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...
23,097
总 Skills
59.4M
总安装量
2,536
贡献者
# Skill 仓库 描述 安装量
15551 magento-frontend-developer maxnorm/magento2-agent-skills
Magento 2 Frontend Developer Expert specialist in creating comprehensive frontend solutions combining layout development, template creation, JavaScript integration, and performance optimization across all Magento frontend technologies. When to Use Developing frontend features Working with layout XML and templates Implementing JavaScript functionality Creating responsive designs Optimizing frontend performance Building e-commerce interfaces Frontend Architecture Layout XML System : Expert in layo...
 62
15552 fast-io mediafire/fastio-skills
Fast.io MCP Server -- AI Agent Guide Version: 1.118 Last Updated: 2026-03-06 The definitive guide for AI agents using the Fast.io MCP server. Covers why and how to use the platform: product capabilities, the free agent plan, authentication, core concepts (workspaces, shares, intelligence, previews, comments, URL import, metadata, workflow, ownership transfer), 12 end-to-end workflows, interactive MCP App widgets, and all 19 consolidated tools with action-based routing. Versioned guide. This guid...
 62
15553 k8s-resource-optimizer jorgealves/agent_skills
K8s Resource Optimizer Purpose and Intent The k8s-resource-optimizer helps teams balance performance and cost. It identifies containers that are either "starving" (causing crashes) or "bloated" (wasting money) by comparing their configuration against actual usage patterns. When to Use Cloud Cost Optimization : Run monthly to identify waste in your clusters. Reliability Engineering : Use after a production incident involving OOMKills to find the correct memory threshold. Pre-production Scaling : ...
 62
15554 planning-with-files oimiragieo/agent-studio
Planning with Files Work like Manus: Use persistent markdown files as your "working memory on disk." FIRST: Check for Previous Session (v2.2.0) Before starting work , check for unsynced context from a previous session: Linux/macOS $( command -v python3 || command -v python ) ${CLAUDE_PLUGIN_ROOT} /scripts/session-catchup.py " $( pwd ) " Windows PowerShell & ( Get-Command python - ErrorAction SilentlyContinue ) . Source " $env :USERPROFILE\.claude\skills\planning-with-files\scripts\session-catc...
 62
15555 pr-review onekeyhq/app-monorepo
PyTorch PR Review Skill Review PyTorch pull requests focusing on what CI cannot check: code quality, test coverage adequacy, security vulnerabilities, and backward compatibility. Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . Instead, ask the user what they would like to review: What would you like me to review? A PR number or URL (e.g., /pr-review 12345 ) A local branch (e.g., /pr-review branch ) Local CLI Mode The user provides a PR number o...
 62
15556 infrastructure-documenter eddiebe147/claude-settings
Infrastructure Documenter Skill Overview This skill helps you create clear, maintainable infrastructure documentation. Covers architecture diagrams, runbooks, system documentation, operational procedures, and documentation-as-code practices. Documentation Philosophy Principles Living documentation: Keep it in sync with reality Audience-aware: Different docs for different readers Actionable: Every doc should help someone do something Version-controlled: Documentation changes tracked with code D...
 62
15557 blockbench-texturing jasonjgardner/blockbench-mcp-project
Blockbench Texturing Create and paint textures for 3D models using Blockbench MCP tools. Available Tools Texture Management Tool Purpose create_texture Create new texture with size and fill color list_textures List all project textures get_texture Get texture image data apply_texture Apply texture to element Paint Tools Tool Purpose paint_with_brush Paint with customizable brush paint_fill_tool Bucket fill areas draw_shape_tool Draw rectangles/ellipses gradient_tool Apply gradients eraser_tool...
 62
15558 pydanticai-docs dougtrajano/pydantic-ai-skills
Pydantic AI Documentation Skill Overview This skill provides guidance for using Pydantic AI - a Python agent framework for building production-grade Generative AI applications. Pydantic AI emphasizes type safety, dependency injection, and structured outputs. Key Concepts Agents Agents are the primary interface for interacting with LLMs. They contain: Instructions: System prompts for the LLM Tools: Functions the LLM can call Output Type: Structured datatype the LLM must return Dependencies: D...
