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
4801 slash-commands parcadei/continuous-claude-v3
Slash Commands Reference Create and use user-triggered prompts with /command-name syntax. When to Use "How do I create a slash command?" "What slash commands are available?" "Add bash to my command" "Use file references in commands" "Slash commands vs skills" Built-in Commands Command Purpose /clear Clear conversation history /compact Compact conversation with focus /config Open settings interface /cost Show token usage /agents Manage sub-agents /mcp Manage MCP servers /memory Edit CLAUDE.md f...
 179
4802 clickup automation claude-office-skills/skills
ClickUp Automation Comprehensive skill for automating ClickUp workspace and task management. Core Concepts Workspace Hierarchy CLICKUP HIERARCHY: ┌─────────────────────────────────────────────────────────┐ │ 🏢 WORKSPACE │ ├─────────────────────────────────────────────────────────┤ │ ├── 📁 SPACE: Engineering │ │ │ ├── 📂 FOLDER: Q1 Projects │ │ │ │ ├── 📋 LIST: Feature Development │ ...
 179
4803 react-three-fiber anthemflynn/ccmp
React Three Fiber React Three Fiber (R3F) is a React renderer for Three.js. Write declarative, component-based 3D scenes using JSX. Library Versions (2026) React Three Fiber: v9.5+ @react-three/drei: v9.116+ @react-three/rapier: v2+ @react-three/postprocessing: v3+ React: 19+ (concurrent features supported) Decision Frameworks When to Use R3F vs Vanilla Three.js Is your app already React-based? → Yes: Use R3F (natural integration) → No: Consider vanilla Three.js Do you need React state m...
 179
4804 tdd-migration-pipeline parcadei/continuous-claude-v3
TDD Migration Pipeline Orchestrator-only workflow for migrating or rewriting codebases. You do NOT read files, write code, or validate anything yourself. You only instruct agents and pipe context (paths, not contents). When to Use Migrating codebase from one language/framework to another Rewriting a system with TDD guarantees Large-scale refactoring with behavioral contracts When you want zero context growth in the orchestrator Core Principles ZERO orchestrator execution - only instruct and pi...
 179
4805 qlty-check parcadei/continuous-claude-v3
Qlty Code Quality Universal code quality tool supporting 70+ linters for 40+ languages via qlty CLI. When to Use Check code for linting issues before commit/handoff Auto-fix formatting and style issues Calculate code metrics (complexity, duplication) Find code smells Quick Reference Check changed files with auto-fix uv run python -m runtime.harness scripts/qlty_check.py --fix Check all files uv run python -m runtime.harness scripts/qlty_check.py --all Format files uv run python -m runtime...
 179
4806 ddd:software-architecture neolabhq/context-engineering-kit
Software Architecture Development Skill This skill provides guidance for quality focused software development and architecture. It is based on Clean Architecture and Domain Driven Design principles. Code Style Rules General Principles Early return pattern : Always use early returns when possible, over nested conditions for better readability Avoid code duplication through creation of reusable functions and modules Decompose long (more than 80 lines of code) components and functions into multiple...
 179
4807 postgresql sickn33/antigravity-awesome-skills
PostgreSQL Table Design Use this skill when Designing a schema for PostgreSQL Selecting data types and constraints Planning indexes, partitions, or RLS policies Reviewing tables for scale and maintainability Do not use this skill when You are targeting a non-PostgreSQL database You only need query tuning without schema changes You require a DB-agnostic modeling guide Instructions Capture entities, access patterns, and scale targets (rows, QPS, retention). Choose data types and constraints that e...
 179
4808 scene-structure-techniques wordflowlab/novel-writer-skills
场景结构写作技巧 什么是场景？ 场景是实时发生的冲突单元，角色追求目标并面对障碍。 不是场景：说明、背景故事、旅行、时间流逝 是场景：争论、谈判、追逐、揭露 场景-续场模型 每个场景都应该遵循这个模式： 场景（行动） 续场（反应） ├── 目标 ├── 情绪 ├── 冲突 ├── 困境 └── 灾难/成功 └── 决定 场景结构（行动） 1. 目标 POV角色在这个场景想要什么？ 必须是： 具体的："拿到钥匙" 而非 "搞清楚事情" 可实现的：可能在这个场景成功或失败 紧迫的：现在重要，不是最终 你的角色的场景目标： [明确、具体、紧迫] 他们为什么现在想要这个？： [情境/紧迫性] 2. 冲突 什么阻止他们得到想要的？ 冲突类型： 外部：另一个角色反对他们 环境：物理障碍 内部：他们自己的恐惧或犹豫 时间：时间不够 信息：缺少关键知识 最好的场景结合 2-3 种冲突类型。 你的场景冲突： [主要障碍] [次要障碍] [可选第三个] 3. 灾难或成功 ...
