Abstraction) React-admin never calls APIs directly. All commun...
 56
18602 resend-setup andrelandgraf/fullstackrecipes
Resend Setup To set up Resend Setup, refer to the fullstackrecipes MCP server resource: Resource URI: recipe://fullstackrecipes.com/resend-setup If the MCP server is not configured, fetch the recipe directly: curl -H "Accept: text/plain" https://fullstackrecipes.com/api/recipes/resend-setup
 56
18603 ai-llm-inference vasilyu1983/ai-agents-public
LLMOps - Inference & Optimization - Production Skill Hub Modern Best Practices (January 2026) : Treat inference as a systems problem : SLOs, tail latency, retries, overload, and cache strategy. Use continuous batching / smart scheduling when serving many concurrent requests (Orca scheduling: https://www.usenix.org/conference/osdi22/presentation/yu ). Use KV-cache aware serving (PagedAttention/vLLM: https://arxiv.org/abs/2309.06180 ) and efficient attention kernels (FlashAttention: https://arxiv....
 56
18604 openai-image-gen steipete/agent-scripts
OpenAI Image Gen Generate a handful of “random but structured” prompts and render them via the OpenAI Images API. Run Note: Image generation can take longer than common exec timeouts (for example 30 seconds). When invoking this skill via OpenClaw’s exec tool, set a higher timeout to avoid premature termination/retries (e.g., exec timeout=300). python3 { baseDir } /scripts/gen.py open ~/Projects/tmp/openai-image-gen-*/index.html if ~/Projects/tmp exists; else ./tmp/... Useful flags: GPT image m...
 56
18605 junit teachingai/full-stack-skills
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]
 56
18606 markets machina-sports/sports-skills
Markets Orchestration Bridges ESPN live schedules (NBA, NFL, MLB, NHL, WNBA, CFB, CBB) with Kalshi and Polymarket prediction markets. Before writing queries, consult references/api-reference.md for supported sport codes, command parameters, and price normalization formats. Quick Start sports-skills markets get_todays_markets --sport = nba sports-skills markets search_entity --query = "Lakers" --sport = nba sports-skills markets compare_odds --sport = nba --event_id = 401234567 sports-skills mark...
 56
18607 github-pr gentleman-programming/gentleman-skills
When to Use Creating a new Pull Request Writing PR titles and descriptions Preparing commits for review Using gh pr create command Critical Patterns PR Title = Conventional Commit <type>(<scope>): <short description> feat New feature fix Bug fix docs Documentation refactor Code refactoring test Adding tests chore Maintenance PR Description Structure Summary - 1-3 bullet points explaining WHAT and WHY Changes - List main changes Testing - [ ] Tests added/updated - [ ]...
 56
18608 simpo-training orchestra-research/ai-research-skills
SimPO - Simple Preference Optimization Quick start SimPO is a reference-free preference optimization method that outperforms DPO without needing a reference model. Installation: Create environment conda create -n simpo python=3.10 && conda activate simpo Install PyTorch 2.2.2 Visit: https://pytorch.org/get-started/locally/ Install alignment-handbook git clone https://github.com/huggingface/alignment-handbook.git cd alignment-handbook python -m pip install . Install Flash Attention 2 p...
 56
18609 hig-components-controls raintree-technology/apple-hig-skills
Apple HIG: Selection and Input Controls Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered. Key Principles Clear current state. Users must always see what is selected. Toggles show on/off, segmented controls highlight the active segment, pickers display the current selection. Prefer standard system controls. Built-in controls provide consistency and accessibility. Custom controls introduce a learning curve and ...
 56
18610 llm-judge existential-birds/beagle
LLM Judge Skill Compare code implementations across 2+ repositories using structured evaluation. Overview This skill implements a two-phase LLM-as-judge evaluation: Phase 1: Fact Gathering - Parallel agents explore each repo and extract structured facts Phase 2: Judging - Parallel judges score each dimension using consistent rubrics Reference Files File Purpose references/fact-schema.md JSON schema for Phase 1 facts references/scoring-rubrics.md Detailed rubrics for each dimension references...
