Files
Obsidian/Claude/If You're Not Using These 100 Repos, Delete CLAUDE CODE - a large collection of repositories.md
2026-07-21 14:53:24 +08:00

1100 lines
33 KiB
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
title: "If You're Not Using These 100 Repos, Delete CLAUDE CODE - a large collection of repositories"
source: "https://x.com/0x_kaize/status/2048059417661174052"
author:
- "[[@0x_kaize]]"
published: 2026-04-25
created: 2026-04-26
description: "Most people think of Claude Code as \"just another AI coding tool.\"I thought the same - until I discovered configs, plugins, skills, and suba..."
tags:
- "clippings"
---
![图像](https://pbs.twimg.com/media/HGwq4IVbYAAzA3r?format=jpg&name=large)
Most people think of Claude Code as "just another AI coding tool."
I thought the same - until I discovered configs, plugins, skills, and subagents.
Before that, I was writing the same prompts over and over. Losing context every session. Wondering why other devs were 5x more productive with the same tool.
So I decided to figure out how to work better. The answer: REPOSITORIES.
I put together a collection of the 100 best repositories:
## CATEGORY 1 - AWESOME LISTS & META-INDEXES
![图像](https://pbs.twimg.com/media/HGhPaZ7XEAAHpD8?format=png&name=large)
awesome-claude-code
The Claude Code ecosystem is evolving so rapidly that it’s hard to keep up. New features appear every day, plugins come and go, and half of all the interesting stuff never even makes it to Hacker News.
Awesome lists help solve this problem. These are community-maintained directories that take on the work of searching: they classify, rank, and filter content based on actual quality, not the number of stars on GitHub.
**1/ awesome-claude-code**
The definitive curated list of the entire Claude Code ecosystem
- 28.5k+ stars, the main index
- only Claude itself is allowed to submit PRs
- skills, hooks, commands, orchestrators, plugins
repo: [https://github.com/hesreallyhim/awesome-claude-code](https://github.com/hesreallyhim/awesome-claude-code)
**2/ awesome-claude-skills (ComposioHQ)**
50+ production-ready Claude skills for automation
- PostgreSQL, deep research, CSV, root-cause tracing
- cross-compatible with Claude Code, Codex, Cursor, Gemini CLI
- install via /skill add
repo: [https://github.com/ComposioHQ/awesome-claude-skills](https://github.com/ComposioHQ/awesome-claude-skills)
**3/ awesome-claude-plugins (ComposioHQ)**
Curated plugin collection for Claude Code
- commands, agents, hooks and MCP servers
- includes connect-apps, frontend-design, artifacts-builder
- install via /plugin marketplace add
repo: [https://github.com/ComposioHQ/awesome-claude-plugins](https://github.com/ComposioHQ/awesome-claude-plugins)
**4/ awesome-claude-prompts**
4.2k+ star collection of optimized Claude prompts
- XML-structured prompt techniques
- business, creative, dev workflows
- copy-paste ready
repo: [https://github.com/langgptai/awesome-claude-prompts](https://github.com/langgptai/awesome-claude-prompts)
**5/ awesome-claude**
All-around list of everything Anthropic Claude-related
- courses, guides, desktop apps, articles
- covers MCP, BMAD method, Claude Code tips
- good starting point for newcomers
repo: [https://github.com/alvinunreal/awesome-claude](https://github.com/alvinunreal/awesome-claude)
**6/ awesome-agent-skills (VoltAgent)**
1000+ agent skills from real engineering teams
- not AI-generated slop, battle-tested
- works with Claude Code, Codex, Gemini CLI, Cursor
- Notion, WhatsApp, NotebookLM, memory included
repo: [https://github.com/VoltAgent/awesome-agent-skills](https://github.com/VoltAgent/awesome-agent-skills)
**7/ awesome-claude-code-subagents (VoltAgent)**
Hand-picked subagents for every stack and task
- domain-specific expertise bundles
- production-ready components
- integrates with most coding agents
repo: [https://github.com/VoltAgent/awesome-claude-code-subagents](https://github.com/VoltAgent/awesome-claude-code-subagents)
**8/ awesome-claude-code-plugins (ccplugins)**
Focused list of Claude Code plugins only
- slash commands, subagents, MCP servers, hooks
- install commands included for each
- enables hosting your own marketplace
repo: [https://github.com/ccplugins/awesome-claude-code-plugins](https://github.com/ccplugins/awesome-claude-code-plugins)
**9/ awesome-claude-code (jqueryscript)**
Curated tools, IDE integrations and frameworks
- star-tier markers
- SDKs, security tools, agent collections
- great discovery tool
repo: [https://github.com/jqueryscript/awesome-claude-code](https://github.com/jqueryscript/awesome-claude-code)
**10/ Claude-Code-Repos-Index**
Indexed catalogue of 75+ quality Claude Code repos
- all original, no AI slop
- maintained by Daniel Rosehill
- great navigator for the ecosystem
repo: [https://github.com/danielrosehill/Claude-Code-Repos-Index](https://github.com/danielrosehill/Claude-Code-Repos-Index)
## CATEGORY 2 - OFFICIAL ANTHROPIC REPOS
![图像](https://pbs.twimg.com/media/HGhP9fRW0AAs-1z?format=jpg&name=large)
Before you start working with any community repository, begin with these.