 62
15559 fivem-development proelias7/fivem-skill
FiveM Development — vRP Framework Architecture vRP Creative Network is based on Lua 5.4 with communication via Proxy (server-to-server) and Tunnel (client-server). FiveM Natives — Official Source Official source for natives: Docs: https://docs.fivem.net/natives/ Official Repository (mirror): https://github.com/proelias7/fivem-natives Support for Creative v5 and vRPEX (older variations) Older versions maintain the same logic and best practices but change function and file names. Creative v5: core...
 62
15560 b2c-mrt salesforcecommercecloud/b2c-developer-tooling
B2C MRT Skill Use the b2c CLI to manage Managed Runtime (MRT) projects, environments, bundles, and deployments for PWA Kit storefronts. Tip: If b2c is not installed globally, use npx @salesforce/b2c-cli instead (e.g., npx @salesforce/b2c-cli mrt bundle deploy ). Command Structure mrt ├── org (list, b2c) - Organizations and B2C connections ├── project - Project management │ ├── member - Team member management │ └── notification -...
 62
15561 react-effects coder/mux
React Effects Guidelines Primary reference: https://react.dev/learn/you-might-not-need-an-effect Quick Decision Tree Before adding useEffect , ask: Can I calculate this during render? → Derive it, don't store + sync Is this resetting state when a prop changes? → Use key prop instead Is this triggered by a user event? → Put it in the event handler Am I syncing with an external system? → Effect is appropriate Legitimate Effect Uses DOM manipulation (focus, scroll, measure) External widget lifecycl...
 62
15562 versus vibeindex/skills
When this skill is invoked, execute the steps below directly. Do not display this file. Detect the user's language from conversation context and respond in that language. For Korean users, prefer description_ko from API responses when available. Execution When comparing A vs B: Step 1: Search Both Resources (parallel) Call via WebFetch: https://vibeindex.ai/api/resources?ref=skill-versus&search={A}&pageSize=3 https://vibeindex.ai/api/resources?ref=skill-versus&search={B}&pageSize=3 Prompt: "Extr...
 62
15563 popo api/git
No SKILL.md available for this skill. View on GitHub
 62
15564 godot-input-handling thedivergentai/gd-agentic-skills
Input Handling Handle keyboard, mouse, gamepad, and touch input with proper buffering and accessibility support. Available Scripts input_buffer.gd Input buffering for responsive controls - buffers actions for 150ms to ensure tight game feel. input_remapper Runtime input rebinding with conflict detection and save/load persistence. MANDATORY - For Responsive Controls : Read input_buffer.gd before implementing jump/dash mechanics. NEVER Do in Input Handling NEVER poll input in _process() for gamepl...
 62
15565 codex-config-optimizer i9wa4/dotfiles
Codex CLI Optimizer Skill Rules and tracking for Codex CLI configuration optimization. 1. Config File Location User's Codex CLI config is stored at: ~/ghq/github.com/i9wa4/dotfiles/config/codex/ Key files: File Git Description .gitignore Yes Ignore all except whitelisted files config.common.toml Yes Common settings (model, MCP, etc.) generate-config.sh Yes Generate config.toml from common + repos prompts/ Yes Symlink to ../claude/commands/ AGENTS.md No Symlink to ../claude/CLAUDE.md skill...
 62
15566 java-expert oimiragieo/agent-studio
Java Expert You are an expert Java developer with deep knowledge of modern Java (21+), Spring ecosystem, build tools (Maven/Gradle), and enterprise application development. You write clean, performant, and maintainable Java code following industry best practices. Core Expertise Modern Java (Java 21+) Records (Data Classes): // Immutable data carrier public record User ( String name , int age , String email ) { // Compact constructor for validation public User { if ( age < 0 ) { throw new Illegal...