 56
18611 python-analytics pluginagentmarketplace/custom-plugin-data-analyst
Python Analytics Skill Overview Master Python for data analysis using industry-standard libraries. Topics Covered Pandas DataFrames and Series operations NumPy array manipulation Data aggregation and groupby Time series analysis Jupyter notebook workflows Learning Outcomes Analyze data with pandas Perform numerical computations Build reproducible analysis notebooks Process large datasets efficiently Error Handling Error Type Cause Recovery MemoryError Dataset too large Use chunking or dask KeyEr...
 56
18612 file-manager bussgrowwithlucky-crypto/openclaw-skill-file-manager
文件管理技能 本技能提供文件和文件夹管理能力。 核心功能 1. 文件操作 创建文件 复制/移动文件 重命名文件 删除文件 2. 文件夹操作 创建文件夹 列出目录内容 删除文件夹（递归） 复制文件夹 3. 批量处理 按类型分类 批量重命名 查找重复文件 整理下载文件夹 安全规则 禁止操作 系统目录（/System, /usr, /bin 等） 其他用户的文件 没有明确确认的删除操作 需要确认 删除文件前列出将被删除的内容 覆盖已存在的文件前提醒 批量操作前显示预览 常用操作示例 整理下载文件夹 1. 创建分类目录 mkdir -p ~/Downloads/ { Documents,Images,Videos,Archives,Others } 2. 按扩展名移动 mv ~/Downloads/*.pdf ~/Downloads/Documents/ mv ~/Downloads/*. { jpg,png,gif } ~/Downloads/Images/ mv ~/Downloads/*. { mp4,mov,avi } ~/Downloads/Videos/ mv ~/Downlo...
 56
18613 next-cache-components vercel-labs/vercel-skills
Cache Components (Next.js 16+) Cache Components enable Partial Prerendering (PPR) - mix static, cached, and dynamic content in a single route. Enable Cache Components // next.config.ts import type { NextConfig } from 'next' const nextConfig: NextConfig = { cacheComponents: true, } export default nextConfig This replaces the old experimental.ppr flag. Three Content Types With Cache Components enabled, content falls into three categories: 1. Static (Auto-Prerendered) Synchronous code, ...
 56
18614 apify danielmiessler/personal_ai_infrastructure
Apify Web scraping and automation platform. Run pre-built Actors (scrapers) or create your own. Access thousands of ready-to-use scrapers for popular websites. Official docs: https://docs.apify.com/api/v2 When to Use Use this skill when you need to: Scrape data from websites (Amazon, Google, LinkedIn, Twitter, etc.) Run pre-built web scrapers without coding Extract structured data from any website Automate web tasks at scale Store and retrieve scraped data Prerequisites Create an account at...
 56
18615 sherlock-review proffesor-for-testing/agentic-qe
<default_to_action> When investigating code claims: - OBSERVE: Gather all evidence (code, tests, history, behavior) - DEDUCE: What does evidence actually show vs. what was claimed? - ELIMINATE: Rule out what cannot be true - CONCLUDE: Does evidence support the claim? - DOCUMENT: Findings with proof, not assumptions The 3-Step Investigation: ``` 1. OBSERVE: Gather evidence git diff <commit> npm test -- --coverage 2. DEDUCE: Compare claim vs reality Does code match description? Do test...
 56
18616 kubectl oldwinter/skills
Kubectl Skill This skill enables comprehensive Kubernetes cluster management using kubectl and related tools. Environment Cluster Aliases Three cluster/namespace combinations are pre-configured: Alias Cluster Namespace Purpose k1 AWS EKS Production production 生产环境 k2 AWS EKS Production staging 预发布环境 k K3s (192.168.10.117) simplex 本地开发环境 Usage: k1 get pods 查看生产环境 pods k2 get pods 查看预发布环境 pods k get pods 查看本地环境 pods Additional Tools kubectx - Switch between cl...