These are Anthropic’s official projects - the command-line interface (CLI) itself, the SDKs, the skills library, and the GitHub Action. Everything else on this list is built on top of them.
They may not always offer the widest range of features, but they are the most stable, best-documented, and most reliable choice for teams.
**11/ anthropics/claude-code**
The official Claude Code terminal tool
- 55k+ stars
- natural language commands for your codebase
- maintained by Anthropic
repo: [https://github.com/anthropics/claude-code](https://github.com/anthropics/claude-code)
**12/ anthropics/skills**
Official public repository of Agent Skills
- 37.5k+ stars
- PDF, DOCX, XLSX, PPTX + art generation
- the canonical skills reference
repo: [https://github.com/anthropics/skills](https://github.com/anthropics/skills)
**13/ anthropics/claude-plugins**
Anthropic-managed directory of quality plugins
- 2.8k+ stars
- vetted official plugin collection
- good baseline for teams
repo: [https://github.com/anthropics/claude-plugins](https://github.com/anthropics/claude-plugins)
**14/ anthropics/claude-code-sdk-python**
Official Python SDK for Claude Code
- 6.1k+ stars
- programmatic access to capabilities
- supports Agent SDK patterns
repo: [https://github.com/anthropics/claude-code-sdk-python](https://github.com/anthropics/claude-code-sdk-python)
**15/ anthropics/claude-agent-sdk-typescript**
Official TypeScript SDK for Claude Agent
- type-safe tool orchestration
- streaming + MCP support
- V2 preview with send()/stream()
repo: [https://github.com/anthropics/claude-agent-sdk-typescript](https://github.com/anthropics/claude-agent-sdk-typescript)
**16/ anthropics/claude-code-security-review**
AI-powered security review GitHub Action
- 2.8k+ stars
- analyzes PR diffs for vulnerabilities
- drop-in CI/CD integration
repo: [https://github.com/anthropics/claude-code-security-review](https://github.com/anthropics/claude-code-security-review)
**17/ anthropics/claude-code-action**
Official GitHub Action for Claude in PRs
- [@claude](https://x.com/@claude) mentions trigger analysis
- diff reviews + patch suggestions
- follows your repo conventions
repo: [https://github.com/anthropics/claude-code-action](https://github.com/anthropics/claude-code-action)
**18/ github/github-mcp-server**
Official GitHub MCP server
- direct access to repos, PRs, issues, CI/CD
- read-only mode via X-MCP-Readonly
- the most-used server in the ecosystem
repo: [https://github.com/github/github-mcp-server](https://github.com/github/github-mcp-server)
**19/ anthropic-cookbook**
Official Anthropic cookbook with recipes
- notebooks, agents, tool-use patterns
- RAG, classification, summarization
- maintained by Anthropic team
repo: [https://github.com/anthropics/anthropic-cookbook](https://github.com/anthropics/anthropic-cookbook)
**20/ courses (Anthropic)**
Free Anthropic courses
- prompt engineering fundamentals
- API usage, agents, AI Fluency
- direct from the source
repo: [https://github.com/anthropics/courses](https://github.com/anthropics/courses)
## CATEGORY 3 - SKILLS COLLECTIONS
Skills are the fastest way to expand Claude Code’s capabilities. They aren’t plugins or agents, just Markdown files that teach Claude how to perform specific tasks, from writing proper pull requests to creating videos in Remotion and conducting security audits.