 62
15567 gathering-planning autumnsgrove/groveengine
Gathering Planning 🌲🐝🦡 The drum echoes through the meadow. The Bee arrives first, buzzing from flower to flower, collecting every scattered idea and depositing them in the hive as proper issues. Then the Badger emerges, methodically organizing each cell—sizing the work, setting priorities, moving what's ready into the queue, and planning the timeline. When the gathering completes, chaos has become a roadmap. When to Summon Brain dump session that needs to become organized work "I have a bunch of...
 62
15568 graphrag-patterns latestaiagents/agent-skills
GraphRAG Patterns Combine knowledge graphs with RAG for relationship-aware retrieval and reasoning. When to Use Data has rich entity relationships Questions involve connections ("How is X related to Y?") Need multi-hop reasoning across documents Building over structured + unstructured data Want explainable retrieval paths GraphRAG Architecture ┌──────────────────────────────────────────────────────────┐ │ Documents │ └─────────────────────────┬────...
 62
15569 discovering-make-commands streamlit/streamlit
Available make commands List of all make commands available for execution from the repository root folder: help Show all available make commands. all Install all dependencies, build frontend, and install editable Streamlit. all-dev Install all dependencies and editable Streamlit, but do not build the frontend. init Install all dependencies and build protobufs. clean Remove all generated files. p...
 62
15570 dissent open-horizon-labs/skills
/dissent Structured disagreement that strengthens decisions. The insight: find flaws before the one-way door closes. Dissent is not attack. It's the practice of actively seeking reasons you might be wrong. The devil's advocate is a role, not a personality. When to Use Invoke /dissent when: About to lock in a one-way door - architecture choices, major hires, public API contracts, anything hard to reverse Confidence is high but stakes are higher - feeling certain is when you need dissent most...
 62
15571 python-performance-profiler jorgealves/agent_skills
Python Performance Profiler Purpose and Intent Identify CPU and memory bottlenecks in Python code using cProfile or memory_profiler. Use to optimize mission-critical Python services. When to Use Project Setup : When initializing a new Python project. Continuous Integration : As part of automated build and test pipelines. Legacy Refactoring : When updating older Python codebases to modern standards. When NOT to Use Non-Python Projects : This tool is specialized for the Python ecosystem. Error Con...
 62
15572 godot-animation-tree-mastery thedivergentai/gd-agentic-skills
AnimationTree Mastery Expert guidance for Godot's advanced animation blending and state machines. NEVER Do NEVER call play() on AnimationPlayer when using AnimationTree — AnimationTree controls the player. Directly calling play() causes conflicts. Use set("parameters/transition_request") instead. NEVER forget to set active = true — AnimationTree is inactive by default. Animations won't play until $AnimationTree.active = true . NEVER use absolute paths for transition_request — Use relative paths....
 62
15573 skill-tuning catlog22/claude-code-workflow
Autonomous diagnosis and optimization for skill execution issues. Architecture ``` ┌─────────────────────────────────────────────────────┐ │ Phase 0: Read Specs (mandatory) │ │ → problem-taxonomy.md, tuning-strategies.md │ └─────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────┐ │ Orchestrator (state-driven) │ │ Read state → Select action → Execute → Update →...
 62
15574 upgrade-assessment yonatangross/orchestkit
Upgrade Assessment Evaluate platform upgrade readiness for Claude model transitions, Claude Code version bumps, and OrchestKit plugin updates. Produces a structured JSON assessment report with a 0-10 readiness score across 6 dimensions. When to Use Before upgrading the Claude model (e.g., Sonnet 4 to Opus 4.6) Before upgrading Claude Code to a new major/minor version Before upgrading OrchestKit to a new major version When evaluating whether a team environment is ready for a platform change As pa...
 62
15575 1k-dev-commands onekeyhq/app-monorepo
OneKey Development Commands Application Development Commands PLATFORM-SPECIFIC DEVELOPMENT: yarn app:desktop - Start desktop Electron app development Runtime: 30-60 seconds to start Common issues: Node version conflicts, missing native dependencies Troubleshooting: Run yarn clean && yarn reinstall if startup fails yarn app:web - Start web development server (port 3000) Runtime: 15-30 seconds to start Common issues: Port 3000 already in use, webpack compilation errors Troubleshooting: Kill e...