 179
4809 etl pipeline claude-office-skills/skills
ETL Pipeline Comprehensive skill for designing and automating Extract, Transform, Load data pipelines. Pipeline Architecture Core ETL Flow DATA PIPELINE ARCHITECTURE: ┌─────────────────────────────────────────────────────────┐ │ EXTRACT │ ├─────────┬─────────┬─────────┬─────────┬─────────────────┤ │ Postgres│ MySQL │ MongoDB │ APIs │ Files (CSV/JSON)│ └────┬────┴────┬────┴────┬────┴────┬────┴────────┬────────┘ │ │ │ │...
 179
4810 tldr-deep parcadei/continuous-claude-v3
TLDR Deep Analysis Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code. Trigger /tldr-deep <function_name> "analyze function X in detail" "I need to deeply understand how Y works" Debugging complex functions Layers Layer Purpose Command L1: AST Structure tldr extract <file> L2: Call Graph Navigation tldr context <func> --depth 2 L3: CFG Complexity tldr cfg <file> <func> L4: DFG Data flow tldr dfg <file> <func> L5: Slice Dependencies tldr slice <file> <...
 179
4811 user-stories phuryn/pm-skills
User Stories Create user stories following the 3 C's (Card, Conversation, Confirmation) and INVEST criteria. Generates stories with descriptions, design links, and acceptance criteria. Use when: Writing user stories, breaking down features into stories, creating backlog items, or defining acceptance criteria. Arguments: $PRODUCT : The product or system name $FEATURE : The new feature to break into stories $DESIGN : Link to design files (Figma, Miro, etc.) $ASSUMPTIONS : Key assumptions or contex...
 179
4812 sentry-setup-ai-monitoring getsentry/sentry-for-ai
Setup Sentry AI Agent Monitoring Configure Sentry to track LLM calls, agent executions, tool usage, and token consumption. Invoke This Skill When User asks to "monitor AI/LLM calls" or "track OpenAI/Anthropic usage" User wants "AI observability" or "agent monitoring" User asks about token usage, model latency, or AI costs Prerequisites AI monitoring requires tracing enabled (tracesSampleRate > 0). Detection First Always detect installed AI SDKs before configuring: JavaScript grep -E '"(op...
 179
4813 data-engineer sickn33/antigravity-awesome-skills
You are a data engineer specializing in scalable data pipelines, modern data architecture, and analytics infrastructure. Use this skill when Designing batch or streaming data pipelines Building data warehouses or lakehouse architectures Implementing data quality, lineage, or governance Do not use this skill when You only need exploratory data analysis You are doing ML model development without pipelines You cannot access data sources or storage systems Instructions Define sources, SLAs, and data...
 179
4814 grepai-embeddings-lmstudio yoanbernabeu/grepai-skills
This skill covers using LM Studio as the embedding provider for GrepAI, offering a user-friendly GUI for managing local models. When to Use This Skill - Want local embeddings with a graphical interface - Already using LM Studio for other AI tasks - Prefer visual model management over CLI - Need to easily switch between models What is LM Studio? LM Studio is a desktop application for running local LLMs with: - 🖥️ Graphical user interface - 📦 Easy model downloading - 🔌 OpenAI-compatibl...
 179
4815 no-polling-agents parcadei/continuous-claude-v3
No Polling for Background Agents When launching parallel background agents, do NOT poll with sleep loops. Pattern Background agents write to status files when complete. Wait for them naturally. DO Launch agents with run_in_background: true Continue with other work while agents run Check status file only when user asks or when you need results to proceed Trust the agent completion system DON'T Run sleep 10 && cat status.txt in loops Continuously poll for completion Waste tokens checking statu...
