Skip to content
alyn
davila7

claude-code-templates

Open-source registry and CLI for Claude Code components: agents, commands, skills, hooks, MCPs, settings and mods

$npx skills add davila7/claude-code-templates
Stars
33,273
Installs
285k
Forks
3.9k
Updated
7 h ago
License
MIT

926 skills in this pack.

82
davila7

owasp-security

Comprehensive OWASP-aligned security guidance across six standards - Top 10 (2021) for web apps, ASVS 5.0, MASVS v2.1.0 for mobile, API Security Top 10 (2023), Kubernetes Top 10 (2022), and…

33k285kSecurity
80
davila7

agents-autogpt

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step…

33k285kResearch
80
davila7

agents-crewai

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent…

33k285kResearch
80
davila7

agents-langchain

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory…

33k285kAI engineering
80
davila7

agents-llamaindex

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and…

33k285kAI engineering
80
davila7

data-processing-nemo-curator

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII…

33k285kResearch
80
davila7

data-processing-ray-data

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine…

33k285kResearch
80
davila7

distributed-training-accelerate

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision…

33k285kAI engineering
80
davila7

distributed-training-deepspeed

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

33k285kAI engineering
80
davila7

distributed-training-megatron-core

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47%…

33k285kAI engineering
79
davila7

design-to-code

Pixel-perfect Figma to React conversion using coderio. Generates production-ready code (TypeScript, Vite, TailwindCSS V4) with high visual fidelity. Features robust error handling…

33k285kDesign
78
davila7

ai-release-hunter

Daily digest of AI releases from Anthropic, Meta, Vercel Labs, OpenAI and Google GitHub repos, the Claude Cowork changelog, the claude.dev blog and Hacker News, deduplicated against a local…

33k285kDevOps
78
davila7

autonomous-agent-patterns

Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents…

33k285kResearch
78
davila7

computer-use-agents

Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and…

33k285kResearch
78
davila7

crewai

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process…

33k285kResearch
78
davila7

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.

33k285kResearch
78
davila7

data-scientist

Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.

33k285kScience
78
davila7

deep-research-notebooklm

Deep research skill powered by NotebookLM MCP. Conducts structured multi-source research (market analysis, competitive intel, trend analysis, prospect research) using Google NotebookLM as…

33k285kResearch
78
davila7

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

33k285kResearch
77
davila7

behavioral-modes

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

33k285kResearch
77
davila7

datadog-cli

Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.

33k285kResearch
76
davila7

gmod-addon-maker

A tool for creating and managing Garry's Mod addons, including Lua scripting, content creation, and addon packaging. Use when: developing new addons, writing Lua scripts for GMod…

33k285kWriting
75
davila7

agent-management

Create, manage, and orchestrate AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "hibernate agent", "wake agent", "install…

33k285kCoding
75
davila7

agent-messaging

Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox"…

33k285kProductivity
75
davila7

deep-research

Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.

33k285kResearch
75
davila7

planning

Create and manage persistent markdown planning files for structured task execution. Use when the user asks to "create a plan", "track progress", "start a research project", or when a task…

33k285kProductivity
74
davila7

agent-evaluation

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on…

33k285kTesting
74
davila7

agent-memory-mcp

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

33k285kProductivity
74
davila7

agent-memory-systems

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term…

33k285kProductivity
74
davila7

ai-agents-architect

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous…

33k285kResearch
74
davila7

autonomous-agents

Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them…

33k285kResearch
74
davila7

claude-code-guide

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the…

33k285kResearch
74
davila7

docs-search

Search auto-generated codebase documentation for function signatures, API docs, class definitions, and code comments. Use when the user asks to "search docs", "find documentation", "look up…

33k285kCoding
74
davila7

graph-query

Query the code graph database to understand component relationships, dependencies, and change impact. Use when the user asks to "find callers", "check dependencies", "what uses this", "show…

33k285kCoding
74
davila7

memory-search

Search conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search memory", "what did we discuss", "remember when"…

33k285kProductivity
73
davila7

agent-manager-skill

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

33k285kResearch
73
davila7

agent-tool-builder

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than…

33k285kResearch
73
davila7

context-window-management

Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context…

33k285kProductivity
73
davila7

context7-auto-research

Automatically fetch latest library/framework documentation for Claude Code via Context7 API

33k285kResearch
73
davila7

conversation-memory

Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat…

33k285kProductivity

Showing 40 of 926. See the full pack on GitHub.

From the README

How to use claude-code-templates

Claude Code Templates logo

Claude Code Templates

An open catalog of components for Claude Code, installable with one command.

npm version npm downloads GitHub stars MIT license

Browse the catalog  ·  Documentation  ·  Contributing  ·  Discussions  ·  Changelog

SPONSORED BY

Swiftproxy

Swiftproxy proudly supports this project.
Connect your AI-powered workflows to reliable residential proxies for web data collection, browser automation, and AI-driven research.
90M+ residential IPs across 220+ locations, rotating and static residential proxies, with HTTP(S) and SOCKS5 support.

Get 10% off with code PROXY90

The aitmpl.com component catalog

About

Claude Code is configured through small files: skills, subagents, slash commands, hooks, MCP servers and settings. Claude Code Templates collects more than 1,980 of them in one catalog at aitmpl.com, where you can search, preview every file a component writes, and combine several components into a single install command. The CLI writes each file to the right place and merges existing configuration instead of overwriting it.