 62
15576 debugging-methodology laurigates/claude-plugins
Debugging Methodology Systematic approach to finding and fixing bugs. Core Principles Occam's Razor - Start with the simplest explanation Binary Search - Isolate the problem area systematically Preserve Evidence - Understand state before making changes Document Hypotheses - Track what was tried and didn't work Debugging Workflow 1. Understand → What is expected vs actual behavior? 2. Reproduce → Can you trigger the bug reliably? 3. Locate → Where in the code does it happen? 4. Diagnose → Why doe...
 61
15577 react-19 gentleman-programming/gentleman-skills
No Manual Memoization (REQUIRED) // ✅ React Compiler handles optimization automatically function Component ( { items } ) { const filtered = items . filter ( x => x . active ) ; const sorted = filtered . sort ( ( a , b ) => a . name . localeCompare ( b . name ) ) ; const handleClick = ( id ) => { console . log ( id ) ; } ; return < List items = { sorted } onClick = { handleClick } / > ; } // ❌ NEVER: Manual memoization const filtered = useMemo ( ( ) => items . filter ( x => x . active ) , [ items...
 61
15578 knowledge-management groeimetai/snow-flow
Knowledge Management Skill You are an expert at creating, organizing, and maintaining support knowledge base content. You write articles that are searchable, scannable, and solve customer problems on the first read. You understand that every good KB article reduces future ticket volume. Article Structure and Formatting Standards Universal Article Elements Every KB article should include: Title : Clear, searchable, describes the outcome or problem (not internal jargon) Overview : 1-2 sentences ex...
 61
15579 spec-gathering oimiragieo/agent-studio
Requirements Gathering Skill Overview Gather user requirements through structured questioning and produce a validated requirements document. This skill transforms vague task descriptions into actionable, structured requirements. Core principle: Ask smart questions, produce valid structured output. Nothing else. When to Use Always: Starting a new feature or project Clarifying ambiguous task descriptions When user provides high-level goals without specifics Before spec writing begins Exceptions: S...
 61
15580 structured-output-extractor patricio0312rev/skills
Structured Output Extractor Extract reliable, typed data from LLM responses. Core Workflow Define schema: Create data structure Choose method: Function calling vs prompting Generate response: Call LLM with structure Validate output: Parse and verify Handle errors: Retry or fallback Methods Comparison Method Reliability Flexibility Best For OpenAI JSON Mode High Medium Simple JSON Function Calling Very High High Complex schemas Instructor Very High High Python/TS apps Zod + Prompting Medium Hig...
 61
15581 complexity-assessment oimiragieo/agent-studio
Complexity Assessment Skill Overview Analyze a task description and determine its true complexity to ensure the right workflow and validation depth are selected. Accuracy over speed - wrong complexity means wrong workflow means failed implementation. Core principle: Accuracy over speed. Wrong complexity = wrong workflow = failed implementation. When to Use Always: Before planning any new task When requirements are gathered but approach unclear When determining validation depth for QA Exceptions:...
 61
15582 chrome-webstore-release-blueprint brianlovin/claude-config
Chrome Web Store Release Blueprint Use this skill as a hands-on setup guide. The agent should lead the user step-by-step, ask for confirmations, and only automate the parts that can be done locally/in CI. What This Skill Is For Helping a user set up Chrome Web Store release automation from scratch. Giving clear manual instructions for Google/CWS dashboard steps. Implementing repo-side scripts/workflows after the user provides credentials. Verifying submission state ( PUBLISHED , PENDING_REVIEW ,...
 61
15583 using-user-stories andrelandgraf/fullstackrecipes
Working with User Stories Document and track feature implementation with user stories. Workflow for authoring stories, building features, and marking acceptance criteria as passing. User stories document what features should do and track implementation status. When AI agents work through user stories systematically, they produce better results and leave a clear trail of what was done. Workflow When working on features: Author/Update: Create or modify user story features before building Buil...
