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...
21,355
总 Skills
33.9M
总安装量
2,437
贡献者
# Skill 仓库 描述 安装量
15051 adding-models letta-ai/letta-code
Adding Models This skill guides you through adding a new LLM model to Letta Code. Quick Reference Key files : src/models.json - Model definitions (required) .github/workflows/ci.yml - CI test matrix (optional) src/tools/manager.ts - Toolset detection logic (rarely needed) Workflow Step 1: Find Valid Model Handles Query the Letta API to see available models: curl -s https://api.letta.com/v1/models/ | jq '.[] | .handle' Or filter by provider: curl -s https://api.letta.com/v1/models/ | jq '.[] | se...
 55
15052 newsletter openclaudia/openclaudia-skills
Newsletter Growth Skill You are a newsletter growth strategist. Help plan content, grow subscribers, improve engagement, and monetize newsletters. Newsletter Fundamentals Subject Lines Formulas that work: Formula Example Open Rate Impact Number + Benefit "7 tools that saved me 10hrs/week" High Question "Are you making this SEO mistake?" High How-to + Specific "How I grew to 10K subs in 6 months" High Curiosity gap "The strategy nobody talks about" Medium-High News/Urgency "Breaking: Google just ...
 55
15053 outlines orchestra-research/ai-research-skills
Outlines: Structured Text Generation When to Use This Skill Use Outlines when you need to: Guarantee valid JSON/XML/code structure during generation Use Pydantic models for type-safe outputs Support local models (Transformers, llama.cpp, vLLM) Maximize inference speed with zero-overhead structured generation Generate against JSON schemas automatically Control token sampling at the grammar level GitHub Stars: 8,000+ | From: dottxt.ai (formerly .txt) Installation Base installation pip install...
 55
15054 workers-runtime-apis secondsky/claude-skills
Master the Workers runtime APIs: Fetch, Streams, Crypto, Cache, WebSockets, and text encoding. Quick Reference | Fetch | HTTP requests | External APIs, proxying | Streams | Data streaming | Large files, real-time | Crypto | Cryptography | Hashing, signing, encryption | Cache | Response caching | Performance optimization | WebSockets | Real-time connections | Chat, live updates | Encoding | Text encoding | UTF-8, Base64 Quick Start: Fetch API ``` export default { as...
 55
15055 readme-generator patricio0312rev/skills
Readme Generator Purpose This skill provides automated assistance for readme generator tasks within the DevOps Basics domain. When to Use This skill activates automatically when you: Mention "readme generator" in your request Ask about readme generator patterns or best practices Need help with foundational devops skills covering version control, containerization, basic ci/cd, and infrastructure fundamentals. Capabilities Provides step-by-step guidance for readme generator Follows industry be...
 55
15056 content-writing eyadsibai/ltk
Collaborative writing partner for articles, blog posts, and documentation. Workflow Overview - Outline - Structure ideas collaboratively - Research - Find sources and add citations - Write - Draft section by section - Feedback - Get review on each section - Polish - Final review and refinement File Organization ``` ~/writing/article-name/ ├── outline.md Structure ├── research.md Sources and citations ├── draft-v1.md First draft ├── draft-v2.md Revis...
 55
15057 sharex architecture and porting sharex/xerahs
Platform Abstractions and Native Code Rules All platform specific functionality must be isolated behind platform abstraction interfaces. No code outside XerahS.Platform.* projects may reference: NativeMethods NativeConstants, NativeEnums, NativeStructs Win32 P/Invoke System.Windows.Forms Windows specific handles or messages Direct calls to Windows APIs are forbidden in Common, Core, Uploaders, Media, or other backend projects. Required Architecture Define platform neutral interfaces in XerahS.Pl...
 55
15058 long-context orchestra-research/ai-research-skills
Long Context: Extending Transformer Context Windows When to Use This Skill Use Long Context techniques when you need to: Process long documents (32k, 64k, 128k+ tokens) with transformer models Extend context windows of pre-trained models (LLaMA, Mistral, etc.) Implement efficient positional encodings (RoPE, ALiBi) Train models with length extrapolation capabilities Deploy models that handle variable-length inputs efficiently Fine-tune existing models for longer contexts with minimal compute K...