The beauty of it is that good skills let you transform Claude from a general-purpose assistant into an expert in a specific field on demand. You don’t need to explain your tech stack from scratch every time you run it the skill already knows it.
**21/ obra/superpowers**
The most popular skills library for Claude Code
- 148k+ stars
- brainstorm → spec → plan → TDD → review → merge
- subagent orchestration
repo: [https://github.com/obra/superpowers](https://github.com/obra/superpowers)
**22/ obra/superpowers-marketplace**
Official marketplace for the Superpowers ecosystem
- 20+ battle-tested skills
- /brainstorm, /write-plan, /execute-plan
- SessionStart context injection
repo: [https://github.com/obra/superpowers-marketplace](https://github.com/obra/superpowers-marketplace)
**23/ obra/superpowers-skills**
Community-editable skills for Superpowers
- auto-cloned to ~/.config/superpowers/skills/
- fork and submit PRs
- the collaborative side
repo: [https://github.com/obra/superpowers-skills](https://github.com/obra/superpowers-skills)
**24/ obra/superpowers-lab**
Experimental skills under active development
- semantic duplicate-function detection
- bleeding-edge techniques
- evolves with real usage
repo: [https://github.com/obra/superpowers-lab](https://github.com/obra/superpowers-lab)
**25/ everything-claude-code**
Hackathon-winning harness built from 10+ months of use
- 30 agents, 136 skills, 60 slash commands
- 1282 tests, 98% coverage
- Cerebral Valley x Anthropic winner
repo: [https://github.com/affaan-m/everything-claude-code](https://github.com/affaan-m/everything-claude-code)
**26/ travisvn/awesome-claude-skills**
Community "best-of" skill collection
- 22k+ installs
- SEO, marketing, design, security, research
- safety warnings on untrusted skills
repo: [https://github.com/travisvn/awesome-claude-skills](https://github.com/travisvn/awesome-claude-skills)
**27/ trailofbits/claude-code-skills**
Security research and audit skills
- by Trail of Bits security firm
- vulnerability detection workflows
- built for real security engineering
repo: [https://github.com/trailofbits/claude-code-skills](https://github.com/trailofbits/claude-code-skills)
**28/ K-Dense-AI/claude-scientific-skills**
Skills for scientific computing
- specialized libraries for research
- academic and lab workflows
- data analysis ready
repo: [https://github.com/K-Dense-AI/claude-scientific-skills](https://github.com/K-Dense-AI/claude-scientific-skills)
**29/ ay-automate/ay-skills**
10 production-tested skills
- SEO audits, headless browser automation
- Remotion video generation, diagrams
- drop-in ready
repo: [https://github.com/ay-automate/ay-skills](https://github.com/ay-automate/ay-skills)
**30/ BehiSecc/awesome-claude-skills**
A "list of lists" for deeper Claude use
- knowledge acquisition, deeper thinking
- skill automation utilities
- meta-resource for curators
repo: [https://github.com/BehiSecc/awesome-claude-skills](https://github.com/BehiSecc/awesome-claude-skills)
## CATEGORY 4 - AGENTS & SUBAGENTS
A single session with Claude can’t handle everything at a high level. It gets overloaded, context gets cluttered with half-read files and outdated debug data and by the time you ask for a code review, it’s already forgotten what you were building.
Subagents solve this problem. Instead of a single Claude that struggles with twenty tasks, you get a team of specialists: each with its own context and a single task.