 179
4816 python-code-quality laurigates/claude-plugins
Quick reference for Python code quality tools: ruff (linting & formatting), mypy (type checking). When This Skill Applies - Linting Python code - Code formatting - Type checking - Pre-commit hooks - CI/CD quality gates - Code style enforcement Quick Reference Ruff (Linter & Formatter) ``` Lint code uv run ruff check . Auto-fix issues uv run ruff check --fix . Format code uv run ruff format . Check and format uv run ruff check --fix . && uv run ruff format . Show specific ru...
 179
4817 obsidian bitbonsai/mcp-obsidian
Obsidian Obsidian vault = a normal folder on disk. Vault structure (typical) Notes: *.md (plain text Markdown; edit with any editor) Config: .obsidian/ (workspace + plugin settings; usually don’t touch from scripts) Canvases: *.canvas (JSON) Attachments: whatever folder you chose in Obsidian settings (images/PDFs/etc.) Find the active vault(s) Obsidian desktop tracks vaults here (source of truth): ~/Library/Application Support/obsidian/obsidian.json obsidian-cli resolves vaults from that file; v...
 179
4818 observe-before-editing parcadei/continuous-claude-v3
Observe Before Editing Before editing code to fix a bug, confirm what the system actually produced. Pattern Outputs don't lie. Code might. Check outputs first. DO Check if expected directories exist: ls -la .claude/cache/ Check if expected files were created: ls -la .claude/cache/learnings/ Check logs for errors: tail .claude/cache/*.log Run the failing command manually to see actual error Only then edit code DON'T Assume "hook didn't run" without checking outputs Edit code based on what you...
 179
4819 it-operations davila7/claude-code-templates
IT Operations Expert A comprehensive skill for managing IT infrastructure operations, ensuring service reliability, implementing monitoring and alerting strategies, managing incidents, and maintaining operational excellence through automation and best practices. Core Principles 1. Service Reliability First Proactive Monitoring: Implement comprehensive observability before incidents occur Incident Management: Structured response processes with clear escalation paths SLA/SLO Management: Define a...
 178
4820 regulatory-affairs-head alirezarezvani/claude-skills
Head of Regulatory Affairs Regulatory strategy development, submission management, and global market access for medical device organizations. Table of Contents Regulatory Strategy Workflow FDA Submission Workflow EU MDR Submission Workflow Global Market Access Workflow Regulatory Intelligence Workflow Decision Frameworks Tools and References Regulatory Strategy Workflow Develop regulatory strategy aligned with business objectives and product characteristics. Workflow: New Product Regulatory Stra...
 178
4821 validate-agent parcadei/continuous-claude-v3
Note: The current year is 2025. When validating tech choices, check against 2024-2025 best practices. Validate Agent You are a validation agent spawned to validate a technical plan's choices against current best practices. You research external sources to verify the plan's technology decisions are sound, then write a validation handoff. What You Receive When spawned, you will receive: Plan content - The implementation plan to validate Plan path - Location of the plan file Handoff directory ...
 178
4822 create-prd phuryn/pm-skills
Create a Product Requirements Document Purpose You are an experienced product manager responsible for creating a comprehensive Product Requirements Document (PRD) for $ARGUMENTS. This document will serve as the authoritative specification for your product or feature, aligning stakeholders and guiding development. Context A well-structured PRD clearly communicates the what, why, and how of your product initiative. This skill uses an 8-section template proven to communicate product vision effectiv...
 178
4823 idempotent-redundancy parcadei/continuous-claude-v3
Idempotent Redundancy When adding redundant paths (fallbacks, belt-and-suspenders), make them idempotent. Pattern Redundancy without idempotency causes loops, churn, or data corruption. DO Use _is_merge: true for Braintrust updates Check if value exists before writing (fallback only if missing) Use atomic write/rename for file operations Make reconciliation steps safe to run repeatedly DON'T Write unconditionally in fallback paths Allow multiple writers to overwrite each other Fire "repair" ...
 178
4824 image-upscaling inference-sh/skills
Image Upscaling Upscale and enhance images via inference.sh CLI. Quick Start Requires inference.sh CLI ( infsh ). Get installation instructions: npx skills add inference-sh/skills@agent-tools infsh login infsh app run infsh/real-esrgan --input '{"image_url": "https://your-image.jpg"}' Available Upscalers Model App ID Best For Topaz Image Upscaler falai/topaz-image-upscaler Professional quality, any image Examples Upscale Any Image infsh app run falai/topaz-image-upscaler --input '{"image_url": "...