 55
15059 miniapp-develop lotosbin/claude-skills
No SKILL.md available for this skill. View on GitHub
 55
15060 modal-serverless-gpu orchestra-research/ai-research-skills
Modal Serverless GPU Comprehensive guide to running ML workloads on Modal's serverless GPU cloud platform. When to use Modal Use Modal when: Running GPU-intensive ML workloads without managing infrastructure Deploying ML models as auto-scaling APIs Running batch processing jobs (training, inference, data processing) Need pay-per-second GPU pricing without idle costs Prototyping ML applications quickly Running scheduled jobs (cron-like workloads) Key features: Serverless GPUs: T4, L4, A10G,...
 55
15061 database-testing proffesor-for-testing/agentic-qe
Database Testing <default_to_action> When testing database operations: VALIDATE schema (tables, columns, constraints exist as expected) TEST data integrity (unique, foreign key, check constraints) VERIFY migrations (forward works, rollback works, data preserved) CHECK transaction isolation (ACID properties, concurrent access) MEASURE query performance (indexes used, execution time) Quick DB Testing Checklist: Schema matches specification Unique constraints prevent duplicates Foreign keys prevent...
 55
15062 copilot-sdk sickn33/antigravity-awesome-skills
GitHub Copilot SDK Embed Copilot's agentic workflows in any application using Python, TypeScript, Go, or .NET. Overview The GitHub Copilot SDK exposes the same engine behind Copilot CLI: a production-tested agent runtime you can invoke programmatically. No need to build your own orchestration - you define agent behavior, Copilot handles planning, tool invocation, file edits, and more. Prerequisites GitHub Copilot CLI installed and authenticated ( Installation guide ) Language runtime : Node.js 1...
 55
15063 product-ux-expert majiayu000/claude-arsenal
Product UX Expert Core Principles Reduce Cognitive Load — Minimize mental effort required for every interaction Accessibility First — WCAG 2.2 AA is the baseline, not an afterthought Evidence-Based — Decisions backed by user research, not assumptions Anticipatory Design — Predict user needs before they ask Ethical Design — No dark patterns, transparent data practices Mobile First — Design for smallest screens, enhance for larger Quick Reference Nielsen's 10 Heuristics Heuristic Key Question 1 V...
 55
15064 diagram-to-image sugarforever/01coder-agent-skills
Diagram to Image Convert Mermaid diagrams and Markdown tables to PNG images via the mermaid-red API (diagramless.xyz). Produces high-quality, styled output with custom themes — no heavy local dependencies needed. When to Use Use this skill when: User has a Mermaid diagram that needs to be converted to an image User has a Markdown table that needs to be converted to an image User is writing content for X/Twitter and needs visual exports User asks to "convert to image", "export as PNG", "make this...
 55
15065 physics-intuition dylantarre/animation-principles
Physics Intuition Think like a physicist watching the world move. Every object has mass. Every motion has cause and consequence. Core Mental Model Before animating anything, ask: What does this weigh? A feather and a bowling ball both fall, but they tell completely different stories. Your job is to make the audience feel that weight without thinking about it. The 12 Principles Through Physics Squash & Stretch — Mass is conserved. When something compresses, it must bulge. A bouncing ball fl...
 55
15066 typo3-ddev dirnbauer/webconsulting-skills
TYPO3 DDEV Local Development Compatibility: TYPO3 v13.x and v14.x (v14 preferred) All configurations in this skill support both TYPO3 v13 and v14. Container Priority Always check for existing containers first: Check .ddev/ exists → use ddev exec Check docker-compose.yml exists → use docker compose exec Only use system tools if no container environment Critical: Use the project's configured PHP version, not system PHP. 1. Project Initialization New TYPO3 Project (v14 - Preferred) Create pr...
 55
15067 performance-benchmark-specialist manutej/luxor-claude-marketplace
Performance Benchmark Specialist Comprehensive performance benchmarking expertise for shell-based tools, focusing on rigorous measurement, statistical analysis, and actionable performance optimization using patterns from the unix-goto project. When to Use This Skill Use this skill when: Creating performance benchmarks for shell scripts Measuring and validating performance targets Implementing statistical analysis for benchmark results Designing benchmark workspaces and test environments Gene...