**31/ wshobson/agents**
Massive collection of production subagents
- 25k+ stars
- strategy, dev, security, design, data, research
- drop-in for Claude Code workflows
repo: [https://github.com/wshobson/agents](https://github.com/wshobson/agents)
**32/ awesome-claude-agents**
Team of specialized AI agents that work together
- 3.7k+ stars
- agents collaborate on full features
- expert-level knowledge across stacks
repo: [https://github.com/vijaythecoder/awesome-claude-agents](https://github.com/vijaythecoder/awesome-claude-agents)
**33/ davepoon/claude-code-subagents-collection**
100+ production-ready subagents
- 2.2k+ stars
- comprehensive domain expertise
- drop-in for any workflow
repo: [https://github.com/davepoon/claude-code-subagents-collection](https://github.com/davepoon/claude-code-subagents-collection)
**34/ claude-code-agents (59 specialists)**
59 specialized AI agents for development
- TypeScript, Python, Java, Kotlin reviewers
- workflow automation agents
- great for onboarding teams
repo: [https://github.com/baryhuang/claude-code-agents](https://github.com/baryhuang/claude-code-agents)
**35/ multi-agent-squad**
Production-ready multi-agent orchestration
- 74+ stars
- task routing + consensus decisions
- works across coding agents
repo: [https://github.com/ruvnet/multi-agent-squad](https://github.com/ruvnet/multi-agent-squad)
**36/ Agent-Fusion**
Multi-agent orchestration across AI tools
- Claude Code, Codex CLI, Amazon Q, Gemini
- bidirectional collaboration
- intelligent task routing
repo: [https://github.com/0xAsten/Agent-Fusion](https://github.com/0xAsten/Agent-Fusion)
**37/ sub-agents**
Manager for Claude Code sub agents
- adds hooks and custom slash commands
- 175+ stars
- lightweight setup
repo: [https://github.com/webdevtodayjason/sub-agents](https://github.com/webdevtodayjason/sub-agents)
**38/ sub-agents-directory**
Curated 100+ subagent prompts
- 74+ stars
- MCP servers included
- community-maintained index
repo: [https://github.com/dotneet/sub-agents-directory](https://github.com/dotneet/sub-agents-directory)
**39/ claude-code-heavy**
Multi-agent research orchestration
- 72+ stars
- parallel research agents
- built specifically for Claude Code
repo: [https://github.com/iamcatdev/claude-code-heavy](https://github.com/iamcatdev/claude-code-heavy)
**40/ ClaudeCodeAgents**
QA-focused agent collection
- 455+ stars
- testing agents, validators
- drop-in QA workflow
repo: [https://github.com/webdevtodayjason/ClaudeCodeAgents](https://github.com/webdevtodayjason/ClaudeCodeAgents)
## CATEGORY 5 - MCP SERVERS
On its own, Claude Code runs in your terminal: it reads files, executes commands, and interacts with APIs. That’s it. It can’t work with your GitHub pull requests, query data from Postgres, open a browser, or read Figma frames.
MCP servers solve this problem. They act as bridges connecting Claude to the rest of your stack via a standardized protocol, transforming the smart “programmer partner” into a true autonomous project participant.
**41/ claude-code-mcp**
Run Claude Code itself as an MCP server
- enables agent-in-agent pattern
- recursive delegation of coding tasks
- integrates with Claude Desktop
repo: [https://github.com/steipete/claude-code-mcp](https://github.com/steipete/claude-code-mcp)
**42/ zilliztech/claude-context**
Semantic code search MCP for massive codebases
- pulls the right files without manual breadcrumbing
- critical for big repos
- community MCP server
repo: [https://github.com/zilliztech/claude-context](https://github.com/zilliztech/claude-context)
**43/ claude-context-mode**
MCP server between Claude Code and outputs
- 2.2k+ stars
- 315 KB → 5.4 KB (98% reduction)
- token savings on every call
repo: [https://github.com/d-e-s-o/claude-context-mode](https://github.com/d-e-s-o/claude-context-mode)
**44/ Continuous-Claude-v2**
Context management for Claude Code
- 2.2k+ stars
- ledger-based hooks maintain state
- MCP execution without context pollution
repo: [https://github.com/continuous-claude/continuous-claude-v2](https://github.com/continuous-claude/continuous-claude-v2)
**45/ context7**
Up-to-date version-specific docs in prompts
- real-time doc access
- libraries + frameworks
- works with Cursor, VS Code, Claude Code, Windsurf
repo: [https://github.com/upstash/context7](https://github.com/upstash/context7)
**46/ postgres-mcp**
Safe PostgreSQL MCP server
- read-only default mode
- multi-connection support
- defense-in-depth security
repo: [https://github.com/crystaldba/postgres-mcp](https://github.com/crystaldba/postgres-mcp)
**47/ playwright-mcp**
Browser automation via MCP
- navigate pages, fill forms
- dynamic content scraping
- official Microsoft-backed
repo: [https://github.com/microsoft/playwright-mcp](https://github.com/microsoft/playwright-mcp)
**48/ mcp-server-sqlite**
Lightweight SQLite MCP for prototyping
- local development friendly
- simple install
- official MCP team
repo: [https://github.com/modelcontextprotocol/servers](https://github.com/modelcontextprotocol/servers)
**49/ claude-code-mcp-enhanced**
Enhanced claude-code-mcp with detailed instructions
- emphatic prompts for compliance
- improved task-following
- by grahama1970
repo: [https://github.com/grahama1970/claude-code-mcp-enhanced](https://github.com/grahama1970/claude-code-mcp-enhanced)
**50/ danielrosehill/Claude-Code-MCP-List**
Short curated MCP collection
- MCPs for Linux desktop Claude Code
- battle-tested selections
- practical daily use
repo: [https://github.com/danielrosehill/Claude-Code-MCP-List](https://github.com/danielrosehill/Claude-Code-MCP-List)
## CATEGORY 6 - ORCHESTRATION & WORKFLOWS
Once you’ve mastered Claude Code, the next hurdle will be yourself. You can only monitor one session at a time, approve only one plan, and run only one agent. Orchestration tools allow you to overcome this limitation.
