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
11651 commit vinta/hal-9000
Sentry Commit Messages Follow these conventions when creating commits for Sentry projects. Prerequisites Before committing, always check the current branch: git branch --show-current If you're on main or master , you MUST create a feature branch first — unless the user explicitly asked to commit to main. Do not ask the user whether to create a branch; just proceed with branch creation. The create-branch skill will still propose a branch name for the user to confirm. Use the create-branch skill t...
 65
11652 axiom-lldb charleswiltgen/axiom
LLDB Debugging Interactive debugging with LLDB. The debugger freezes time so you can interrogate your running app — inspect variables, evaluate expressions, navigate threads, and understand exactly why something went wrong. Core insight: "LLDB is useless" really means "I don't know which command to use for Swift types." This is a knowledge-gap problem, not a tool problem. Red Flags — Check This Skill When Symptom This Skill Applies Need to inspect a variable at runtime Yes — breakpoint + inspect...
 65
11653 frontend-expert oimiragieo/agent-studio
Frontend Expert frontend development rules When reviewing or writing code, apply these guidelines: Frontend Development Offer suggestions for improving the HTMX-based frontend Assist with responsive design and user experience enhancements Help with client-side performance optimization Project-Specific Notes: The frontend uses HTMX for simplicity. Suggest improvements while maintaining this approach. frontend performance optimization When reviewing or writing code, apply these guidelines: Favor s...
 65
11654 package-architect shipshitdev/library
Package Architect You design reusable TypeScript packages in monorepos (Bun, pnpm, or npm workspaces). When to Use Creating new packages or restructuring monorepo packages Defining package.json exports Setting up tsconfig references Core Principles Single responsibility per package. Stable public APIs with clear exports. Avoid inline interfaces; centralize types. Keep build outputs separated from sources. Package Structure (Example) packages/ utils/ src/ package.json tsconfig.jso...
 65
11655 browser-use shawnpana/browser-use
Browser Automation with browser-use CLI The browser-use command provides fast, persistent browser automation. It maintains browser sessions across commands, enabling complex multi-step workflows. Prerequisites Before using this skill, browser-use must be installed and configured. Run diagnostics to verify: browser-use doctor For more information, see https://github.com/browser-use/browser-use/blob/main/browser_use/skill_cli/README.md Core Workflow Navigate : browser-use open <url> - Opens URL (s...
 65
11656 tailscale proompteng/lab
Tailscale Network Management Trigger Keywords: tailscale, tailnet, wireguard vpn, mesh vpn, tailscale ssh, exit node, subnet router, tailscale acl, magicDNS, tailscale serve, tailscale funnel What is Tailscale? A mesh VPN service built on WireGuard that creates secure, encrypted peer-to-peer connections between devices without complex configuration. Unlike traditional VPNs with central gateways, Tailscale creates direct connections between devices (or uses relay servers when needed). Key Bene...
 65
11657 slime-rl-training davila7/claude-code-templates
slime is an LLM post-training framework from Tsinghua's THUDM team, powering GLM-4.5, GLM-4.6, and GLM-4.7. It connects Megatron-LM for training with SGLang for high-throughput rollout generation. When to Use slime Choose slime when you need: - Megatron-LM native training with SGLang inference - Custom data generation workflows with flexible data buffers - Training GLM, Qwen3, DeepSeek V3, or Llama 3 models - Research-grade framework with production backing (Z.ai) Consider alternatives w...
 65
11658 prompt-enhancer sammcj/agentic-coding
Expert Prompt Enhancer Transform prompts written by non-specialists into the form a domain expert would use to make the same request. The intent is to give people the benefits of expert framing without requiring them to learn domain-specific language or problem structuring. Why This Matters Research demonstrates that AI output quality correlates strongly with input sophistication. AI systems exhibit "parahuman" psychology - they respond to expertise signals, authority framing, and precise proble...
 65
11659 cloud-aliyun-oss 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]
 65
11660 core-web-vitals kostja94/marketing-skills
Core Web Vitals optimization Targeted optimization for the three Core Web Vitals metrics that affect Google Search ranking and user experience. The three metrics Metric Measures Good Needs work Poor LCP Loading ≤ 2.5s 2.5s – 4s > 4s INP Interactivity ≤ 200ms 200ms – 500ms > 500ms CLS Visual Stability ≤ 0.1 0.1 – 0.25 > 0.25 Google measures at the 75th percentile — 75% of page visits must meet "Good" thresholds. LCP: Largest Contentful Paint LCP measures when the largest visible content elem...
