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
7601 skill yeachan-heo/oh-my-claudecode
Skill Management CLI Meta-skill for managing oh-my-claudecode skills via CLI-like commands. Subcommands /skill list Show all local skills organized by scope. Behavior: Scan user skills at ~/.claude/skills/omc-learned/ Scan project skills at .omc/skills/ Parse YAML frontmatter for metadata Display in organized table format: USER SKILLS (~/.claude/skills/omc-learned/): | Name | Triggers | Quality | Usage | Scope | |-------------------|--------------------|---------|-------|-...
 112
7602 symfony:runner-selection makfly/superpowers-symfony
$ npx skills add https://github.com/makfly/superpowers-symfony --skill symfony:runner-selection<div
 112
7603 ln-733-env-configurator levnikolaevich/claude-code-skills
ln-733-env-configurator Type: L3 Worker Category: 7XX Project Bootstrap Parent: ln-730-devops-setup Configures environment variables for development and production environments. Purpose & Scope Creates environment configuration files: Does: Generate .env files, update .gitignore for secrets protection Does NOT: Store secrets, manage external secrets managers, configure CI/CD secrets Inputs Input Source Description Project Name Directory name Used for database/service naming Backend Port Sta...
 112
7604 brand-architect shipshitdev/library
Brand Architect - Day-One Brand Strategy Overview Help indie founders build brands that scale using Hexa's "Branding from Day One" methodology. Execute strategic brand development by guiding users through naming, positioning, voice, and visual identity foundations. Hexa's Core Principle: "The name of your business should reflect not only your initial point of entry in the market but also where you aim to be in the future." When This Activates "What should I name it" Brand name questions Brand...
 112
7605 secondme mindverse/second-me-skills
SecondMe 一站式项目创建 将 secondme-init → secondme-prd → secondme-nextjs 三个步骤合并为一个完整流程。 工具使用： 收集用户输入时使用 AskUserQuestion 工具。 参数说明 参数 说明 (无参数) 完整流程：初始化 → PRD → 生成项目 --quick 快速流程：初始化 → 跳过 PRD → 生成项目 执行流程 环境检查（首次执行前） 重要提醒： 当前目录将作为项目根目录，Next.js 项目会直接在此目录中初始化。 显示当前工作目录路径，让用户确认： 📂 当前工作目录: /path/to/current/dir ⚠️ Next.js 项目将直接在此目录中初始化，请确保你已在一个新建的空文件夹中运行。 检查当前目录内容（除 .secondme/ 、 .git/ 、 CLAUDE.md 、 .claude/ 等配置文件外）： 如果目录为空或仅有配置文件 ：继续 如果存在其他文件 ：发出警告并使用 AskUserQuestion 让用户确认是否继续 阶段 0：检测当前状态 检查 .secondme/state.js...
 112
7606 multi-cloud-strategy aj-geddes/useful-ai-prompts
Multi-Cloud Strategy Overview Multi-cloud strategies enable leveraging multiple cloud providers for flexibility, redundancy, and optimization. Avoid vendor lock-in, optimize costs by comparing cloud services, and implement hybrid deployments with seamless data synchronization. When to Use Reducing vendor lock-in risk Optimizing costs across providers Geographic distribution requirements Compliance with regional data laws Disaster recovery and high availability Hybrid cloud deployments Multi-re...
 112
7607 monday membranedev/application-skills
Monday Monday.com is a work operating system where teams can plan, track, and manage their work. It's used by project managers, marketing teams, and sales teams to improve collaboration and execution. Official docs: https://developers.monday.com/ Monday Overview Board Item Column User When to use which actions: Use action names and parameters as needed. Working with Monday This skill uses the Membrane CLI to interact with Monday. Membrane handles authentication and credentials refresh automatica...
 112
7608 product manager aj-geddes/claude-code-bmad-skills
Product Manager Skill Role: Phase 2 - Planning and requirements specialist Function: Create comprehensive requirements documents (PRDs), define functional and non-functional requirements, prioritize features, break down work into epics and user stories, and create lightweight technical specifications for smaller projects. When to Use This Skill Use this skill when you need to: Create Product Requirements Documents (PRDs) for Level 2+ projects Create Technical Specifications for Level 0-1 project...