These repositories let you run parallel Claude sessions, coordinate multi-step workflows, preserve state between runs, and manage agents just as you would manage a small team of developers.
**51/ Claude-Flow**
Enterprise-grade AI orchestration platform
- 11.4k+ stars
- multi-agent orchestration with persistent memory
- reshapes how teams build with AI
repo: [https://github.com/ruvnet/claude-flow](https://github.com/ruvnet/claude-flow)
**52/ claude-squad**
Terminal multiplexer for AI coding agents
- 5.6k+ stars
- manages Claude Code, Aider, Codex, OpenCode, Amp
- parallel agents without chaos
repo: [https://github.com/smtg-ai/claude-squad](https://github.com/smtg-ai/claude-squad)
**53/ claude\_code\_agent\_farm**
Parallel Claude Code sessions orchestrator
- runs multiple cc agents at scale
- systematic codebase improvement
- automation-first design
repo: [https://github.com/Dicklesworthstone/claude\_code\_agent\_farm](https://github.com/Dicklesworthstone/claude_code_agent_farm)
**54/ ccpm (Claude Code PM)**
Project-management workflow for Claude Code
- by Ran Aroussi
- specialized agents + slash commands
- turnkey setup
repo: [https://github.com/automazeio/ccpm](https://github.com/automazeio/ccpm)
**55/ cc-sessions**
Opinionated extension set for Claude Code
- 1.5k+ stars
- hooks, subagents, commands
- task/git management infrastructure
repo: [https://github.com/cc-sessions/cc-sessions](https://github.com/cc-sessions/cc-sessions)
**56/ claude-sessions**
Custom slash commands for session tracking
- 1.1k+ stars
- comprehensive documentation
- dev session logging
repo: [https://github.com/iannuttall/claude-sessions](https://github.com/iannuttall/claude-sessions)
**57/ claude-code-infrastructure-showcase**
Infrastructure approach to Skills
- hooks that activate skills contextually
- smart skill routing
- adaptable to any project
repo: [https://github.com/diet103/claude-code-infrastructure-showcase](https://github.com/diet103/claude-code-infrastructure-showcase)
**58/ infinite-agentic-loop**
Infinite agentic loop demonstration
- 492+ stars
- two-prompt system design
- experimental but educational
repo: [https://github.com/disler/infinite-agentic-loop](https://github.com/disler/infinite-agentic-loop)
**59/ agentsys**
Automation harness for multiple tools
- 473+ stars
- 14 plugins, 43 agents, 30 skills
- Claude Code + OpenCode + Codex
repo: [https://github.com/agentsys/agentsys](https://github.com/agentsys/agentsys)
**60/ Citadel**
Agent orchestration harness
- 430+ stars
- parallel agent coordination
- session memory persistence
repo: [https://github.com/gabrieltonnellier/citadel](https://github.com/gabrieltonnellier/citadel)
## CATEGORY 7 - MEMORY & CONTEXT
Claude Code’s biggest drawback is also the one that’s easiest to fix: every session starts from scratch. Yesterday’s solutions, last week’s architecture discussions, the reasons you chose Postgres over MongoDB - all of that disappears the moment you close the terminal.
Memory and context stores help solve this problem. They provide Claude with a persistent state across sessions - semantic memory, a condensed history, knowledge graphs of your codebase, as well as background agents that quietly accumulate knowledge while you work.