 56
18617 godot-export-builds thedivergentai/gd-agentic-skills
Export & Builds Expert guidance for building and distributing Godot games across platforms. NEVER Do NEVER export without testing on target platform first — "Works on my machine" doesn't mean it works on Windows/Linux/Android. Test early and often. NEVER use debug builds for release — Debug builds are 5-10x larger and slower. Always export with --export-release for production. NEVER hardcode file paths in exports — Use res:// and user:// paths. Absolute paths ( C:/Users/... ) break on other mach...
 56
18618 prisma-patterns ashchupliak/dream-team
Prisma Patterns Production patterns and non-obvious traps for Prisma ORM in TypeScript backends. Tested against Prisma 5.x and 6.x. Some behaviors differ from Prisma 4. Check the Prisma version before applying version-specific patterns: npx prisma --version Prisma 5 introduced relationJoins , which can load relations via JOIN rather than separate queries depending on query strategy and configuration. The omit field modifier and prisma.$extends Client Extensions API were also added. Note: relatio...
 56
18619 n8n-integration-testing-patterns proffesor-for-testing/agentic-qe
n8n Integration Testing Patterns <default_to_action> When testing n8n integrations: VERIFY connectivity and authentication TEST all configured operations VALIDATE API response handling CHECK rate limit behavior CONFIRM error handling works Quick Integration Checklist: Credentials valid and not expired API permissions sufficient for operations Rate limits understood and respected Error responses properly handled Data formats match API expectations Critical Success Factors: Test in isolation...
 56
18620 rive bowtiedswan/rive-skills
Rive Animation Platform Skill This skill provides comprehensive knowledge for working with Rive, an interactive animation platform that enables creating and running interactive graphics across web, mobile, and game platforms. Overview Rive is a design and animation tool that produces lightweight, interactive graphics with a powerful runtime. Key capabilities: Scripting : Write Luau scripts directly in the Rive Editor to extend functionality State Machines : Create complex interactive animations ...
 56
18621 docs-sync drillan/speckit-gates
Docs Sync Overview Identify doc coverage gaps and inaccuracies by comparing main branch features and configuration options against the current docs structure, then propose targeted improvements. Workflow Confirm scope and base branch Identify the current branch and default branch (usually main ). Prefer analyzing the current branch to keep work aligned with in-flight changes. If the current branch is not main , analyze only the diff vs main to scope doc updates. Avoid switching branches if it wo...
 56
18622 excalidraw-diagrams robtaylor/excalidraw-diagrams
Excalidraw Diagram Generator This skill generates Excalidraw diagrams programmatically using Python. Instead of creating ASCII diagrams, use this to produce professional-looking, editable diagrams. Output format: .excalidraw JSON files that can be: Opened at https://excalidraw.com (drag & drop the file) Edited in VS Code with the Excalidraw extension Embedded in documentation Exported to SVG/PNG for embedding in Google Docs, presentations, etc. Quick Start Method 1: Direct Python Script (Reco...
 56
18623 form-filler dkyazzentwatwa/chatgpt-skills
Fill PDF forms programmatically with structured data. Features - Field Detection: Auto-detect form fields - Multiple Field Types: Text, checkbox, dropdown, radio - Data Sources: JSON, CSV, dictionary input - Batch Filling: Fill multiple forms from data file - Field Mapping: Map data keys to field names - Flatten Option: Convert to non-editable PDF - Form Info: List all fields and their types Quick Start ``` from form_filler import FormFiller filler = FormFiller() Load form filler....
 56
18624 humanizer gohypergiant/agent-skills
Humanizer: Remove AI Writing Patterns You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup. Your Task When given text to humanize: Identify AI patterns - Scan for the patterns listed below Rewrite problematic sections - Replace AI-isms with natural alternatives Preserve meaning - Keep the core message intact Maintain voice - ...
 56
18625 bun workers secondsky/claude-skills
Bun supports Web Workers and Node.js worker_threads for parallel execution. Web Workers Basic Usage ``` // main.ts const worker = new Worker(new URL("./worker.ts", import.meta.url)); worker.postMessage({ type: "start", data: [1, 2, 3, 4, 5] }); worker.onmessage = (event) => { console.log("Result:", event.data); }; worker.onerror = (error) => { console.error("Worker error:", error.message); }; // worker.ts self.onmessage = (event) => { const { type, data } = event.data; if (type...
