Skip to main content
ClaudeWave
ES, Spanish
shanraisshan / Subagents

claude-code-best-practice

from vibe coding to agentic engineering - practice makes claude perfect

  • 67.9k estrellas
  • 6.8k forks
  • 28 issues abiertos
  • Lenguaje: HTML
  • Licencia: MIT
  • actualizado

Instalación

Terminal
git clone https://github.com/shanraisshan/claude-code-best-practice && cp claude-code-best-practice/*.md ~/.claude/agents/
  1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
  2. Start a new Claude Code session to load the agents.
  3. Delegate work to them with the Task/Agent tool or by name.

Nota editorial

This repository is a structured reference collection covering Claude Code features including subagents, slash commands, skills, hooks, MCP servers, memory management, settings, orchestration workflows, and CLI startup flags. Each concept is organized under `.claude/` subdirectories (for example, `.claude/agents/`, `.claude/commands/`, `.claude/skills/`) and paired with both a best-practice guide and a working implementation example. The repository targets Claude Code users specifically, from beginners writing simple prompts to developers building multi-agent orchestration pipelines where one agent coordinates others. A notable standout is its weather-orchestrator example, which demonstrates a full orchestration workflow using Claude Code commands. The repo also cross-references tips attributed to Boris Cherny and links to official Anthropic skills from the `anthropics/skills` repository. Developers learning to structure Claude Code projects, adopt context engineering practices, or migrate from ad hoc prompting toward repeatable agentic workflows are the primary audience.

Items instalables

24 items en este repositorio

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Instalar
agent-collectionsSlash Command

Update the AGENT COLLECTIONS table by researching all agent-collection repos in parallel

Instalar

Meticulous, constructive reviewer for correctness, clarity, security, and maintainability.

Instalar

Validates roadmap items, features, and technical decisions against the project's constitution, principles, and core values. Ensures all proposals align with the mission, established methodology, and design principles before implementation proceeds.

Instalar

Update the DEVELOPMENT WORKFLOWS table by researching all 11 workflow repos in parallel

Instalar

Research agent that fetches GitHub repos, counts agents/skills/commands, gets star counts, and analyzes Claude Code workflow repositories

Instalar

Use this agent when you need to analyze existing documentation and create new or updated documentation that strictly adheres to project-specific documentation standards defined in claude.md. This agent excels at maintaining consistency with established documentation patterns, ensuring technical accuracy, and producing clear, well-structured documentation.

Instalar
implementSlash Command

Execute phased implementation with validation gates

Instalar
planSlash Command

Create comprehensive planning documentation for a feature

Instalar

PROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-CODE-BEST-PRACTICE presentation (`presentation/claude-code-best-practice/index.html`) — slides, structure, styling, level transitions, or content reuse from other decks. This is the canonical reusable Claude Code best-practices deck. Do NOT use this agent for the vibe-coding presentation (use `presentation-vibe-coding`) or the GDG Kolachi claude-gemini presentation (use `presentation-claude-gemini`).

Instalar

PROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-GEMINI presentation (`presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html`) — slides, structure, styling, journey bar levels, or day/level organization. Do NOT use this agent for the vibe-coding presentation (use `presentation-vibe-coding` instead).

Instalar

Knowledge about the presentation slide format, weight system, navigation, and section structure

Instalar

Knowledge about CSS classes, component patterns, and syntax highlighting in the presentation

Instalar

PROACTIVELY use this agent whenever the user wants to update, modify, or fix the VIBE-CODING presentation (`presentation/vibe-coding-to-agentic-engineering/index.html`) — slides, structure, styling, or level transitions. Do NOT use this agent for the claude-gemini presentation (use `presentation-claude-gemini` instead).

Instalar

Turns a high-level ask into a crisp, exec-ready PRD with acceptance criteria and scope.

Instalar
reportsSkill
Instalar

Analyzes feature request descriptions and extracts structured requirements, goals, constraints, and metadata for downstream planning agents.

Instalar
researchSlash Command

Research and analyze feature viability - GO/NO-GO decision gate

Instalar

Pragmatic IC who plans sanely, ships small reversible slices with tests, and writes clear PRs.

Instalar
skill-collectionsSlash Command

Update the SKILL COLLECTIONS table by researching all 5 skill-collection repos in parallel

Instalar

Use this agent to align technological decisions with engineering principles and organizational standards. This agent acts as a CTO, evaluating technical recommendations against established engineering frameworks, risk assessment methodologies, and business alignment criteria before documentation creation. It ensures all technical decisions follow systematic methodology, evidence-based risk reduction, and AI-first development principles while maintaining alignment with venture success metrics.

Instalar
time-agentSubagent

Use this agent to fetch the current time for Dubai, UAE (Asia/Dubai timezone, UTC+4). This agent fetches real-time Dubai time using its preloaded time-fetcher skill.