**61/ thedotmack/claude-mem**
Long-term memory via compression
- persists context between sessions
- lightweight and composable
- solves the #1 Claude Code complaint
repo: [https://github.com/thedotmack/claude-mem](https://github.com/thedotmack/claude-mem)
**62/ hanfang/claude-memory-skill**
Minimal hierarchical memory system
- background agents + filesystem persistence
- low-friction setup
- works alongside existing skills
repo: [https://github.com/hanfang/claude-memory-skill](https://github.com/hanfang/claude-memory-skill)
**63/ 0xfurai/claude-subconscious**
Background agent whispering guidance
- 2.4k+ stars
- watches sessions, reads files
- builds memory over time
repo: [https://github.com/0xfurai/claude-subconscious](https://github.com/0xfurai/claude-subconscious)
**64/ claude-code-semantic-memory**
Persistent semantic memory for Claude Code
- 70+ stars
- vector-based recall
- session continuity
repo: [https://github.com/dheerajoruganty/claude-code-semantic-memory](https://github.com/dheerajoruganty/claude-code-semantic-memory)
**65/ claude-user-memory**
User memory system with 12 specialist agents
- 125+ stars
- intelligent orchestration
- auto-selects right specialist
repo: [https://github.com/brennercruvinel/claude-user-memory](https://github.com/brennercruvinel/claude-user-memory)
**66/ Repomix**
Pack your codebase into one AI-readable file
- 20.9k+ stars
- XML, Markdown, plain text output
- essential for large-repo context
repo: [https://github.com/yamadashy/repomix](https://github.com/yamadashy/repomix)
**67/ graphify**
Interactive knowledge graph from codebases
- explore, search, ask questions
- works with Claude Code, Codex, Cursor
- great for onboarding
repo: [https://github.com/safishamsi/graphify](https://github.com/safishamsi/graphify)
**68/ context-prime**
Systematic project context priming
- by elizaOS
- scenario-specific priming commands
- CLAUDE.md enhancement
repo: [https://github.com/elizaOS/context-prime](https://github.com/elizaOS/context-prime)
**69/ claude-code-heavy-research**
Multi-agent research with parallel context
- 72+ stars
- deep-dive research workflows
- agent-based knowledge gathering
repo: [https://github.com/iamcatdev/claude-code-heavy](https://github.com/iamcatdev/claude-code-heavy)
**70/ ledger**
Context-preserving ledger system
- hooks maintain ledger state
- handoffs between agents
- MCP without pollution
repo: [https://github.com/continuous-claude/continuous-claude-v2](https://github.com/continuous-claude/continuous-claude-v2)
## CATEGORY 8 - SLASH COMMANDS & HOOKS
Every time you catch yourself typing the same instructions for Claude for the third time, you’ll come across a slash command that’s just begging to be used. /fix-issue 456, /review, /tdd - a single keystroke instead of a whole paragraph, every single time.
Hooks go even further. They trigger automatically at key moments in your workflow, blocking commits without tests, automatically formatting code before a push, adding context when starting a session. You no longer need to remind Claude of your rules, because the rules are enforced automatically.
**71/ wshobson/commands**
57 production-ready slash commands
- 1.7k+ stars
- 15 workflows + 42 tools
- multi-agent orchestration
repo: [https://github.com/wshobson/commands](https://github.com/wshobson/commands)
**72/ nizos/tdd-guard**
Automated TDD enforcement for Claude Code
- 1.7k+ stars
- blocks skipping tests
- explains why it blocked
repo: [https://github.com/nizos/tdd-guard](https://github.com/nizos/tdd-guard)
**73/ ccundo**
Granular undo for Claude Code
- 1.3k+ stars
- seamless integration
- action-level rollback
repo: [https://github.com/RonitSachdev/ccundo](https://github.com/RonitSachdev/ccundo)
**74/ claude-canvas**
TUI toolkit giving Claude Code its own display
- 1.1k+ stars
- interactive terminal UI
- rich visualization
repo: [https://github.com/claude-canvas/claude-canvas](https://github.com/claude-canvas/claude-canvas)
**75/ ClaudoPro Directory**
Wide selection of hooks, commands, subagents
- better than average template sites
- specialized task coverage
- curated by ghost
repo: [https://github.com/ClaudoPro/claudopro-directory](https://github.com/ClaudoPro/claudopro-directory)
**76/ danielrosehill/Claude-Slash-Commands**
Curated custom slash commands
- organized by category
- pre-push hook for sync
- index-based discovery
repo: [https://github.com/danielrosehill/Claude-Slash-Commands](https://github.com/danielrosehill/Claude-Slash-Commands)