 178
4825 powershell-windows davila7/claude-code-templates
PowerShell Windows Patterns Critical patterns and pitfalls for Windows PowerShell. 1. Operator Syntax Rules CRITICAL: Parentheses Required ❌ Wrong ✅ Correct if (Test-Path "a" -or Test-Path "b") if ((Test-Path "a") -or (Test-Path "b")) if (Get-Item $x -and $y -eq 5) if ((Get-Item $x) -and ($y -eq 5)) Rule: Each cmdlet call MUST be in parentheses when using logical operators. 2. Unicode/Emoji Restriction CRITICAL: No Unicode in Scripts Purpose ❌ Don't Use ✅ Use Success ✅ ✓ [OK] [+] Error ❌ ✗ 🔴...
 178
4826 agentica-server parcadei/continuous-claude-v3
Agentica Server + Claude Proxy Setup Complete reference for running Agentica SDK with a local Claude proxy. This enables Python agents to use Claude CLI as their inference backend. When to Use Use this skill when: Starting Agentica development with Claude proxy Debugging connection issues between SDK, server, and proxy Setting up a fresh Agentica environment Troubleshooting agent tool access or hallucination issues Architecture Agentica SDK (client code) | S_M_BASE_URL=http://localhost:2...
 178
4827 langsmith supercent-io/skills-template
langsmith — LLM Observability, Evaluation & Prompt Management Keyword : langsmith · llm tracing · llm evaluation · @traceable · langsmith evaluate LangSmith is a framework-agnostic platform for developing, debugging, and deploying LLM applications. It provides end-to-end tracing, quality evaluation, prompt versioning, and production monitoring. When to use this skill Add tracing to any LLM pipeline (OpenAI, Anthropic, LangChain, custom models) Run offline evaluations with evaluate() against a cu...
 178
4828 batch-processor claude-office-skills/skills
Batch Processor Skill Overview This skill enables efficient bulk processing of documents - convert, transform, extract, or analyze hundreds of files with parallel execution and progress tracking. How to Use Describe what you want to accomplish Provide any required input data or files I'll execute the appropriate operations Example prompts: "Convert 100 PDFs to Word documents" "Extract text from all images in a folder" "Batch rename and organize files" "Mass update document headers/footers" Domai...
 178
4829 pubmed-search yorkeccak/scientific-skills
PubMed Search Search the complete PubMed database of biomedical literature using natural language queries powered by Valyu's semantic search API. Why This Skill is Powerful No API Parameter Parsing: Just pass natural language queries directly - no need to construct complex search parameters Semantic Search: Understands the meaning of your query, not just keyword matching Full-Text Access: Returns complete article content, not just abstracts Image Links: Includes figures and images from papers ...
 178
4830 repomix mrgoonie/claudekit-skills
Repomix Skill Repomix packs entire repositories into single, AI-friendly files. Perfect for feeding codebases to LLMs like Claude, ChatGPT, and Gemini. When to Use Use when: Packaging codebases for AI analysis Creating repository snapshots for LLM context Analyzing third-party libraries Preparing for security audits Generating documentation context Investigating bugs across large codebases Creating AI-friendly code representations Quick Start Check Installation repomix --version Install np...
 178
4831 data-analysis-jupyter mindrally/skills
Data Analysis and Jupyter Notebook Development You are an expert in data analysis, visualization, and Jupyter Notebook development, with a focus on pandas, matplotlib, seaborn, and numpy. Key Principles Write concise, technical responses with accurate Python examples Prioritize readability and reproducibility in data analysis workflows Favor functional programming approaches; minimize class-based solutions Prefer vectorized operations over explicit loops for better performance Employ descripti...
 178
4832 mot parcadei/continuous-claude-v3
MOT - System Health Check Run comprehensive health checks on all Claude Code components. Usage /mot Full audit (all categories) /mot skills Just skills /mot agents Just agents /mot hooks Just hooks /mot memory Just memory system /mot --fix Auto-fix simple issues /mot --quick P0 checks only (fast) Audit Process Phase 1: Skills Audit Count skills echo "=== SKILLS ===" SKILL_COUNT=$(find .claude/skills -name "SKILL.md" | wc -l | xargs) ec...
 178
4833 executing-plans davila7/claude-code-templates
Executing Plans Overview Load plan, review critically, execute all tasks, report when complete. Announce at start: "I'm using the executing-plans skill to implement this plan." Note: Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use superpowers:subagent-driven-development instead of this skill. The Proce...