 112
7609 landing-page-designer eddiebe147/claude-settings
No SKILL.md available for this skill. View on GitHub
 112
7610 auto-trigger charon-fan/agent-playbook
Auto-Trigger Hooks This skill defines automatic trigger relationships between skills. When a skill completes its workflow, it should automatically trigger the next skill in the chain. Hook Definitions PRD Creation Chain prd_complete: triggers: - skill: self-improving-agent mode: background condition: PRD file exists and is complete - skill: session-logger mode: auto context: "PRD created for {feature_name}" prd_implemented: triggers: - skill: session-lo...
 112
7611 secondme-nextjs mindverse/second-me-skills
SecondMe Next.js 项目生成 基于 /secondme-init 的配置和 /secondme-prd 的需求定义，生成完整的 Next.js 项目。 前置条件检查 1. 检查 state.json 首先检查 .secondme/state.json 是否存在： 不存在 → 提示： 请先运行 /secondme-init 初始化项目配置 存在 → 继续 2. 检查执行模式 检查参数是否包含 --quick ： 快速模式 (--quick) ： 跳过 stage 检查 使用默认 PRD 配置 直接开始生成项目 标准模式 ： 检查 stage >= "prd" 如果 stage == "init" → 提示： 请先运行 /secondme-prd 定义需求，或使用 /secondme-nextjs --quick 快速生成 如果 stage >= "prd" → 继续 读取配置 从 .secondme/state.json 读取： const state = { app_name : "secondme-tinder" , // 应用名称 modules : [ "auth"...
 112
7612 aggregating-crypto-news jeremylongshore/claude-code-plugins-plus-skills
Aggregating Crypto News Overview This skill aggregates cryptocurrency news from 50+ authoritative sources using RSS feeds. It provides real-time news scanning with filtering by coin, category, time window, and relevance scoring. Key Capabilities: Multi-source aggregation from top crypto news sites Coin-specific filtering (BTC, ETH, SOL, etc.) Category filtering (DeFi, NFT, regulatory, exchange, etc.) Relevance scoring with market-moving keyword detection Multiple output formats (table, JSON, ...
 112
7613 avalonia-layout-zafiro davila7/claude-code-templates
Avalonia Layout with Zafiro.Avalonia Master modern, clean, and maintainable Avalonia UI layouts. Focus on semantic containers, shared styles, and minimal XAML. 🎯 Selective Reading Rule Read ONLY files relevant to the layout challenge! 📑 Content Map File Description When to Read themes.md Theme organization and shared styles Setting up or refining app themes containers.md Semantic containers ( HeaderedContainer , EdgePanel , Card ) Structuring views and layouts icons.md Icon usage with IconExtens...
 112
7614 creating-reanimated-animations estevg/skills
React Native Reanimated Code Generator Generate performant animation code using React Native Reanimated. Supports both v3 and v4. Version Detection Check the project's package.json to determine the version: v4 (New Architecture only): requires react-native-worklets as separate dependency v3 (supports Legacy and New Architecture): single package install Setup Reanimated v4 (latest) npm install react-native-reanimated react-native-worklets Babel plugin: 'react-native-worklets/plugin' (must be last...
 112
7615 extract-transcripts 0xbigboss/claude-code
Extract Transcripts Extracts readable markdown transcripts from Claude Code and Codex CLI session JSONL files. Scripts Claude Code Sessions Extract a single session uv run ~/.claude/skills/extract-transcripts/extract_transcript.py <session.jsonl> With tool calls and thinking blocks uv run ~/.claude/skills/extract-transcripts/extract_transcript.py <session.jsonl> --include-tools --include-thinking Extract all sessions from a directory uv run ~/.claude/skills/extract-transcripts/extract_tra...
 112
7616 refactoring-specialist charon-fan/agent-playbook
Refactoring Specialist Expert guidance on refactoring code to improve structure, readability, and maintainability while preserving functionality. When This Skill Activates Activates when you: Ask to refactor code Request cleanup or improvement Mention "technical debt" or "code smell" Want to improve code quality Refactoring Principles Preserve Behavior : Refactoring must not change external behavior Small Steps : Make small, incremental changes Test Coverage : Ensure tests pass before and after ...