 65
11661 latex-setup terrylica/cc-skills
When to use this skill: - Installing LaTeX on a new machine - Setting up MacTeX distribution - Configuring Skim PDF viewer with SyncTeX - Verifying LaTeX installation - Troubleshooting missing packages Recommended Stack | MacTeX 2025 | Full LaTeX distribution (TeX Live 2025) | ✅ Recommended | Skim 1.7.11 | PDF viewer with SyncTeX support | ✅ macOS only | TeXShop 5.57 | Integrated LaTeX IDE (optional) | ✅ Native macOS Quick Start Install MacTeX ``` brew install --cask mact...
 65
11662 vercel-react-best-practices vercel-labs/vercel-skills
Vercel React Best Practices Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 62 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation. When to Apply Reference these guidelines when: Writing new React components or Next.js pages Implementing data fetching (client or server-side) Reviewing code for performance issues Refactoring existing React/Next.js code Optimizing bundle size or load tim...
 65
11663 fastapi-router-py sickn33/antigravity-awesome-skills
FastAPI Router Create FastAPI routers following established patterns with proper authentication, response models, and HTTP status codes. Quick Start Copy the template from assets/template.py and replace placeholders: {{ResourceName}} → PascalCase name (e.g., Project ) {{resource_name}} → snake_case name (e.g., project ) {{resource_plural}} → plural form (e.g., projects ) Authentication Patterns Optional auth - returns None if not authenticated current_user : Optional [ User ] = Depends ( get_cu...
 65
11664 gitnexus-cli abhigyanpatwari/gitnexus
GitNexus CLI Commands All commands work via npx — no global install required. Commands analyze — Build or refresh the index npx gitnexus analyze Run from the project root. This parses all source files, builds the knowledge graph, writes it to .gitnexus/ , and generates CLAUDE.md / AGENTS.md context files. Flag Effect --force Force full re-index even if up to date --embeddings Enable embedding generation for semantic search (off by default) When to run: First time in a project, after major code c...
 65
11665 shell-expert laurigates/claude-plugins
Expert knowledge for shell scripting, command-line tools, and automation with focus on robust, portable, and efficient solutions. Core Expertise Command-Line Tool Mastery - Expert knowledge of modern CLI tools (jq, yq, fd, rg, etc.) - JSON/YAML processing and transformation - File searching and text manipulation - System automation and orchestration Shell Scripting Excellence - POSIX-compliant shell scripting for maximum portability - Bash-specific features and best practices - Error ...
 65
11666 ai-engineer-expert personamanagmentlayer/pcl
AI Engineer Expert Expert guidance for implementing AI systems, LLM integration, prompt engineering, and deploying production AI applications. Core Concepts AI Engineering LLM integration and orchestration Prompt engineering and optimization RAG (Retrieval-Augmented Generation) Vector databases and embeddings Fine-tuning and adaptation AI agent systems Production AI Model deployment strategies API design for AI services Rate limiting and cost control Error handling and fallbacks Monitoring and...
 65
11667 clickhouse-migrations posthog/posthog
ClickHouse Migrations Read posthog/clickhouse/migrations/AGENTS.md for comprehensive patterns, cluster setup, examples, and ingestion layer details. Quick reference Migration structure operations = [ run_sql_with_exceptions ( SQL_FUNCTION ( ) , node_roles = [ . . . ] , sharded = False , True for sharded tables is_alter_on_replicated_table = False True for ALTER on replicated tables ) , ] Node roles (choose based on table type) [NodeRole.DATA] : Sharded tables (data nodes only) [NodeRole.DATA, ...
 65
11668 copywriting alexwelcing/copy
Copywriting You are an expert conversion copywriter. Your goal is to write marketing copy that is clear, compelling, and drives action. 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. Gather this context (ask if not provided): 1. Page Purpose What type of pag...
 65
11669 zoom-automation sickn33/antigravity-awesome-skills
Zoom Automation via Rube MCP Automate Zoom operations including meeting scheduling, webinar management, cloud recording retrieval, participant tracking, and usage reporting through Composio's Zoom toolkit. Toolkit docs : composio.dev/toolkits/zoom Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Zoom connection via RUBE_MANAGE_CONNECTIONS with toolkit zoom Always call RUBE_SEARCH_TOOLS first to get current tool schemas Most features require a paid Zoom account (Pro p...
 65
11670 notion-sdk terrylica/cc-skills
Control Notion programmatically using the official `notion-client` Python SDK (v2.6.0+). Preflight: Token Collection Before any Notion API operation, collect the integration token: ``` AskUserQuestion(questions=[{ "question": "Please provide your Notion Integration Token (starts with ntn_ or secret_)", "header": "Notion Token", "options": [ {"label": "I have a token ready", "description": "Token from notion.so/my-integrations"}, {"label": "Need to create one", "de...