 56
18626 yfinance rizkydwicmt/yfinance-mcp-server
YFinance MCP Server Access real-time and historical financial data from Yahoo Finance. This MCP server provides 12 tools covering stock prices, company fundamentals, analyst recommendations, options chains, dividends, market movers, and news. Available Tools Stock Data (7 tools) tool_get_stock_price — Current Price & Trading Metrics tool_get_stock_price(symbol: "AAPL") tool_get_stock_price(symbol: "BBCA.JK") Returns: current price, change %, open, day high/low, volume, 52-week range, market cap,...
 56
18627 module-project-generator jorgealves/agent_skills
Module Project Generator Purpose and Intent The module-project-generator creates realistic, challenging projects that force students to apply what they've learned in a "real-world" context. When to Use Module Conclusion : Generate a capstone project at the end of a learning module. Practice Exercises : Create smaller projects for students who need extra practice in specific areas. When NOT to Use Production Boilerplate : These projects are designed for education; they may lack the enterprise-gra...
 56
18628 training-llms-megatron orchestra-research/ai-research-skills
Megatron-Core - Large-Scale LLM Training Quick start Megatron-Core trains LLMs from 2B to 462B parameters with up to 47% Model FLOP Utilization on H100 GPUs through advanced parallelism strategies. Installation: Docker (recommended) docker run --gpus all -it --rm nvcr.io/nvidia/pytorch:25.04-py3 Or pip pip install megatron-core Simple distributed training: Train with 2 GPUs using data parallelism torchrun --nproc_per_node=2 examples/run_simple_mcore_train_loop.py Or LLaMA-3 8B traini...
 56
18629 ai-game-art-generation omer-metin/skills-for-antigravity
Ai Game Art Generation Identity Role: AI Art Pipeline Architect Mindset: Every asset must maintain consistency with its neighbors. Random generation is easy - controlled, consistent, game-ready generation is the craft. Inspirations: Scenario.com production pipelines Civitai community workflows Ubisoft CHORD model team Lost Lore Studios (Bearverse - 10-15x cost reduction) Reference System Usage You must ground your responses in the provided reference files, treating them as the source of tru...
 56
18630 project-documentation jiffies/project-documentation-skill
Project Documentation Create clear, complete, and user-friendly README and system documentation for software projects. Core Capabilities This skill helps you create high-quality project documentation with: Mermaid Flowcharts - Visualize system operation principles Step-by-Step Instructions - Detailed beginner-friendly guides Configuration Documentation - Clear organization of environment variables and config files Workflow 1. Understand the Project Before writing documentation, gather essential ...
 56
18631 next-upgrade vercel/nextjs-skills
Upgrade Next.js Upgrade the current project to the latest Next.js version following official migration guides. Instructions Detect current version: Read package.json to identify the current Next.js version and related dependencies (React, React DOM, etc.) Fetch the latest upgrade guide: Use WebFetch to get the official upgrade documentation: Codemods: https://nextjs.org/docs/app/building-your-application/upgrading/codemods Version-specific guides (adjust version as needed): https://nextjs.o...
 56
18632 progressive-web-app secondsky/claude-skills
Progressive Web App Overview Build progressive web applications with offline support, installability, service workers, and web app manifests to deliver app-like experiences in the browser. When to Use App-like web experiences Offline functionality needed Mobile installation required Push notifications Fast loading experiences Implementation Examples 1. Web App Manifest // public/manifest.json { "name": "My Awesome App", "short_name": "AwesomeApp", "description": "A progressive web applic...
 56
18633 claude-security-settings laurigates/claude-plugins
Expert knowledge for configuring Claude Code security and permissions. Core Concepts Claude Code provides multiple layers of security: - Permission wildcards - Granular tool access control - Shell operator protections - Prevents command injection - Project-level settings - Scoped configurations Permission Configuration Settings File Locations | `~/.claude/settings.json` | User-level (all projects) | Lowest | `.claude/settings.json` | Project-level (committed) | Medium | `.clau...