 112
7617 ln-633-test-value-auditor levnikolaevich/claude-code-skills
Specialized worker calculating Usefulness Score for each test. Purpose & Scope - Worker in ln-630 coordinator pipeline - Audit Risk-Based Value (Category 3: Critical Priority) - Calculate Usefulness Score = Impact × Probability - Make KEEP/REVIEW/REMOVE decisions - Calculate compliance score (X/10) Inputs (from Coordinator) Receives `contextStore` with Impact/Probability matrices, test file list. Workflow - Parse context - For each test: calculate Usefulness Score - Classify: KEEP...
 112
7618 axiom-networking-legacy charleswiltgen/axiom
Legacy iOS 12-25 NWConnection Patterns These patterns use NWConnection with completion handlers for apps supporting iOS 12-25. If your app targets iOS 26+, use NetworkConnection with async/await instead (see axiom-network-framework-ref skill). Pattern 2a: NWConnection with TLS (iOS 12-25) Use when Supporting iOS 12-25, need TLS encryption, can't use async/await yet Time cost 10-15 minutes GOOD: NWConnection with Completion Handlers import Network // Create connection with TLS let connectio...
 112
7619 autonomous-agent-gaming qodex-ai/ai-agent-skills
Autonomous Agent Gaming Build sophisticated game-playing agents that learn strategies, adapt to opponents, and master complex games through AI and reinforcement learning. Overview Autonomous game agents combine: Game Environment Interface: Connect to game rules and state Decision-Making Systems: Choose optimal actions Learning Mechanisms: Improve through experience Strategy Development: Long-term planning and adaptation Applications Chess and board game masters Real-time strategy (RTS) game ...
 112
7620 vue-best-practices dedalus-erp-pas/foundation-skills
Vue Best Practices Workflow Use this skill as an instruction set. Follow the workflow in order unless the user explicitly asks for a different order. Core Principles Keep state predictable: one source of truth, derive everything else. Make data flow explicit: Props down, Events up for most cases. Favor small, focused components: easier to test, reuse, and maintain. Avoid unnecessary re-renders: use computed properties and watchers wisely. Readability counts: write clear, self-documenting code. 1...
 112
7621 youtube-uploader aviz85/claude-skills-library
YouTube Uploader Upload videos to YouTube with full metadata control. Quick Start cd ~/.claude/skills/youtube-uploader/scripts First time: authenticate npx ts-node youtube-upload.ts --auth Upload video npx ts-node youtube-upload.ts \ --video /path/to/video.mp4 \ --title "My Awesome Video" \ --description "Check out this amazing content!" \ --tags "tech,ai,tutorial" \ --privacy unlisted Upload as YouTube Short (vertical video) npx ts-node youtube-upload.ts \ --video /path/to/s...
 112
7622 upgrade-solidity-contracts openzeppelin/openzeppelin-skills
Solidity Upgrades Contents Proxy Patterns Overview Upgrade Restrictions Between Major Versions (v4 → v5) Writing Upgradeable Contracts Hardhat Upgrades Workflow Foundry Upgrades Workflow Handling Upgrade Validation Issues Upgrade Safety Checklist Proxy Patterns Overview Pattern Upgrade logic lives in Best for UUPS ( UUPSUpgradeable ) Implementation contract (override _authorizeUpgrade ) Most projects — lighter proxy, lower deploy gas Transparent Separate ProxyAdmin contract When admin/user call ...
 112
7623 smtp2go-api jezweb/claude-skills
SMTP2GO API Integration Build email and SMS delivery with the SMTP2GO transactional API. Quick Start // Send email with SMTP2GO const response = await fetch ( 'https://api.smtp2go.com/v3/email/send' , { method : 'POST' , headers : { 'Content-Type' : 'application/json' , 'X-Smtp2go-Api-Key' : env . SMTP2GO_API_KEY , } , body : JSON . stringify ( { sender : 'noreply@yourdomain.com' , to : [ 'recipient@example.com' ] , subject : 'Hello from SMTP2GO' , html_body : '<h1>Welcome!</h1><p>Your account i...
 112
7624 computer-vision-expert sickn33/antigravity-awesome-skills
Computer Vision Expert (SOTA 2026) Role : Advanced Vision Systems Architect & Spatial Intelligence Expert Purpose To provide expert guidance on designing, implementing, and optimizing state-of-the-art computer vision pipelines. From real-time object detection with YOLO26 to foundation model-based segmentation with SAM 3 and visual reasoning with VLMs. When to Use Designing high-performance real-time detection systems (YOLO26). Implementing zero-shot or text-guided segmentation tasks (SAM 3). Bui...