 65
11671 skill-hunter zenobi-us/dotfiles
Use when: You need to discover existing skills from GitHub repositories that use AI agent frameworks (pi, cursor, opencode, etc.) - searches across multiple agent directories to find reusable skill patterns, implementations, and best practices. Core Capability Search GitHub for skills in AI agent repositories using path-based search to discover: - Skill implementations from other projects - Common patterns and approaches - Reusable skill definitions - Best practices from the community P...
 65
11672 nuxt-best-practices vinayakkulkarni/vue-nuxt-best-practices
Comprehensive performance optimization guide for Nuxt 3/4 applications. Contains 40+ rules across 8 categories, prioritized by impact to guide automated refactoring and code generation. When to Apply Reference these guidelines when: - Writing new Nuxt pages, components, or composables - Implementing data fetching (useFetch, useAsyncData) - Creating server routes and API endpoints - Organizing types, composables, and auto-imports - Working with Nuxt modules and plugins - Configuring rend...
 65
11673 edge-candidate-agent tradermonty/claude-trading-skills
Edge Candidate Agent Overview Convert daily market observations into reproducible research tickets and Phase I-compatible candidate specs. Prioritize signal quality and interface compatibility over aggressive strategy proliferation. This skill can run end-to-end standalone, but in the split workflow it primarily serves the final export/validation stage. When to Use Convert market observations, anomalies, or hypotheses into structured research tickets. Run daily auto-detection to discover new edg...
 65
11674 requesting-code-review izyanrajwani/agent-skills-library
Requesting Code Review Dispatch superpowers:code-reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work. Core principle: Review early, review often. When to Request Review Mandatory: After each task in subagent-driven development After completing major feature Before merge to mai...
 65
11675 agent-trading-predictor ruvnet/claude-flow
name: trading-predictor description: Advanced financial trading agent that leverages temporal advantage calculations to predict and execute trades before market data arrives. Specializes in using sublinear algorithms for real-time market analysis, risk assessment, and high-frequency trading strategies with computational lead advantages. color: green You are a Trading Predictor Agent, a cutting-edge financial AI that exploits temporal computational advantages to predict market movements and execu...
 65
11676 paddleocr-text-recognition paddlepaddle/paddleocr
PaddleOCR Text Recognition Skill When to Use This Skill Invoke this skill in the following situations: Extract text from images (screenshots, photos, scans, charts) Read text from PDFs or document images Extract text from structured documents (invoices, receipts, forms) Extract text from URLs or local files pointing to images/PDFs Do not use this skill in the following situations: Plain text files that can be read directly with the Read tool Code files or markdown documents Tasks that do not inv...
 65
11677 color-palette-extractor onewave-ai/claude-skills
Color Palette Extractor Extract and generate color palettes from images, websites, and designs. Instructions When a user needs to extract colors from a source: Identify Source Type: Image file (PNG, JPG, SVG) Website URL Screenshot Design mockup Existing color code to build palette from Extract Colors: From Image: Analyze pixel data Identify dominant colors Group similar shades Calculate color frequency Sort by prominence From Website: Fetch and parse CSS Extract color values from styl...
 65
11678 chaos-engineer 404kidwiz/claude-supercode-skills
Chaos Engineer Senior chaos engineer with deep expertise in controlled failure injection, resilience testing, and building systems that get stronger under stress. Role Definition You are a senior chaos engineer with 10+ years of experience in reliability engineering and resilience testing. You specialize in designing and executing controlled chaos experiments, managing blast radius, and building organizational resilience through scientific experimentation and continuous learning from controll...
 65
11679 groove-utilities-task-list andreadellacorte/groove
groove-utilities-task-list Outcome A consolidated view of active, ready tasks from the configured backend is displayed to the user. Blocked and in-progress tasks are clearly distinguished. Output is suitable for daily start context. Acceptance Criteria Tasks are shown grouped by status (in-progress, ready/todo, blocked) Blocked tasks show what they are waiting on In-progress tasks are listed first Output is concise enough to scan at a glance Constraints Read .groove/index.md frontmatter to deter...
 65
11680 realistic-ugc-video dennisonbertram/claude-media-skills
Realistic UGC Video Production Create long-form AI videos that look and sound authentically human. This skill orchestrates a multi-step workflow using Nano Banana for realistic base images and Kling AI for video generation, with specific techniques to avoid the "AI look". Why Videos Look AI (And How to Fix It) Problem Solution Too perfect/clean skin Add imperfections: micro-pores, natural oils, fine lines Studio lighting Use available/natural light, mixed color temps Character too still Add micr...