 178
4834 android-development dpconde/claude-android-skill
Android Development Build Android applications following Google's official architecture guidance, as demonstrated in the NowInAndroid reference app. Quick Reference Task Reference File Project structure & modules modularization.md Architecture layers (UI, Domain, Data) architecture.md Jetpack Compose patterns compose-patterns.md Gradle & build configuration gradle-setup.md Testing approach testing.md Workflow Decision Tree Creating a new project? → Read modularization.md for project structure...
 178
4835 pdf ocr extraction claude-office-skills/skills
PDF OCR Extraction Extract text from scanned documents and image-based PDFs using OCR technology. Overview This skill helps you: Extract text from scanned documents Make image PDFs searchable Digitize paper documents Process handwritten text (limited) Batch process multiple documents How to Use Basic OCR "Extract text from this scanned PDF" "OCR this document image" "Make this PDF searchable" With Options "Extract text from pages 1-10, English language" "OCR this document, preserve layout" "Extr...
 178
4836 onboard parcadei/continuous-claude-v3
Create or improve onboarding experiences that help users understand, adopt, and succeed with the product quickly. Assess Onboarding Needs Understand what users need to learn and why: Identify the challenge : What are users trying to accomplish? What's confusing or unclear about current experience? Where do users get stuck or drop off? What's the "aha moment" we want users to reach? Understand the users : What's their experience level? (Beginners, power users, mixed?) What's their motivation? (Ex...
 178
4837 telegram-mini-app davila7/claude-code-templates
Telegram Mini App Role: Telegram Mini App Architect You build apps where 800M+ Telegram users already are. You understand the Mini App ecosystem is exploding - games, DeFi, utilities, social apps. You know TON blockchain and how to monetize with crypto. You design for the Telegram UX paradigm, not traditional web. Capabilities Telegram Web App API Mini App architecture TON Connect integration In-app payments User authentication via Telegram Mini App UX patterns Viral Mini App mechanics TON bl...
 178
4838 tanstack-table tanstack-skills/tanstack-skills
TanStack Table Headless data tables with server-side pagination, filtering, sorting, and virtualization for Cloudflare Workers + D1 Quick Start Last Updated : 2026-01-09 Versions : @tanstack/react-table@8.21.3, @tanstack/react-virtual@3.13.18 npm install @tanstack/react-table@latest npm install @tanstack/react-virtual@latest For virtualization Basic Setup (CRITICAL: memoize data/columns to prevent infinite re-renders): import { useReactTable , getCoreRowModel , ColumnDef } from '@tanstack/react...
 178
4839 notion-meeting-intelligence davila7/claude-code-templates
Meeting Intelligence Prep meetings by pulling Notion context, tailoring agendas/pre-reads, and enriching with Codex research. Quick start Confirm meeting goal, attendees, date/time, and decisions needed. Gather context: search with Notion:notion-search , then fetch with Notion:notion-fetch (prior notes, specs, OKRs, decisions). Pick the right template via reference/template-selection-guide.md (status, decision, planning, retro, 1:1, brainstorming). Draft agenda/pre-read in Notion with Notion:not...
 178
4840 frontend-dev-guidelines mrgoonie/claudekit-skills
Frontend Development Guidelines (React · TypeScript · Suspense-First · Production-Grade) You are a senior frontend engineer operating under strict architectural and performance standards. Your goal is to build scalable, predictable, and maintainable React applications using: Suspense-first data fetching Feature-based code organization Strict TypeScript discipline Performance-safe defaults This skill defines how frontend code must be written , not merely how it can be written. 1. Frontend Feasibi...
 178
4841 migrate parcadei/continuous-claude-v3
Migrate to Playwright Interactive migration from Cypress or Selenium to Playwright with file-by-file conversion. Input $ARGUMENTS can be: "from cypress" — migrate Cypress test suite "from selenium" — migrate Selenium/WebDriver tests A file path: convert a specific test file Empty: auto-detect source framework Steps 1. Detect Source Framework Use Explore subagent to scan: cypress/ directory or cypress.config.ts → Cypress selenium , webdriver in package.json deps → Selenium .py test files with sel...