Every pull request is checked by Claude Code's plugin validator and scanned by NVIDIA SkillSpector.

Quickstart

Runs with npx, no global install needed.

# Browse the catalog and install interactively
npx claude-code-templates@latest

# Install one component
npx claude-code-templates@latest --skill creative-design/frontend-design

# Install a stack in one command
npx claude-code-templates@latest \
  --agent development-team/frontend-developer \
  --command testing/generate-tests \
  --mcp integration/github-integration

Add --yes to skip the confirmation prompt. Every component page on aitmpl.com shows its exact install command. To find one from the terminal: npx claude-code-templates@latest --search "code review".

One example per component type
npx claude-code-templates@latest --skill creative-design/frontend-design
npx claude-code-templates@latest --agent development-tools/code-reviewer
npx claude-code-templates@latest --command performance/optimize-bundle-size
npx claude-code-templates@latest --mcp database/postgresql-integration
npx claude-code-templates@latest --setting mcp/mcp-timeouts
npx claude-code-templates@latest --hook git/conventional-commits
npx claude-code-templates@latest --mod security/secret-redactor      # Claude Code 2.1.287+
npx claude-code-templates@latest --loop engineering/docs-sweep-loop  # also installs the components the loop uses
npx claude-code-templates@latest --plugin productivity/champion-kit  # via the aitmpl marketplace, Claude Code 2.1.288+

What's in the catalog

Type Count What it is Examples
Skills 918 Reusable capabilities with progressive disclosure PDF processing, frontend design, code review
Agents 422 Subagents specialized in one domain Security auditor, frontend developer, database architect
Commands 288 Custom slash commands /generate-tests, /optimize-bundle-size, /security-audit
MCPs 119 External service integrations GitHub, PostgreSQL, Stripe, Supabase, Sentry
Settings 80 Claude Code configuration Timeouts, permissions, status lines
Hooks 63 Automation triggers Conventional commits, blocking direct pushes
Mods 50 Plugins that change Claude Code's own interface and behavior Secret redaction, protected paths, terminal games
Loops 18 Autonomous workflows with a goal, an interval and a stop condition Docs sweep, build-test-fix, adversarial review
Templates 14 Complete project configurations Language and framework setups
Sandboxes 11 Launchers that run Claude Code in an isolated environment (reference only, see cli-tool/components/sandbox/) E2B, Cloudflare, Docker
Plugins 1 Whole Claude Code plugins, installed from the aitmpl marketplace Champion Kit

Live counts: dashboard/public/counts.json.

Local tools

The CLI also ships three local tools. The two dashboards listen on 127.0.0.1 only, because they serve your conversation history.

Command What it does
npx claude-code-templates@latest --analytics Real-time session monitoring and usage metrics at localhost:3333
npx claude-code-templates@latest --chats Read and search your conversations in a mobile-friendly UI at localhost:9876
npx claude-code-templates@latest --health-check Diagnose your Claude Code installation and project setup

To open the conversation browser from another device, forward the port over SSH: ssh -L 9876:localhost:9876 <host>.

Flags removed in 1.31.0

--plugins, --skills-manager, --command-stats, --hook-stats, --mcp-stats, --agents, --chats-mobile, --teams, --2025, --studio, --sandbox, --tunnel, --create-agent, --list-agents, --update-agent, --remove-agent and --clone-session were removed. Running one prints what replaced it. To see what is installed in each scope, use the stack viewer mod (--mod ui/stack-viewer, then /stack in Claude Code). Details in the CHANGELOG.

Documentation

Guides, the CLI reference and the catalog API live at docs.aitmpl.com.

Contributing

Contributions are welcome. Read the contributing guide to add a skill, agent, command, MCP, setting, hook or mod, and the Code of Conduct before you open a pull request.

Sponsors and programs

Sponsors

Z.AI   Bright Data

Open source programs

Claude for Open Source    Vercel OSS Program    Neon Open Source Program

davila7%2Fclaude-code-templates | Trendshift

Support the project

Sponsor on GitHub   Buy me a coffee

Everyone who supports the project is listed at aitmpl.com/supporters.

Attribution

The catalog includes components from these sources. Each keeps its original license and attribution.

Source License Contributes
K-Dense-AI/claude-scientific-skills (K-Dense Inc.) MIT 139 scientific skills for biology, chemistry, medicine and computational research
anthropics/skills See repo 21 official Anthropic skills
anthropics/claude-code See repo 10 skills from development guides and examples
obra/superpowers (Jesse Obra) MIT 14 workflow skills
alirezarezvani/claude-skills (Alireza Rezvani) MIT 36 professional role skills
wshobson/agents MIT 48 agents
hesreallyhim/awesome-claude-code CC0 1.0 21 commands
mehdi-lamrani/awesome-claude-skills Apache 2.0 Community skills
NerdyChefsAI Skills MIT Specialized enterprise skills
move-code-quality-skill MIT
cocoindex-claude Apache 2.0

Star history

Stargazers over time

License

MIT

Questions

What is davila7/claude-code-templates?

Open-source registry and CLI for Claude Code components: agents, commands, skills, hooks, MCPs, settings and mods

How do I install claude-code-templates?

Run "npx skills add davila7/claude-code-templates" and choose the skills you want. Many packs also document their own install path (for example a Claude Code plugin marketplace) in the README below.

How many skills are in claude-code-templates?

926 SKILL.md skills. Alyn lists 40 of them with their own pages.