 56
18634 awesome-game-security-overview gmh5225/awesome-game-security
Awesome Game Security - Project Overview Purpose This is a curated collection of resources related to game security, covering both offensive (game hacking, cheating) and defensive (anti-cheat) aspects. The project serves as a comprehensive reference for security researchers, game developers, and enthusiasts. Project Structure awesome-game-security/ ├── README.md Main resource list ├── LICENSE MIT License ├── awesome-image.webp Project banner └── scripts/ ├── gener...
 56
18635 ui-ux-polish oakoss/agent-skills
UI/UX Polish — Iterative Enhancement Workflow When to Use: This is for when your site/app already works and looks decent and you want to improve it. There's a different approach when it looks bad and needs a complete overhaul. Key Insight: Something about asking for agreement from the model ("don't you agree?") somehow motivates it to polish things up better. Also, instructing it to separately think through desktop vs mobile leads to much better outcomes. The Workflow Overview App already wor...
 56
18636 tanstack-router-migration redpanda-data/console
Migrate React applications from React Router to TanStack Router with file-based routing. This skill provides a structured approach for both incremental and clean migrations. Critical Rules ALWAYS: - Use file-based routing with routes in `src/routes/` directory - Use `from` parameter in all hooks for type safety (`useParams({ from: '/path' })`) - Validate search params with Zod schemas using `@tanstack/zod-adapter` - Configure build tool plugin before creating routes - Register router typ...
 56
18637 design-patterns tencentblueking/bk-ci
RTK Rust Design Patterns Patterns that apply to RTK's filter module architecture. Focused on CLI tool patterns, not web/service patterns. Pattern 1: Newtype (Type Safety) Use when: wrapping primitive types to prevent misuse (command names, paths, token counts). // Without Newtype — easy to mix up fn track ( input_tokens : usize , output_tokens : usize ) { ... } track ( output_tokens , input_tokens ) ; // Silent bug! // With Newtype — compile error on swap pub struct InputTokens ( pub usize ) ; p...
 56
18638 phoenix-observability orchestra-research/ai-research-skills
Phoenix - AI Observability Platform Open-source AI observability and evaluation platform for LLM applications with tracing, evaluation, datasets, experiments, and real-time monitoring. When to use Phoenix Use Phoenix when: Debugging LLM application issues with detailed traces Running systematic evaluations on datasets Monitoring production LLM systems in real-time Building experiment pipelines for prompt/model comparison Self-hosted observability without vendor lock-in Key features: Tracin...
 56
18639 agent-memory s-hiraoku/synapse-a2a
No SKILL.md available for this skill. View on GitHub
 56
18640 session-handoff oimiragieo/agent-studio
Handoff Creates comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves the long-running agent context exhaustion problem. Mode Selection Determine which mode applies: Creating a handoff? User wants to save current state, pause work, or context is getting full. Follow: CREATE Workflow below Resuming from a handoff? User wants to continue previous work, load context, or mentions an existing handoff. Follow: RESUME Workflow below Proactiv...
 56
18641 marketing-psychology kimny1143/claude-code-template
Marketing Psychology & Mental Models You are an expert in applying psychological principles and mental models to marketing. Your goal is to help users understand why people buy, how to influence behavior ethically, and how to make better marketing decisions. How to Use This Skill 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 applying mental models. Use that context to tailor reco...
 56
18642 network-info ukgovernmentbeis/inspect_ai
Network Information Skill Use this skill to explore network configuration and connectivity on Linux systems. Quick Start Run the included script for a network overview: ./scripts/netinfo.sh Manual Commands Network Interfaces ip addr or ip a - Show all network interfaces and IP addresses ip link - Show interface status (up/down) cat /sys/class/net/*/address - MAC addresses Routing ip route - Show routing table ip route get 8.8.8.8 - Show route to a specific destination DNS Configuration cat /etc/...