**77/ claude-commands/command-fix-issue**
TDD-based GitHub issue fixer
- /fix-issue 456
- Red → Green → Refactor
- creates PR automatically
repo: [https://github.com/claude-commands/command-fix-issue](https://github.com/claude-commands/command-fix-issue)
**78/ Design Review Workflow**
Automated UI/UX design review
- by Patrick Ellis
- responsive + accessibility checks
- specialized subagents
repo: [https://github.com/patrick-ellis/design-review-workflow](https://github.com/patrick-ellis/design-review-workflow)
**79/ tdd-implement**
TDD slash command by jerseycheese
- Red/Green/Refactor automation
- test-first enforcement
- feature-to-test breakdown
repo: [https://github.com/jerseycheese/tdd-implement](https://github.com/jerseycheese/tdd-implement)
**80/ security-review**
Official security review slash command
- scans PRs for issues
- suggests fixes
- easy to disable
repo: [https://github.com/anthropics/claude-code-security-review](https://github.com/anthropics/claude-code-security-review)
## CATEGORY 9 - GUIDES & LEARNING
Claude Code has its own complexities that nobody talks about. The command line is simple—but what about developing prompts, creating skills, configuring MCP, designing hooks, managing context, and token economics?
It is at this stage that most developers get stuck and start blaming the tool.
Guides and training materials help overcome this barrier. Detailed reference guides, hint development guides, system hint archives, pattern encyclopedias - all of which would take months to learn on your own.
**81/ ThamJiaHe/claude-prompt-engineering-guide**
Definitive prompt engineering guide
- covers Opus 4.6, Sonnet 4.6, Haiku 4.5
- Skills, Plugins, MCP, Hooks, Ultrathink
- 220+ verified sources
repo: [https://github.com/ThamJiaHe/claude-prompt-engineering-guide](https://github.com/ThamJiaHe/claude-prompt-engineering-guide)
**82/ nikiforovall/claude-code-handbook**
Best practices for Claude Code workflows
- distributable plugins included
- daily-use patterns
- battle-tested tips
repo: [https://github.com/nikiforovall/claude-code-handbook](https://github.com/nikiforovall/claude-code-handbook)
**83/ FlorianBruniaux/claude-code-ultimate-guide**
Massive 22,000+ line documentation project
- 225 production templates
- 9 AI personas + 26 slash commands
- 271 quiz questions
repo: [https://github.com/FlorianBruniaux/claude-code-ultimate-guide](https://github.com/FlorianBruniaux/claude-code-ultimate-guide)
**84/ Piebald-AI/claude-code-system-prompts**
All Claude Code system prompts
- updated within minutes of each release
- tool descriptions + sub-agent prompts
- CHANGELOG across 155+ versions
repo: [https://github.com/Piebald-AI/claude-code-system-prompts](https://github.com/Piebald-AI/claude-code-system-prompts)
**85/ Encyclopedia of Agentic Coding Patterns**
190+ patterns for AI-assisted development
- by Wolf McNally
- foundational → agentic construction
- governance + testing
repo: [https://github.com/wolfmcnally/Encyclopedia-of-Agentic-Coding-Patterns](https://github.com/wolfmcnally/Encyclopedia-of-Agentic-Coding-Patterns)
**86/ RiyaParikh0112/claude-code-playbook**
Claude Code playbook with TDD workflows
- integration test patterns
- CI/CD pipeline configs
- PR prep guides
repo: [https://github.com/RiyaParikh0112/claude-code-playbook](https://github.com/RiyaParikh0112/claude-code-playbook)
**87/ 40+ Claude Code Tips**
Power-user tips collection
- custom status line scripts
- system prompt halving tricks
- Claude Code in containers
repo: [https://github.com/iannuttall/claude-code-tips](https://github.com/iannuttall/claude-code-tips)
**88/ awesome-claude-prompts topic**
Topic-based discovery of prompt repos
- community-submitted repos
- tagged for navigation
- fresh additions regularly
repo: [https://github.com/topics/awesome-claude-prompts](https://github.com/topics/awesome-claude-prompts)
**89/ Context Priming by disler**
Systematic context priming approach
- scenario-specific commands
- project context patterns
- reference templates
repo: [https://github.com/disler/context-priming](https://github.com/disler/context-priming)
**90/ My Experience With Claude Code (2 weeks)**
Real-world lessons and workflows
- TODO.md discipline
- cost management tips
- refactor strategies
repo: [https://github.com/shaharia-lab/my-claude-code-journey](https://github.com/shaharia-lab/my-claude-code-journey)
## CATEGORY 10 - IDE INTEGRATIONS & DESKTOP
By default, Claude Code runs in the terminal which is convenient if you’re always working in the terminal, but not so much if you’re not.