 112
7625 event-driven-architect 404kidwiz/claude-supercode-skills
Event-Driven Architect Purpose Provides expertise in designing and implementing event-driven architectures. Covers message brokers, event sourcing, CQRS, and standards like CloudEvents and AsyncAPI for building scalable, decoupled systems. When to Use Designing event-driven architectures Implementing message queues and brokers Building event sourcing systems Implementing CQRS patterns Creating AsyncAPI specifications Designing event mesh topologies Building asynchronous microservices Quick Sta...
 112
7626 ln-130-tasks-docs-creator levnikolaevich/claude-code-skills
This skill creates task management documentation: docs/tasks/README.md (task management system rules) and docs/tasks/kanban_board.md (Linear integration with Epic Story Counters). When to Use This Skill This skill is a L2 WORKER invoked by ln-100-documents-pipeline orchestrator OR used standalone. Use this skill when: - Creating task management documentation (docs/tasks/) - Setting up Linear integration and kanban board - Validating existing task documentation structure and content - Con...
 112
7627 trigger-dev davila7/claude-code-templates
Trigger.dev Integration You are a Trigger.dev expert who builds reliable background jobs with exceptional developer experience. You understand that Trigger.dev bridges the gap between simple queues and complex orchestration - it's "Temporal made easy" for TypeScript developers. You've built AI pipelines that process for minutes, integration workflows that sync across dozens of services, and batch jobs that handle millions of records. You know the power of built-in integrations and the importan...
 112
7628 hummingbot hummingbot/skills
hummingbot When the skill is loaded, print this ASCII art: *,. *,,.* ,,,, .,* *,,,,,,,( .,, *,,,,,,,, .,,, * /,,,,,,,,,, .*,,,,,,, .,,,,,,,,,,, .,,,,,,,,,,* // ,,,,,,,,,,,,,,,,,,,,,,,,,,*% .,,,,,,,. *,,,,,,,,,,,,,,,,,,,,,,,,,,,,,%%%%&@ ,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,%%%%%%%& ,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,%%%%%%%%& /*,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,((%%%& . ,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,((((((((. ...
 112
7629 wix-cli-backend-event wix/skills
Wix CLI Backend Event Extension Creates event extensions for Wix CLI applications. Events are triggered when specific conditions occur—on a Wix user's site for app projects, or on your project's site for headless projects. Your project responds using event extensions built on JavaScript SDK webhooks; the CLI subscribes your project to these webhooks. Common use cases: run logic when a contact is created, an order is placed, a booking is confirmed, or a blog post is published. Quick Start Checkli...
 112
7630 revision jwynia/agent-skills
Revision: Diagnostic Skill You diagnose revision-level problems and guide systematic manuscript improvement. Your role is to help writers work through revision efficiently and know when they're done. Core Principle Revision is not one activity but many, each operating at a different scale. Work from largest scale to smallest: Developmental (structure, story) Line (sentences, paragraphs) Copy (mechanics, consistency) Crucial insight: Polishing prose in a scene you'll later cut is wasted eff...
 112
7631 release yeachan-heo/oh-my-claudecode
Release Skill Purpose: Take a project from "code is ready" to "tagged and ready to push." Pre-flight validation, changelog from git history, version bumps across package files, release commit, annotated tag, and curated release notes. Everything is local and reversible. Publishing (including the GitHub Release page) is CI's job. Quick Start /release 1.7 .0 full release: changelog + bump + commit + tag /release 1.7 .0 --dry-run show what would happen, change nothing /release --check readiness ...
 112
7632 angular sickn33/antigravity-awesome-skills
Angular You are an Angular, SASS, and TypeScript expert creating scalable, high-performance web applications with strict type safety and Angular's official style guide adherence. Core Principles Provide concise, precise examples with clear explanations Apply immutability and pure functions throughout services and state management Favor component composition over inheritance for enhanced modularity Use descriptive naming conventions (e.g., isUserLoggedIn, fetchData()) Enforce kebab-case file na...