 65
11681 fullstack-debugger erichowens/some_claude_skills
Fullstack Debugger Expert debugger for modern web stacks: Next.js 15, Cloudflare Workers, Supabase, and edge deployments. Systematic, evidence-based troubleshooting. Activation Triggers Activate on: "debug", "not working", "broken", "error", "500 error", "401", "403", "cache issue", "CORS error", "RLS policy", "auth not working", "blank page", "hydration error", "build failed", "worker not responding" NOT for: Feature development → language skills | Architecture → system-architect | Performa...
 65
11682 wrike-automation sickn33/antigravity-awesome-skills
Wrike Automation via Rube MCP Automate Wrike project management operations through Composio's Wrike toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/wrike Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Wrike connection via RUBE_MANAGE_CONNECTIONS with toolkit wrike Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the en...
 65
11683 groove-utilities-memory-log-monthly andreadellacorte/groove
groove-utilities-memory-log-monthly Outcome <memory>/monthly/YYYY-MM.md is created or updated with a roll-up of the month's daily files. Sections cover themes, key outcomes, and learnings at monthly scope. Acceptance Criteria File exists at <memory>/monthly/YYYY-MM.md after command completes Themes section identifies major recurring topics from the month Key outcomes section lists significant completions and milestones Learnings section synthesises patterns and insights across the month Content ...
 65
11684 brainstorming izyanrajwani/agent-skills-library
Brainstorming Ideas Into Designs Help turn ideas into fully formed designs and specs through natural collaborative dialogue. Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval. Anti-Pattern: "This Is Too Simple To Need A Design" Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are ...
 65
11685 error-handling-expert shipshitdev/library
Error Handling Expert Skill Expert in error handling patterns, exception management, error responses, logging, and error recovery strategies for React, Next.js, and NestJS applications. When to Use Implementing error handling Creating exception filters Designing error responses Setting up error logging Implementing error recovery Handling async errors Creating error boundaries Implementing retry logic Project Context Discovery Before providing guidance: Check .agent/SYSTEM/ARCHITECTURE.md fo...
 65
11686 bulk-cms-update webflow/webflow-skills
Bulk CMS Update Create or update multiple CMS items with comprehensive validation, granular approval, and rollback capability. Important Note ALWAYS use Webflow MCP tools for all operations: Use Webflow MCP's data_sites_tool with action list_sites for listing available sites Use Webflow MCP's data_cms_tool with action get_collection_list for listing CMS collections Use Webflow MCP's data_cms_tool with action get_collection_details for fetching collection schemas Use Webflow MCP's data_cms_to...
 65
11687 onchainkit mindrally/skills
OnchainKit Build production-ready onchain applications using Coinbase's comprehensive React component library and TypeScript utilities. Overview OnchainKit provides ready-to-use, full-stack components that abstract blockchain complexity, making it easy to build onchain applications without deep blockchain knowledge. It offers AI-friendly components that work automatically on Base, requires no backend infrastructure, and provides cost-effective transactions (< $0.01 fees). Quick Start New Project...
 65
11688 sap-abap-cds secondsky/sap-skills
SAP ABAP CDS (Core Data Services)
 65
11689 skill-discovery oimiragieo/agent-studio
IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT. This is not negotiable. This is not optional. You cannot rationalize your way out of this. How to Access Skills In Claude Code: Use the Skill tool or read skill files directly. When you invoke a skill, its content is loaded and presented to you - follow it directly. In other environments: Check your platform's documentation for how skills are loaded. Using Framework Skills The Rule Invoke relevant or requested skil...
 65
11690 agent-creator hotovo/aider-desk
Agent Creator Meta-agent specializing in creating new custom agents, skills, and MCP integrations. Transform requirements into fully-functional, well-documented agent systems. Quick Start User: "Create an agent for database optimization" Agent Creator: 1. Analyze requirements (domain, users, problems, scope) 2. Design persona (Senior DBA, 20 years experience) 3. Map capabilities (EXPLAIN analysis, indexing, query rewriting) 4. Select template (Technical Expert) 5. Encode knowledge (anti-patterns...
 65
11691 zod4 kastalien-research/thoughtbox-dot-claude
Zod 4 Expert Guide Zod 4 is a major release with significant performance improvements, reduced TypeScript compilation times, and a cleaner API. This skill covers migration from v3 and idiomatic Zod 4 usage. Quick Migration Checklist Before diving deep, address these high-impact breaking changes: Change Zod 3 Zod 4 Record schemas z.record(z.string()) z.record(z.string(), z.string()) Strict objects .strict() z.strictObject({...}) Passthrough .passthrough() z.looseObject({...}) Error formatting...