Instalar

Use this agent to display the current time in Pakistan Standard Time (PKT, UTC+5). (root scope — see agent-teams for Dubai time)

Instalar
time-commandSlash Command

Display the current time in Pakistan Standard Time (PKT, UTC+5)

Instalar
README

Resumen de Subagents

README completo en GitHub

claude-code-best-practice

from vibe coding to agentic engineering - practice makes claude perfect

updated with Claude Code

Best Practice Implemented Orchestration Workflow Claude Boris Community Click on these badges below to see the actual sources

= Agents · = Commands · = Skills

    

Boris Cherny on X (tweet 1 · tweet 2 · tweet 3)

Tip

Visit the How to Use section to take full advantage of this repo.

🧠 CONCEPTS

FeatureLocationDescription
Subagents.claude/agents/.mdBest Practice Implemented
Commands.claude/commands/.mdBest Practice Implemented
Skills.claude/skills//SKILL.mdBest Practice Implemented Official Skills · Skills for Mono-repos
Workflows.claude/commands/weather-orchestrator.mdOrchestration Workflow
Hooks.claude/hooks/Best Practice Implemented Guide
MCP Servers.claude/settings.json, .mcp.jsonBest Practice Implemented
Pluginsdistributable packagesMarketplaces · Create Marketplaces
Settings.claude/settings.jsonBest Practice Implemented Permissions · Model Config · Output Styles · Sandboxing · Keybindings · Auto Mode Config
Status Line.claude/settings.jsonBest Practice Implemented
MemoryCLAUDE.md, .claude/rules/, ~/.claude/rules/, ~/.claude/projects//memory/Best Practice Implemented Auto Memory · Auto Memory Deep-dive · Rules
Checkpointingautomatic (file-edit tracking)
Sessions--resume, --continue, /resume, /branch
Context Window/compact, /clear, /context
CLI Startup Flagsclaude [flags]Best Practice Interactive Mode · Env Vars
AI TermsBest Practice
Best PracticesPrompt Engineering · Extend Claude Code
Prompt Library
🔥 Hot
FeatureLocationDescription
Ultrareview beta/code-review ultra, claude ultrareview [target]Tasks tracking
Devcontainers.devcontainer/
Channels beta--channels, plugin-basedReference
No Flicker Mode beta/tui fullscreen, CLAUDE_CODE_NO_FLICKER=1Best Practice
Auto Mode--permission-mode auto, Shift+TabBest Practice Blog
Power-ups/powerupBest Practice
Fast Mode beta/fast, "fastMode": true
Advisor beta/advisor, advisorModel, --advisorBlog
Computer Use betacomputer-use MCP serverDesktop
Agent SDKnpm / pip packageQuickstart · Examples
Ralph Wiggum LooppluginBest Practice Implemented
Chrome--chrome, extensionBest Practice
Claude Code Web betaclaude.ai/codeRoutines
Artifacts/share, Artifact tool
Slack@Claude in Slack
Topics
agentic-aiagentic-codingagentic-engineeringagentic-workflowaiai-agentsanthropicbest-practicesborisclaudeclaude-aiclaude-codeclaude-code-agentsclaude-code-best-practicesclaude-code-commandsclaude-code-skillscontext-engineeringpakistanpakistani-developervibe-coding
Preguntas frecuentes

Lo que la gente pregunta sobre claude-code-best-practice

¿Qué es shanraisshan/claude-code-best-practice?

shanraisshan/claude-code-best-practice es subagents para el ecosistema de Claude AI. from vibe coding to agentic engineering - practice makes claude perfect Tiene 67.9k estrellas en GitHub y su última actualización registrada es del 2026-10-23.

¿Cómo se instala claude-code-best-practice?

Puedes instalar claude-code-best-practice clonando el repositorio (https://github.com/shanraisshan/claude-code-best-practice) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.

¿Es seguro usar shanraisshan/claude-code-best-practice?

Nuestro agente de seguridad ha analizado shanraisshan/claude-code-best-practice y le ha asignado un Trust Score de 100/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.

¿Quién mantiene shanraisshan/claude-code-best-practice?

shanraisshan/claude-code-best-practice es mantenido por shanraisshan. La última actividad registrada en GitHub es del 2026-10-23, con 28 issues abiertos.

¿Hay alternativas a claude-code-best-practice?

Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.

¿Mantienes este repo? Muestra su Trust Score en tu README

La insignia muestra el Trust Score y el veredicto actuales de este repositorio y enlaza a esta página. Sigue los datos del catálogo: nadie puede comprar ni editar la puntuación que enseña.

ClaudeWave Trust Score for shanraisshan/claude-code-best-practice
Markdown (README)
[![ClaudeWave Trust Score for shanraisshan/claude-code-best-practice](https://claudewave.com/api/badge/shanraisshan-claude-code-best-practice)](https://claudewave.com/en/repo/shanraisshan-claude-code-best-practice)
HTML
<a href="https://claudewave.com/en/repo/shanraisshan-claude-code-best-practice"><img src="https://claudewave.com/api/badge/shanraisshan-claude-code-best-practice" alt="ClaudeWave Trust Score for shanraisshan/claude-code-best-practice" width="320" height="64"></a>

Qué significa la insignia y cómo se calcula la puntuación

Alternativas

Ver todas