 55
15068 skill-composer-studio onewave-ai/claude-skills
Skill Composer Studio CHAIN multiple existing skills into custom multi-step workflows. Programmable skill combinations with automatic handoffs. Create composite skills from building blocks with conditional logic. Instructions You are a master workflow orchestrator and skill integrator. When user describes a multi-step workflow, map it to a sequence of existing skills with automatic handoffs between steps. Output from step N becomes input for step N+1. Support conditional logic (if-then-else base...
 55
15069 mamba-architecture orchestra-research/ai-research-skills
Mamba - Selective State Space Models Quick start Mamba is a state-space model architecture achieving O(n) linear complexity for sequence modeling. Installation: Install causal-conv1d (optional, for efficiency) pip install causal-conv1d>=1.4.0 Install Mamba pip install mamba-ssm Or both together pip install mamba-ssm[causal-conv1d] Prerequisites: Linux, NVIDIA GPU, PyTorch 1.12+, CUDA 11.6+ Basic usage (Mamba block): import torch from mamba_ssm import Mamba batch, length, dim = 2, 64,...
 55
15070 search-console openclaudia/openclaudia-skills
Google Search Console Pull search performance data, index coverage, and Core Web Vitals from Google Search Console API. Prerequisites Requires Google OAuth credentials: GOOGLE_CLIENT_ID GOOGLE_CLIENT_SECRET A valid OAuth access token with https://www.googleapis.com/auth/webmasters.readonly scope Set credentials in .env , .env.local , or ~/.claude/.env.global . Getting an Access Token Step 1: Authorization URL (user visits in browser) echo "https://accounts.google.com/o/oauth2/v2/auth?client_id=...
 55
15071 react-performance s-hiraoku/synapse-a2a
React Performance Optimization Master react performance optimization for building high-performance, scalable React applications with industry best practices. React.memo and Component Memoization React.memo prevents unnecessary re-renders by memoizing component output: import { memo } from 'react' ; interface Props { name : string ; onClick : ( ) => void ; } // Basic memoization const ExpensiveComponent = memo ( function ExpensiveComponent ( { name , onClick } : Props ) { console . log ( 'Renderi...
 55
15072 nanogpt orchestra-research/ai-research-skills
nanoGPT - Minimalist GPT Training Quick start nanoGPT is a simplified GPT implementation designed for learning and experimentation. Installation: pip install torch numpy transformers datasets tiktoken wandb tqdm Train on Shakespeare (CPU-friendly): Prepare data python data/shakespeare_char/prepare.py Train (5 minutes on CPU) python train.py config/train_shakespeare_char.py Generate text python sample.py --out_dir=out-shakespeare-char Output: ROMEO: What say'st thou? Shall I speak, ...
 55
15073 bevy-ecs-expert sickn33/antigravity-awesome-skills
Bevy ECS Expert Overview A guide to building high-performance game logic using Bevy's data-oriented ECS architecture. Learn how to structure systems, optimize queries, manage resources, and leverage parallel execution. When to Use This Skill Use when developing games with the Bevy engine in Rust. Use when designing game systems that need to run in parallel. Use when optimizing game performance by minimizing cache misses. Use when refactoring object-oriented logic into data-oriented ECS patterns....
 55
15074 zcl marcohefti/zero-context-lab
ZCL Orchestrator (Codex Skill) This skill is for the orchestrator (you), not the spawned mission agent. Native Runtime Boundary (Current) ZCL has first-class native runtime execution in zcl suite run and campaign flows via runner.type=codex_app_server . Runtime selection is strategy-based and deterministic via ordered fallback chains ( --runtime-strategies , ZCL_RUNTIME_STRATEGIES ). Process runner mode remains supported as explicit fallback ( --session-isolation process ). Native runtime strate...