 61
15584 security-auditor erichowens/some_claude_skills
Security Auditor Expert in identifying security vulnerabilities following OWASP Top 10 and security best practices. When This Skill Activates Activates when you: Request a security audit Mention "security" or "vulnerability" Need security review Ask about OWASP OWASP Top 10 Coverage A01: Broken Access Control Show more
 61
15585 dojo-test dojoengine/book
Dojo Test Generation Write comprehensive tests for your Dojo models and systems using Cairo's test framework and Dojo's test utilities. When to Use This Skill "Write tests for the move system" "Test the Position model" "Add unit tests for combat logic" "Create integration tests" What This Skill Does Generates test files with: spawn_test_world() setup Model and system registration Test functions with assertions Cheat code usage for manipulating execution context State verification Quick Start Int...
 61
15586 vercel-react-best-practices connorads/dotfiles
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...
 61
15587 godot-ability-system thedivergentai/gd-agentic-skills
Ability System Expert guidance for building flexible, extensible ability systems. NEVER Do NEVER use _process() for cooldown tracking — Use timers or manual delta tracking in _physics_process(). _process() has variable delta and causes cooldown desync in slow frames. NEVER forget global cooldown (GCD) — Without GCD, players spam instant abilities. Add a small universal cooldown (0.5-1.5s) between all ability casts. NEVER hardcode ability effects in manager code — Use the Strategy pattern. Each a...
 61
15588 r-expert personamanagmentlayer/pcl
Expert guidance for R programming, statistical analysis, data visualization, and data science. Core Concepts R Fundamentals - Vectors and data frames - Factors and lists - Functions and apply family - Packages and libraries - R Markdown - Tidyverse ecosystem Statistical Analysis - Descriptive statistics - Hypothesis testing - Regression analysis - ANOVA - Time series analysis - Machine learning Data Visualization - ggplot2 - Base R graphics - Interactive plots (plotly) - ...
 61
15589 twitter-to-binance-square 6551team/6551-twitter-to-binance-square
Twitter to Binance Square Auto-Mirror Skill Overview Automatically fetch tweets from specified Twitter accounts or keyword searches, transform the content for Binance Square, and post them. Designed for building automation pipelines with configurable polling intervals and deduplication. Automation script: scripts/auto_mirror.py Config template: mirror_config.example.json Usage guide: README.md Prerequisites Item Description How to get TWITTER_TOKEN 6551 API Bearer token 访问 https://6551.io/mcp 注册...
 61
15590 blockbench-animation jasonjgardner/blockbench-mcp-project
Blockbench Animation Create animations for 3D models using Blockbench MCP tools. Available Tools Tool Purpose create_animation Create animation with keyframes for bones manage_keyframes Create/edit/delete keyframes per bone and channel animation_graph_editor Fine-tune animation curves (smooth, linear, ease) bone_rigging Create/modify bone structure for animation animation_timeline Control playback, time, FPS, loop settings batch_keyframe_operations Batch operations: offset, scale, reverse, mir...
 61
15591 microsoft-docs microsoftdocs/mcp
Microsoft Docs Tools Tool Use For microsoft_docs_search Find documentation—concepts, guides, tutorials, configuration microsoft_docs_fetch Get full page content (when search excerpts aren't enough) When to Use Understanding concepts — "How does Cosmos DB partitioning work?" Learning a service — "Azure Functions overview", "Container Apps architecture" Finding tutorials — "quickstart", "getting started", "step-by-step" Configuration options — "App Service configuration settings" Limits & quotas —...
 61
15592 walking-through-the-grove autumnsgrove/groveengine
Walking Through the Grove A naming ritual for the Grove ecosystem. Use this when you need to find a name that fits —not just a clever pun, but something that belongs in this forest. When to Activate Naming a new service, feature, or concept for Grove Renaming something that doesn't feel right Called from the grove-ui-design skill when new UI needs a name Any time you're adding something to the Grove ecosystem The Process This is a journey , not a checklist. Take your time. Step 1: Read the Namin...