 178
4842 competitive-analysis claude-office-skills/skills
Competitive Analysis Help the user understand competitive dynamics using frameworks from 49 product leaders who have navigated competition at companies from startups to Netflix and Google. How to Help When the user asks for help with competitive analysis: Expand the competitive set - Identify not just direct competitors but the status quo and workarounds Understand the true threat - Determine if the competition is features, distribution, or fundamental business model Find asymmetries - Help them...
 178
4843 aws-lambda-python-integration giuseppe-trisciuoglio/developer-kit
AWS Lambda Python Integration Patterns for creating high-performance AWS Lambda functions in Python with optimized cold starts and clean architecture. Overview This skill provides complete patterns for AWS Lambda Python development, covering two main approaches: AWS Chalice Framework - Full-featured framework with built-in routing, dependency injection, and local testing server Raw Python - Minimal overhead approach with maximum flexibility and control Both approaches support API Gateway and ALB...
 178
4844 skill-seekers sickn33/antigravity-awesome-skills
Skill Seekers Overview -Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes. When to Use This Skill Use this skill when you need to work with -automatically convert documentation websites, github repositories, and pdfs into claude ai skills in minutes.. Instructions This skill provides guidance and patterns for -automatically convert documentation websites, github repositories, and pdfs into claude ai skills in minutes.. For more informati...
 178
4845 compose-outreach anthropics/knowledge-work-plugins
Compose Outreach Generate three personalized outreach formats — email, call script, and LinkedIn message — grounded in Common Room signals for a specific company or contact. Outreach Process Step 1: Look Up the Target Use Common Room MCP tools to find and retrieve data for the target (company and/or specific contact). Pull: Recent product activity and engagement signals Community activity (posts, questions, reactions) 3rd-party intent signals (job postings, news, funding) Relationship history (p...
 178
4846 frontend-react-router-best-practices sergiodxa/agent-skills
Performance optimization and architecture patterns for React Router applications. Contains 55 rules across 11 categories focused on data loading, actions, forms, streaming, and route organization. When to Apply Reference these guidelines when: - Writing new React Router routes (loaders, actions) - Handling forms and mutations - Implementing streaming with Single Fetch - Organizing route files and colocating queries - Setting up authentication patterns - Adding SEO/meta tags Rules Summ...
 178
4847 text-to-speech inference-sh/skills
ElevenLabs Text-to-Speech Generate natural speech from text - supports 70+ languages, multiple models for quality vs latency tradeoffs. Setup: See Installation Guide . For JavaScript, use @elevenlabs/* packages only. Quick Start Python from elevenlabs import ElevenLabs client = ElevenLabs ( ) audio = client . text_to_speech . convert ( text = "Hello, welcome to ElevenLabs!" , voice_id = "JBFqnCBsd6RMkjVDRZzb" , George model_id = "eleven_multilingual_v2" ) with open ( "output.mp3" , "wb" ) as f ...
 178
4848 huggingface-tokenizers davila7/claude-code-templates
HuggingFace Tokenizers - Fast Tokenization for NLP Fast, production-ready tokenizers with Rust performance and Python ease-of-use. When to use HuggingFace Tokenizers Use HuggingFace Tokenizers when: Need extremely fast tokenization (<20s per GB of text) Training custom tokenizers from scratch Want alignment tracking (token → original text position) Building production NLP pipelines Need to tokenize large corpora efficiently Performance: Speed: <20 seconds to tokenize 1GB on CPU Implementat...
 178
4849 fine-tuning-with-trl davila7/claude-code-templates
TRL - Transformer Reinforcement Learning Quick start TRL provides post-training methods for aligning language models with human preferences. Installation: pip install trl transformers datasets peft accelerate Supervised Fine-Tuning (instruction tuning): from trl import SFTTrainer trainer = SFTTrainer( model="Qwen/Qwen2.5-0.5B", train_dataset=dataset, Prompt-completion pairs ) trainer.train() DPO (align with preferences): from trl import DPOTrainer, DPOConfig config = DPOConf...
 178
4850 react-native alinaqi/claude-bootstrap
React Native Skill Load with: base.md + typescript.md Project Structure project/ ├── src/ │ ├── core/ Pure business logic (no React) │ │ ├── types.ts │ │ └── services/ │ ├── components/ Reusable UI components │ │ ├── Button/ │ │ │ ├── Button.tsx │ │ │ ├── Button.test.tsx │ │ │ └── index.ts │ │ └── index.ts Barrel export │ ├── screens/ Screen components │ │ ├── Home/ │ │ │ ├── HomeScree...
 178