 55
15075 torchforge-rl-training orchestra-research/ai-research-skills
torchforge: PyTorch-Native Agentic RL Library torchforge is Meta's PyTorch-native RL library that separates infrastructure concerns from algorithm concerns. It enables rapid RL research by letting you focus on algorithms while handling distributed training, inference, and weight sync automatically. When to Use torchforge Choose torchforge when you need: Clean separation between RL algorithms and infrastructure PyTorch-native abstractions (no Ray dependency) Easy algorithm experimentation (GRPO, ...
 55
15076 ios-unit-test dengineproblem/agents-monorepo
iOS Unit Testing Expert Expert in iOS testing with XCTest framework and best practices. Core Testing Principles Test Structure and Organization Follow the Arrange-Act-Assert (AAA) pattern Use descriptive test method names explaining scenario and expected outcome Group related tests using nested test classes or test suites Maintain test independence - each test should run in isolation XCTest Framework Fundamentals import XCTest @testable import YourApp class UserServiceTests : XCTestCase { // Sys...
 55
15077 nodejs-development manutej/luxor-claude-marketplace
Node.js Development Guidelines You are an expert in Node.js development with TypeScript, covering various frameworks and patterns. Payload CMS with Next.js Project Setup project/ ├── src/ │ ├── app/ Next.js app directory │ ├── collections/ Payload collections │ ├── blocks/ Custom blocks │ ├── fields/ Custom fields │ └── access/ Access control functions ├── payload.config.ts Payload configuration └── next.config.js Next.js con...
 55
15078 prospect-investigation qodex-ai/ai-agent-skills
Lead Research Assistant This skill helps you identify and qualify potential leads for your business by analyzing your product/service, understanding your ideal customer profile, and providing actionable outreach strategies. When to Use This Skill Finding potential customers or clients for your product/service Building a list of companies to reach out to for partnerships Identifying target accounts for sales outreach Researching companies that match your ideal customer profile Preparing for bus...
 55
15079 vercel-composition-patterns vercel-labs/vercel-skills
React Composition Patterns Composition patterns for building flexible, maintainable React components. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. These patterns make codebases easier for both humans and AI agents to work with as they scale. When to Apply Reference these guidelines when: Refactoring components with many boolean props Building reusable component libraries Designing flexible component APIs Reviewing component architecture W...
 55
15080 agent-browser code-yeongyu/oh-my-opencode
Browser Automation with agent-browser The CLI uses Chrome/Chromium via CDP directly. Install via npm i -g agent-browser , brew install agent-browser , or cargo install agent-browser . Run agent-browser install to download Chrome. Core Workflow Every browser automation follows this pattern: Navigate : agent-browser open <url> Snapshot : agent-browser snapshot -i (get element refs like @e1 , @e2 ) Interact : Use refs to click, fill, select Re-snapshot : After navigation or DOM changes, get fresh r...
 55
15081 issues-workflow terrylica/cc-skills
GitHub Issues-First Workflow Default : Use GitHub Issues exclusively for all content, hierarchy, and tracking. Optional : Link to Projects v2 for cross-repo visualization only. Critical Principle: Issues Are Everything GitHub Issues = Content + Hierarchy + Status + History. GitHub Projects v2 = Visualization layer only (no content, no history). With sub-issues (GA April 2025), Issues now handle hierarchy natively. Projects v2 is reduced to an optional visualization dashboard. Issues vs Projects ...
 55
15082 performance-audit mgd34msu/goodvibes-plugin
Resources scripts/ validate-performance-audit.sh references/ performance-patterns.md Performance Audit This skill guides you through performing comprehensive performance audits on web applications to identify bottlenecks, optimization opportunities, and performance regressions. Use this when preparing for production deployments, investigating performance issues, or conducting periodic performance reviews. When to Use This Skill Conducting pre-deployment performance reviews Investigating slow pag...
 55
15083 design-master huangserva/skill-prompt-generator
No SKILL.md available for this skill. View on GitHub
 55
15084 runway vm0-ai/vm0-skills
Runway API Use the Runway API via direct curl calls to generate AI videos from images, text, or video inputs. Official docs: https://docs.dev.runwayml.com/ When to Use Use this skill when you need to: Generate video from images (image-to-video) Generate video from text prompts (text-to-video) Transform existing videos (video-to-video) Generate images from text (text-to-image) Upscale video resolution (4X upscale) Generate sound effects or speech Prerequisites Sign up at Runway Developer Portal P...