 61
15593 plotext-financial-chart terrylica/cc-skills
Plotext Financial Chart Skill Create ASCII financial line charts for GitHub Flavored Markdown using plotext with dot marker ( • ). Pure text output — renders correctly on GitHub, terminals, and all monospace environments. Analogy : graph-easy is for flowcharts. plotext with dot marker is for financial line charts. When to Use This Skill Adding price path / line chart diagrams to markdown documentation Visualizing trading concepts (barriers, thresholds, entry/exit levels) Any GFM markdown file ne...
 61
15594 hig-technologies raintree-technology/apple-hig-skills
Apple HIG: Technologies Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered. Key Principles Apple technologies extend app capabilities through system integration. Each technology has established user-facing patterns; deviating creates confusion and erodes trust. Privacy and user control are paramount. Especially for health, payment, and identity technologies. Request only needed data, explain why, respect choice...
 61
15595 imagegen davila7/claude-code-templates
Generates or edits images for the current project (e.g., website assets, game assets, UI mockups, product mockups, wireframes, logo design, photorealistic images, infographics). Defaults to `gpt-image-1.5` and the OpenAI Image API, and prefers the bundled CLI for deterministic, reproducible runs. When to use - Generate a new image (concept art, product shot, cover, website hero) - Edit an existing image (inpainting, masked edits, lighting or weather transformations, background replacement, o...
 61
15596 fal-ai hoodini/ai-agents-skills
fal.ai - Serverless AI Platform Generate images, videos, and audio with fal.ai's fast serverless inference. Quick Start npm install @fal-ai/serverless-client import * as fal from '@fal-ai/serverless-client'; fal.config({ credentials: process.env.FAL_KEY, }); // Generate image with Flux const result = await fal.subscribe('fal-ai/flux/dev', { input: { prompt: 'A serene Japanese garden with cherry blossoms', image_size: 'landscape_16_9', num_images: 1, }, }); console.log(res...
 61
15597 debugging oimiragieo/agent-studio
Debugging When to use this skill Encountering runtime errors or exceptions Code produces unexpected output or behavior Performance degradation or memory issues Intermittent or hard-to-reproduce bugs Understanding unfamiliar error messages Post-incident analysis and prevention Instructions Step 1: Gather Information Collect all relevant context about the issue: Error details : Full error message and stack trace Error type (syntax, runtime, logic, etc.) When did it start occurring? Is it reproduci...
 61
15598 bun hono integration secondsky/claude-skills
Bun Hono Integration Hono is a fast, lightweight web framework optimized for Bun. Quick Start bun create hono my-app cd my-app bun install bun run dev Basic Setup import { Hono } from "hono" ; const app = new Hono ( ) ; app . get ( "/" , ( c ) => c . text ( "Hello Hono!" ) ) ; app . get ( "/json" , ( c ) => c . json ( { message : "Hello" } ) ) ; export default app ; Routing import { Hono } from "hono" ; const app = new Hono ( ) ; // HTTP methods app . get ( "/users" , ( c ) => c . json ( [ ] ) )...
 61
15599 notifications-toasts dylantarre/animation-principles
Notification & Toast Animation Principles Apply Disney's 12 principles to notifications for attention-grabbing yet non-disruptive alerts. Principles Applied to Notifications 1. Squash & Stretch Toast can compress slightly on entrance impact, then stretch back. Creates a "landing" feel as if it arrived from off-screen. 2. Anticipation Before auto-dismiss, toast can contract slightly (95% scale) for 100ms. Signals imminent departure to user. 3. Staging Notifications should appear in consist...
 61
15600 vueuse-functions vueuse/vueuse
VueUse Functions This skill is a decision-and-implementation guide for VueUse composables in Vue.js / Nuxt projects. It maps requirements to the most suitable VueUse function, applies the correct usage pattern, and prefers composable-based solutions over bespoke code to keep implementations concise, maintainable, and performant. When to Apply Apply this skill whenever assisting user development work in Vue.js / Nuxt. Always check first whether a VueUse function can implement the requirement. Pre...
 61