Most developers want Claude to work directly within the editor they’re already using, rather than in a separate window that distracts them.
Integration with an IDE solves this problem. Extensions for VS Code, plugins for Neovim, modes for Emacs, and even desktop shells integrate Claude into any of your existing workflows.
**91/ coder/claudecode.nvim**
First Neovim IDE integration for Claude Code
- pure Lua, zero dependencies
- WebSocket-based MCP protocol
- reverse-engineered from official extensions
repo: [https://github.com/coder/claudecode.nvim](https://github.com/coder/claudecode.nvim)
**92/ greggh/claude-code.nvim**
Seamless Neovim + Claude Code integration
- toggle terminal window
- \--continue + custom variants
- auto-reload modified files
repo: [https://github.com/greggh/claude-code.nvim](https://github.com/greggh/claude-code.nvim)
**93/ manzaltu/claude-code-ide.el**
Emacs integration for Claude Code
- ediff-based suggestions
- LSP/flymake/flycheck diagnostics
- tree-sitter AST queries
repo: [https://github.com/manzaltu/claude-code-ide.el](https://github.com/manzaltu/claude-code-ide.el)
**94/ stevemolitor/claude-code.el**
Emacs interface for Claude Code CLI
- simple terminal wrapper
- lightweight integration
- idiomatic Emacs
repo: [https://github.com/stevemolitor/claude-code.el](https://github.com/stevemolitor/claude-code.el)
**95/ Haleclipse/Claudix**
VSCode extension for Claude Code
- interactive chat interface
- session management
- Vue 3 + TypeScript
repo: [https://github.com/Haleclipse/Claudix](https://github.com/Haleclipse/Claudix)
**96/ Clawd on Desk**
Desktop pet reacting to Claude sessions
- thinking, typing, juggling, sleeping
- real-time session awareness
- pure fun, zero productivity
repo: [https://github.com/Ruller-Lulu/clawd-on-desk](https://github.com/Ruller-Lulu/clawd-on-desk)
**97/ Claude Desktop Debian**
Unofficial Claude desktop app for Linux
- Debian-native package
- community-maintained
- fills the Linux gap
repo: [https://github.com/aaddrick/claude-desktop-debian](https://github.com/aaddrick/claude-desktop-debian)
**98/ instructkr/claw-code**
Korean-built Claude Code alternative/tooling
- localized workflows
- lightweight install
- community project
repo: [https://github.com/instructkr/claw-code](https://github.com/instructkr/claw-code)
## CATEGORY 11 - SPECIALIZED WORKFLOWS
Not all Claude Code repositories can be clearly classified into a specific category. Some are designed to perform a single, specific task. For example, UI/UX tools focused exclusively on design patterns, a real-time directory that tracks the entire ecosystem, or niche tools that excel at solving just one particular problem.
**99/ nextlevelbuilder/ui-ux-pro-max-skill**
UI/UX skill for design-focused workflows
- structured design patterns
- component-oriented guidance
- production-grade output
repo: [https://github.com/nextlevelbuilder/ui-ux-pro-max-skill](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill)
**100/ ClaudeWave**
Real-time directory of 3800+ Claude repos
- 8 categories, tagged use-cases
- ranked by stars + velocity
- updated every 12 hours
repo: [https://github.com/claudewave/claudewave](https://github.com/claudewave/claudewave)
This isn’t the full picture, no one has the full picture. The Claude Code ecosystem is evolving too quickly for anyone to keep up with everything. But if you install just 5–10 of the repositories listed above, you’ll already be ahead of 95% of the users who pay for the same Claude subscription as you. More AI deep-dives and ecosystem breakdowns I post in my Telegram: [https://t.me/+LorUR\_GakbViOTQy](https://t.me/+LorUR_GakbViOTQy)