By loulanyue
Enhance Claude Code with a curated collection of agents, skills, hooks, and rules for automated testing, code review, security scanning, and multi-language development workflows, evolved from 10+ months of daily use.
Fix Gradle build errors for Android and KMP projects
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
Incrementally fix build and type errors with minimal, safe changes.
Orchestrate parallel Claude Code agents via Claude DevFleet — plan projects from natural language, dispatch agents in isolated worktrees, monitor progress, and read structured reports.
Create or verify a checkpoint in your workflow.
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/info_only/meeting_info/action_required), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
Engineering operating model for teams where AI agents generate a large share of implementation output.
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
一套面向 Claude Code 与多种 AI coding harness 的生产级工作流资产库。
把 AI coding agent 从“偶尔好用”,推进到“稳定可复用”。
awesome claude notes 提供已经打磨过的 agents、skills、commands、rules、hooks、 MCP configs 和跨平台脚本,帮助你更快搭起一套可落地的 agent harness,而不是从零 拼装目录、提示词和自动化流程。
[!IMPORTANT] 本仓库是基于 affaan-m/ECC 的独立社区发行版, 重点维护中文文档、打包与跨工具使用体验,并非官方上游。原作者、贡献者和 MIT 许可证信息均予以保留;同步与差异策略见
UPSTREAM.md。
你通常会在下面这些场景里需要这个仓库:
说明:当前仓库默认以中文作为根 README 展示,
README.zh-CN.md为同步镜像;旧资料里出现的历史仓库名通常只是旧截图或旧安装残留。
推荐路径只保留一条:先安装插件,再安装你当前语言需要的规则和命令。
Quick start gives you access to 28 agents, 125 skills, and 60 commands.
/plugin marketplace add loulanyue/awesome-claude-notes
/plugin install awesome-claude-notes@awesome-claude-notes
Claude Code 插件不会自动分发
rules,所以这一步仍然必需。
git clone https://github.com/loulanyue/awesome-claude-notes.git
cd awesome-claude-notes
npm install
npx ecc typescript
可替换语言示例:python、golang、swift、php。
兼容旧入口:npx ecc-install typescript。
/awesome-claude-notes:plan "Add user authentication"
如果你是手动安装命令,也可以直接使用:
/plan "Add user authentication"。
the-shortform-guide.mdthe-longform-guide.mdthe-security-guide.mddocs/zh-CN/README.mddocs/SELECTIVE-INSTALL-ARCHITECTURE.md
(当前主要为英文)ReleasesTROUBLESHOOTING.md这个仓库的核心目录与能力如下:
| Category | Snapshot | Notes |
|---|---|---|
| Agents | ✅ 28 agents | Specialized subagents for planning, review, build fixing, and orchestration |
| Commands | ✅ 60 commands | Slash-command workflows for planning, testing, review, and maintenance |
| Skills | ✅ 125 skills | Reusable workflow and domain-knowledge modules across harnesses |
agents/:专用子代理,例如 planner、architect、code-reviewer、build resolver。skills/:工作流定义与领域知识模块。commands/:可直接调用的 slash commands,如 /plan、/tdd、/code-review。hooks/:基于工具和生命周期事件的自动化。rules/:始终生效的公共规则与语言专属规则。mcp-configs/:外部集成所需的 MCP 配置。scripts/:跨平台 Node.js 安装与运维脚本。tests/:脚本与安装器的验证用例。从 package.json 当前发布内容看,仓库同时覆盖 Claude、Cursor、Codex、
OpenCode 相关资产,以及 ecc / ecc-install 两个 CLI 入口。
.codex/ 与 AGENTS.md 体系,约束能力更依赖说明文件和沙箱配置。npx ecc <language>?因为 Claude Code 插件本身不能自动分发 rules。
推荐保留插件安装,再用 npx ecc <language> 安装当前语言所需资产。
可以。选择性安装入口保留为:
npx ecc install --profile ... 或 npx ecc install --modules ...。
详细说明见
docs/SELECTIVE-INSTALL-ARCHITECTURE.md。
可以。如果你希望自己管理 ~/.claude/agents/、~/.claude/rules/、
~/.claude/commands/、~/.claude/skills/,请参考完整说明:
docs/zh-CN/README.md。
Duplicate hooks file 怎么办?npx claudepluginhub loulanyue/awesome-claude-notesComplete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.