 55
15085 cass dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
CASS - Coding Agent Session Search Unified, high-performance CLI/TUI to index and search your local coding agent history. Aggregates sessions from 11 agents : Codex, Claude Code, Gemini CLI, Cline, OpenCode, Amp, Cursor, ChatGPT, Aider, Pi-Agent, and Factory (Droid). CRITICAL: Robot Mode Required for AI Agents NEVER run bare cass - it launches an interactive TUI that blocks your session! WRONG - blocks terminal cass CORRECT - JSON output for agents cass search "query" --robot cass search "quer...
 55
15086 resend vm0-ai/vm0-skills
Resend Quick Send — Node.js import { Resend } from 'resend' ; const resend = new Resend ( process . env . RESEND_API_KEY ) ; const { data , error } = await resend . emails . send ( { from : 'Acme <onboarding@resend.dev>' , to : [ 'delivered@resend.dev' ] , subject : 'Hello World' , html : '<p>Email body here</p>' , } , { idempotencyKey : ` welcome-email/ ${ userId } ` } ) ; if ( error ) { console . error ( 'Failed:' , error . message ) ; return ; } console . log ( 'Sent:' , data . id ) ; Key got...
 55
15087 godot-performance-optimization thedivergentai/gd-agentic-skills
Performance Optimization Profiler-driven analysis, object pooling, and visibility culling define optimized game performance. Available Scripts custom_performance_monitor.gd Manager for adding and updating custom performance monitors in the Godot debugger. multimesh_foliage_manager.gd Expert MultiMesh pattern for rendering thousands of foliage instances efficiently. NEVER Do in Performance Optimization NEVER optimize without profiling first — "I think physics is slow" without data? Premature opti...
 55
15088 vueuse-integrations-skilld harlan-zw/vue-ecosystem-skills
vueuse/vueuse @vueuse/integrations Integration wrappers for utility libraries Version: 14.2.1 (Feb 2026) Deps: @vueuse/core@14.2.1, @vueuse/shared@14.2.1 Tags: next: 5.0.0 (Jun 2021), alpha: 14.0.0-alpha.3 (Sep 2025), beta: 14.0.0-beta.1 (Sep 2025), latest: 14.2.1 (Feb 2026) References: Docs — API reference, guides API Changes This section documents version-specific API changes — prioritize recent major/minor releases. BREAKING: Requires Vue 3.5+ — v14.x now requires Vue 3.5.0 as a peer dependen...
 55
15089 paddleocr-doc-parsing paddlepaddle/paddleocr
PaddleOCR Document Parsing Skill When to Use This Skill ✅ Use Document Parsing for : Documents with tables (invoices, financial reports, spreadsheets) Documents with mathematical formulas (academic papers, scientific documents) Documents with charts and diagrams Multi-column layouts (newspapers, magazines, brochures) Complex document structures requiring layout analysis Any document requiring structured understanding ❌ Use Text Recognition instead for : Simple text-only extraction Quick OCR task...
 55
15090 drizzle-migrations erichowens/some_claude_skills
Drizzle ORM Database Migrations (TypeScript) Migration-first database development workflow using Drizzle ORM for TypeScript/JavaScript projects. When to Use This Skill Use this skill when: Working with Drizzle ORM in TypeScript/JavaScript projects Need to create or modify database schema Want migration-first development workflow Setting up new database tables or columns Need to ensure schema consistency across environments Core Principle: Migration-First Development Critical Rule: Schema ch...
 55
15091 readme oimiragieo/agent-studio
/readme — Gold-Standard README Generation Purpose: Generate a README that converts skimmers into users and satisfies deep readers — then validate it with a council. YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it. Quick Start /readme Interview + generate + validate (new README) /readme --rewrite Rewrite existing README with same patterns /readme --validate Council-validate an existing README without rewriting The Patterns These are non-negotiable. Every README this skill produces foll...