 112
7633 schema-exploration langchain-ai/deepagents
Schema Exploration Skill When to Use This Skill Use this skill when you need to: Understand the database structure Find which tables contain certain types of data Discover column names and data types Map relationships between tables Answer questions like "What tables are available?" or "What columns does the Customer table have?" Workflow 1. List All Tables Use sql_db_list_tables tool to see all available tables in the database. This returns the complete list of tables you can query. 2. Get...
 112
7634 axiom-ui-recording charleswiltgen/axiom
Recording UI Automation (Xcode 26+) Guide to Xcode 26's Recording UI Automation feature for creating UI tests through user interaction recording. The Three-Phase Workflow From WWDC 2025-344: ┌─────────────────────────────────────────────────────────────┐ │ UI Automation Workflow │ ├─────────────────────────────────────────────────────────────┤ │ │ │ 1. RECORD ──────► Interact with app in Simulat...
 112
7635 correlation analysis aj-geddes/useful-ai-prompts
Correlation Analysis Overview Correlation analysis measures the strength and direction of relationships between variables, helping identify which features are related and detect multicollinearity. When to Use Identifying relationships between numerical variables Detecting multicollinearity before regression modeling Exploratory data analysis to understand feature dependencies Feature selection and dimensionality reduction Validating assumptions about variable relationships Comparing linear and n...
 112
7636 tooluniverse-gwas-trait-to-gene mims-harvard/tooluniverse
GWAS Trait-to-Gene Discovery Discover genes associated with diseases and traits using genome-wide association studies (GWAS) Overview This skill enables systematic discovery of genes linked to diseases/traits by analyzing GWAS data from two major resources: GWAS Catalog (EBI/NHGRI): Curated catalog of published GWAS with >500,000 associations Open Targets Genetics : Fine-mapped GWAS signals with locus-to-gene (L2G) predictions Use Cases Clinical Research "What genes are associated with type 2 di...
 112
7637 new-component longbridge/gpui-component
Instructions When creating new GPUI components: Follow existing patterns: Base implementation on components in crates/ui/src (examples: Button, Select) Style consistency: Follow existing component styles and Shadcn UI patterns Component type decision: Use stateless elements for simple components (like Button) Use stateful elements for complex components with data (like Select and SelectState) API consistency: Maintain the same API style as other elements Documentation: Create component documen...
 112
7638 ln-775-api-docs-generator levnikolaevich/claude-code-skills
Type: L3 Worker Category: 7XX Project Bootstrap Parent: ln-770-crosscutting-setup Configures API documentation with Swagger/OpenAPI. Overview | Input | Context Store from ln-770 | Output | Swagger/OpenAPI configuration | Stacks | .NET (Swashbuckle), Python (FastAPI built-in) Phase 1: Receive Context + Analyze API Structure Accept Context Store and scan for API endpoints. Required Context: - `STACK`: .NET or Python - `PROJECT_ROOT`: Project directory path Idempotency Check: - ...
 112
7639 ln-220-story-coordinator levnikolaevich/claude-code-skills
Universal Story management coordinator that delegates CREATE/REPLAN operations to specialized workers after building IDEAL Story plan. When to Use This Skill Use when: - Decompose Epic to User Stories (5-10 Stories covering Epic scope) - Update existing Stories when Epic requirements change - Rebalance Story scopes within Epic - Add new Stories to existing Epic structure Core Pattern: Decompose-First Key principle: Build IDEAL Story plan FIRST, THEN check existing Stories to determine ...
 112
7640 windows privilege escalation davila7/claude-code-templates
Windows Privilege Escalation Purpose Provide systematic methodologies for discovering and exploiting privilege escalation vulnerabilities on Windows systems during penetration testing engagements. This skill covers system enumeration, credential harvesting, service exploitation, token impersonation, kernel exploits, and various misconfigurations that enable escalation from standard user to Administrator or SYSTEM privileges. Inputs / Prerequisites Initial Access : Shell or RDP access as standard...
 112
7641 difficult-workplace-conversations davila7/claude-code-templates
Difficult Conversations Skill A structured framework for approaching challenging workplace conversations including conflicts, performance issues, sensitive feedback, and emotionally charged discussions. When to Use This Skill Preparing for a challenging conversation with a colleague Addressing performance issues with a team member Delivering difficult feedback to a peer or manager Navigating conflict between team members Discussing sensitive topics (salary, promotion, termination) Handling emoti...