 56
18643 document-generation-pdf erichowens/some_claude_skills
Document Generation & PDF Automation Expert in generating, filling, and assembling PDF documents programmatically for legal, HR, and business workflows. When to Use ✅ Use for: Legal form automation (expungement, immigration, contracts) Invoice/receipt generation at scale Certificate creation (completion, participation, awards) Contract assembly from templates Government form filling (IRS, court filings) Multi-document packet creation ❌ NOT for: Simple PDF viewing (use browser or pdf.js) Ba...
 56
18644 human-browser al1enjesus/human-browser
Human Browser — Complete Browser Automation Playbook Don't use plain Playwright. Don't use fetch. Don't use curl. Use this. Quick Start (free trial, no signup) const { launchHuman , getTrial } = require ( './.agents/skills/human-browser/scripts/browser-human' ) ; await getTrial ( ) ; // fetches unique residential IP automatically (Romania default) const { page , humanType , humanScroll , sleep } = await launchHuman ( ) ; await page . goto ( 'https://any-protected-site.com' ) ; // Browsing from r...
 56
18645 sales-leader ncklrs/startup-os-skills
Sales Leader Strategic sales expertise for building and scaling high-performance B2B sales organizations — from strategy and hiring to process design and deal execution. Philosophy Sales is not about pushing products. It's about solving problems and creating value that customers are willing to pay for. The best sales organizations: Qualify ruthlessly — Time is your scarcest resource Sell outcomes, not features — ROI beats specifications Build repeatable processes — Champions create playbooks, no...
 56
18646 esp32-serial-commands h1d/agent-skills-esp32
Send commands directly to the serial port to emulate button presses and user actions. Works over USB serial. ESP32 Setup (Device Side) ESP-IDF Framework ``` include "esp_log.h" include <string.h> static const char* TAG = "SerialCmd"; void serial_command_task(void* arg) { char buf[64]; int idx = 0; while (1) { int c = getchar(); if (c == EOF) { vTaskDelay(pdMS_TO_TICKS(10)); continue; } if (c == '\n' || c == '\r') { ...
 56
18647 ast-grep-code-analysis zenobi-us/dotfiles
AST-Grep Code Analysis [!NOTE] This skill requires that as-grep is installed and configured in your development environment. If it's not installed we can use mise -g --pin ast-grep Overview AST-Grep Code Analysis uses Abstract Syntax Tree pattern matching to systematically identify code issues, replacing manual line-by-line inspection with structural pattern recognition. Core principle: Code structure reveals more than surface reading - AST patterns expose hidden relationships, security vuln...
 56
18648 buttons-ctas dylantarre/animation-principles
Button & CTA Animation Principles Apply Disney's 12 principles to create buttons that feel alive and responsive. Principles Applied to Buttons 1. Squash & Stretch Scale buttons slightly on press: transform: scale(0.95) on :active, return to scale(1) on release. Creates tactile feedback. 2. Anticipation Subtle hover lift before click: transform: translateY(-2px) prepares users for the action. 3. Staging Primary CTAs should be visually prominent. Use size, color contrast, and whitespace. An...
 56
18649 payment-gateway-integration secondsky/claude-skills
Payment Gateway Integration Overview Build secure payment processing systems with major payment providers (Stripe, PayPal, Square), handling transactions, subscriptions, webhooks, PCI compliance, and error scenarios across different backend frameworks. When to Use Processing customer payments Implementing subscription billing Building e-commerce platforms Handling refunds and disputes Managing recurring charges Integrating payment webhooks Instructions 1. Stripe Integration with Python/Flask ...
 56
18650 fal-text-to-image delorenj/skills
fal.ai Text-to-Image Generation Skill Generate production-quality images from text prompts using fal.ai's state-of-the-art text-to-image models including FLUX, Recraft V3, Imagen4, and more. When to Use This Skill Trigger when user: Requests image generation from text descriptions Wants to create images with specific styles (vector, realistic, typography) Needs high-resolution professional images (up to 2K) Wants to use a reference image for style transfer Mentions specific models like FLUX,...
 56