 55
15092 web-search rtgs2017/nagaagent
Web Search & Extraction Search the web and extract content via inference.sh CLI. Quick Start Requires inference.sh CLI ( infsh ). Get installation instructions: npx skills add inference-sh/skills@agent-tools infsh login Search the web infsh app run tavily/search-assistant --input '{"query": "latest AI developments 2024"}' Available Apps Tavily App App ID Description Search Assistant tavily/search-assistant AI-powered search with answers Extract tavily/extract Extract content from URLs Exa App A...
 55
15093 database-expert travisjneuman/.claude
Database Expert database algorithm rules When reviewing or writing code, apply these guidelines: You are an expert in database algorithms. Optimize algorithms for performance and scalability. Use appropriate data structures and indexing strategies. database interaction best practices When reviewing or writing code, apply these guidelines: When interacting with databases: Use prepared statements to prevent SQL injection. Handle database errors gracefully. Consider using an ORM for complex queries...
 55
15094 gamedev-expert oimiragieo/agent-studio
Gamedev Expert When reviewing or writing code, apply these guidelines: Use exceptions for exceptional cases, not for control flow. Implement proper error logging and user-friendly messages. dragonruby general ruby rules When reviewing or writing code, apply these guidelines: Write concise, idiomatic Ruby code with accurate examples. Follow Ruby and DragonRuby conventions and best practices. Use object-oriented and functional programming patterns as appropriate. Prefer iteration and modularizatio...
 55
15095 response-rater oimiragieo/agent-studio
Response Rater Skill Step 1: Define Rating Rubric Use appropriate rubric for the content type: For Plans : Dimension Weight Description Completeness 20% All required sections present Feasibility 20% Plan is realistic and achievable Risk Mitigation 20% Risks identified with mitigations Agent Coverage 20% Appropriate agents assigned Integration 20% Fits with existing systems For Responses : Dimension Weight Description Correctness 25% Technically accurate Completeness 25% Addresses all requirement...
 55
15096 miles-rl-training orchestra-research/ai-research-skills
No SKILL.md available for this skill. [View on GitHub ](https://github.com/davila7/claude-code-templates)
 55
15097 architecture-review getsentry/warden
Architecture Review Analyze, audit, and improve project structure. Key Principles Measure before changing — Map structure and identify concrete issues before proposing changes Clear boundaries — Layers (UI, logic, data) separated with consistent dependency direction Colocation — Related code together; easy to find, change, and delete features Incremental migration — Refactor in phases, validate each step with tests Quick Assessment No circular dependencies Consistent directory naming and groupin...
 55
15098 workflow epicenterhq/epicenter
CRITICAL : Always Use Correct workflow Documentation Your knowledge of workflow is outdated. The workflow documentation outlined below matches the installed version of the Workflow DevKit. Follow these instructions before starting on any workflow -related tasks: Search the bundled documentation in node_modules/workflow/docs/ : Find docs : glob "node_modules/workflow/docs//*.mdx" Search content : grep "your query" node_modules/workflow/docs/ Documentation structure in node_modules/workflow/docs/ ...
 55
15099 fabric-onelake-2025 josiahsiegel/claude-plugin-marketplace
🚨 CRITICAL GUIDELINES Windows File Path Requirements MANDATORY: Always Use Backslashes on Windows for File Paths When using Edit or Write tools on Windows, you MUST use backslashes (\) in file paths, NOT forward slashes (/). Examples: ❌ WRONG: D:/repos/project/file.tsx ✅ CORRECT: D:\repos\project\file.tsx This applies to: Edit tool file_path parameter Write tool file_path parameter All file operations on Windows systems Documentation Guidelines NEVER create new documentation files unless ...
 55
15100 openclaw paulrberg/agent-skills
OpenClaw CLI Overview OpenClaw is a multi-channel messaging and agent platform. The CLI provides commands for gateway management, agent orchestration, channel operations (WhatsApp, Telegram), device pairing, and automated messaging workflows. Quick Reference Check CLI version and help openclaw --version openclaw --help openclaw --log-level < level > Override log level (silent|fatal|error|warn|info|debug|trace) openclaw --no-color Disable ANSI colors Setup and configuration openclaw setup In...
 55