 112
7642 regression modeling aj-geddes/useful-ai-prompts
Regression Modeling Overview Regression modeling predicts continuous target values based on input features, establishing quantitative relationships between variables for forecasting and analysis. When to Use Predicting sales, prices, or other continuous numerical outcomes Understanding relationships between independent and dependent variables Forecasting trends based on historical data Quantifying the impact of features on a target variable Building baseline models for comparison with more compl...
 112
7643 winui-app openai/skills
WinUI App Use this skill for WinUI 3 and Windows App SDK work that needs grounded setup guidance, app bootstrap, modern Windows UX decisions, or concrete implementation patterns. Required Flow Classify the task as environment/setup, new-app bootstrap, design, implementation, review, or troubleshooting. If the task is about preparing a machine for WinUI, auditing readiness, or creating a brand new app, start with the bundled setup-and-scaffold flow in this skill before broader design, implementat...
 112
7644 biome-validator gracefullight/stock-checker
Biome Validator Validates Biome 2.3+ configuration and prevents outdated patterns. Ensures type-aware linting, domains, and modern Biome features are properly configured. When This Activates Setting up linting for a new project Before any code quality work Auditing existing Biome configurations After AI generates biome.json CI/CD pipeline validation Quick Start python3 ~/.claude/skills/biome-validator/scripts/validate.py --root . python3 ~/.claude/skills/biome-validator/scripts/validate.py --roo...
 112
7645 performance-testing-review-multi-agent-review sickn33/antigravity-awesome-skills
Multi-Agent Code Review Orchestration Tool Use this skill when Working on multi-agent code review orchestration tool tasks or workflows Needing guidance, best practices, or checklists for multi-agent code review orchestration tool Do not use this skill when The task is unrelated to multi-agent code review orchestration tool You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Prov...
 112
7646 openspec itechmeat/llm-code
OpenSpec (OPSX) Skill Use this skill to guide or reason about the OpenSpec artifact-driven workflow system (OPSX), including artifact graphs, schema/template resolution, change lifecycle, and experimental commands/skills. When to Use You need to explain or apply the artifact-driven workflow (OPSX). You are planning or reviewing changes based on artifact dependencies. You need to interpret schema/template resolution rules (XDG + built-ins). You are asked to design or validate changes to the Ope...
 112
7647 axiom-core-spotlight-ref charleswiltgen/axiom
Core Spotlight & NSUserActivity Reference Overview Comprehensive guide to Core Spotlight framework and NSUserActivity for making app content discoverable in Spotlight search, enabling Siri predictions, and supporting Handoff. Core Spotlight directly indexes app content while NSUserActivity captures user engagement for prediction. Key distinction Core Spotlight = indexing all app content; NSUserActivity = marking current user activity for prediction/handoff. When to Use This Skill Use this sk...
 112
7648 pencil-renderer phrazzld/claude-config
Pencil Renderer Translate aesthetic DNA codes into Pencil .pen frames via MCP. Interface Input: DNA code: [layout, color, typography, motion, density, background] Component type: hero | card | form | nav | footer | section | button | input Optional: Name, dimensions, parent frame ID Output: Frame ID in .pen file Screenshot of rendered frame Workflow 1. Ensure Document Ready // Check if editor open mcp__pencil__get_editor_state({ include_schema: false }) // If no editor, open or create mcp...
 112
7649 evaluate-rag hamelsmu/evals-skills
Evaluate RAG Overview Do error analysis on end-to-end traces first. Determine whether failures come from retrieval, generation, or both. Build a retrieval evaluation dataset: queries paired with relevant document chunks. Measure retrieval quality with Recall@k (most important for first-pass retrieval). Evaluate generation separately: faithfulness (grounded in context?) and relevance (answers the query?). If retrieval is the bottleneck, optimize chunking via grid search before tuning generation. ...
 112
7650 langgraph-implementation existential-birds/beagle
LangGraph Implementation Core Concepts LangGraph builds stateful, multi-actor agent applications using a graph-based architecture: StateGraph: Builder class for defining graphs with shared state Nodes: Functions that read state and return partial updates Edges: Define execution flow (static or conditional) Channels: Internal state management (LastValue, BinaryOperatorAggregate) Checkpointer: Persistence for pause/resume capabilities Essential Imports from langgraph.graph import StateGraph, STA...
 112