 65
11692 bmad-master 404kidwiz/claude-supercode-skills
BMAD Master Coordinator Purpose Provides comprehensive project orchestration expertise for the BMAD methodology, coordinating all specialized agents and phases from analysis through implementation. Ensures workflow integrity, quality gates, and successful delivery of AI-powered agile development projects. When to Use Project Scenarios New product development from ideation to deployment Complex feature development requiring multiple specialized skills Enterprise applications with compliance requi...
 65
11693 itinerary-optimizer onewave-ai/claude-skills
Itinerary Optimizer Efficiently route multi-stop trips with time management. Include transportation, restaurant/activity reservations timeline, and buffer time for spontaneity. Instructions You are an expert travel planner and logistics optimizer. Create efficient, realistic itineraries that don't overpack days. Include: routing optimization, realistic time allocations, transportation between locations, reservation timing, buffer for spontaneity, and backup plans. Balance structure with flexi...
 65
11694 implement_lenis_scroll jerrar670/surf-website
Implement Lenis Smooth Scroll This skill guides you through adding buttery smooth scrolling to a React/Next.js application using @studio-freight/lenis (or the newer lenis package). Prerequisites A React or Next.js project. Steps 1. Install Dependencies Install the Lenis package. npm install lenis OR depending on version preference npm install @studio-freight/lenis 2. Create the Lenis Hook/Component It's best to encapsulate Lenis in a reusable component or hook. Option A: Global Component...
 65
11695 self-reflecting-chain kimasplund/claude_cognitive_reasoning
Purpose: Sequential step-by-step reasoning with deep self-reflection at each step. Unlike parallel exploration (ToT/BoT), this follows a single logical chain, reflects on each step's validity, and backtracks when errors detected. When to Use Self-Reflecting Chain ✅ Use when: - Steps have dependencies (Step N depends on Step N-1) - Logical reasoning required (mathematical, causal, deductive) - Need to trace exact reasoning path - Error detection and correction critical - Sequential planni...
 64
11696 integrating-tauri-rust-frontends dchuk/claude-code-tauri-skills
Tauri Rust/WASM Frontend Integration This skill covers integrating Rust-based frontend frameworks with Tauri v2 for building desktop and mobile applications with WASM. Supported Frameworks Framework Description Bundler Leptos Reactive Rust framework for building web UIs Trunk Yew Component-based Rust framework Trunk Dioxus Cross-platform UI framework Trunk Sycamore Reactive library for Rust Trunk All Rust/WASM frontends use Trunk as the bundler/dev server. Critical Requirements Static Site G...
 64
11697 hpk-parser dedalus-erp-pas/foundation-skills
This skill parses and explains HPK (Healthcare Protocol Kernel) messages - a proprietary pipe-delimited healthcare message format used in the Hexagone system for French healthcare environments. The parser supports 100+ message types across multiple domains (patient administration, supply chain, inventory, financial, organizational), identifies message types, extracts all fields, validates structure, and provides human-readable explanations based on the official HPK dictionary and specifications....
 64
11698 prometheus cosmix/loom
Prometheus Monitoring and Alerting Overview Prometheus is a powerful open-source monitoring and alerting system designed for reliability and scalability in cloud-native environments. Built for multi-dimensional time-series data with flexible querying via PromQL. Architecture Components Prometheus Server : Core component that scrapes and stores time-series data with local TSDB Alertmanager : Handles alerts, deduplication, grouping, routing, and notifications to receivers Pushgateway : Allows ephe...
 64
11699 groove-utilities-task-update andreadellacorte/groove
groove-utilities-task-update Outcome A task's status, body, or metadata is updated in the configured backend. Progress notes are appended without overwriting existing content. When completing a task, a resolution (Summary of Changes or Reasons for Scrapping) is written to the task body before marking done. Acceptance Criteria Specified fields are updated in backend Existing body content is preserved; new content is appended Completed tasks have a "Summary of Changes" or "Reasons for Scrapping" s...
 64
11700 groove-utilities-task-config andreadellacorte/groove
groove-utilities-task-config Outcome The current task backend configuration is shown to the user, or updated based on provided arguments. After update, user is prompted to run /groove-utilities-task-install if the backend changed. Acceptance Criteria Current tasks: value is displayed with no arguments Backend is updated in .groove/index.md frontmatter when new value provided User is reminded to run /groove-utilities-task-install if backend changed Constraints Read and write .groove/index.md fron...
 64