By spongebobgit
Complete 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
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.
Create or verify a checkpoint in your workflow.
Start NanoClaw v2 — ECC's persistent, zero-dependency REPL with model routing, skill hot-load, branching, compaction, export, and metrics.
Comprehensive security and quality review of uncommitted 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.
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.
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.
SwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance optimization, and modern iOS/macOS UI best practices.
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
Interactive agent picker for composing and dispatching parallel teams
A comprehensive verification system for Claude Code sessions.
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
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
混合检索问答系统:结合RAG语义理解与MySQL关键词检索的智能知识助手,专为教育领域优化
graph TB
%% 用户层
User[👤 用户] --> Web[🌐 Web界面]
User --> CLI[💻 CLI工具]
User --> API[🔌 API调用]
%% API网关层
Web --> Router[🔄 路由网关]
CLI --> Router
API --> Router
%% 查询分类层
Router --> Classifier{🤖 BERT分类器}
Classifier -->|简单/事实型| BM25[🔍 MySQL BM25检索]
Classifier -->|复杂/推理型| RAG[🧠 RAG引擎]
%% MySQL检索分支
BM25 --> MySQL[(🗄️ MySQL知识库)]
MySQL --> Cache1[⚡ Redis缓存]
Cache1 --> Answer1[✅ 精准答案]
%% RAG检索分支
RAG --> Loader[📄 文档加载器]
Loader --> Splitter[✂️ 文本分割器]
Splitter --> Vectorizer[🔢 向量编码]
Vectorizer --> Milvus[(📊 Milvus向量库)]
Milvus --> Retriever[🎯 语义检索]
Retriever --> LLM[🤖 大语言模型]
LLM --> Answer2[💡 生成答案]
%% 公共组件
subgraph "🛡️ 支撑系统"
Cache[(⚡ Redis缓存)]
Logger[📝 日志系统]
Monitor[📈 性能监控]
Auth[🔐 认证授权]
end
%% 数据流
Answer1 --> Response[📦 响应组装]
Answer2 --> Response
Response --> Cache
Response --> Logger
Response --> User
%% 管理接口
Admin[👨💼 管理员] --> Upload[⬆️ 文档上传]
Upload --> Logger
Upload --> Rollback[↩️ 回滚机制]
| 组件 | 技术选择 | 版本 | 说明 |
|---|---|---|---|
| 后端框架 | FastAPI | 0.115+ | 高性能异步API框架,自动生成OpenAPI文档 |
| 向量数据库 | Milvus | 2.5+ | 支持大规模向量相似性检索 |
| 关系数据库 | MySQL | 8.0+ | 结构化知识存储与BM25检索 |
| 缓存系统 | Redis | 5.0+ | 会话缓存、结果缓存、热点数据加速 |
| 文档处理 | LangChain + Unstructured | 0.3+ | 多格式文档解析与文本提取 |
| 向量模型 | BGE-M3 | 1.3+ | 中文语义理解,支持稠密+稀疏+ColBERT检索 |
| LLM服务 | 阿里云DashScope | - | 通义千问系列模型,性价比高 |
| 文本分割 | 中文递归分割器 | 自定义 | 针对中文文档优化的分割算法 |
| 查询分类 | BERT-base-chinese | - | 问题复杂度自动分类 |
| 前端界面 | React + Vite | 18+ | 现代化Web管理界面 |
# 克隆项目
git clone https://github.com/spongebobgit/Hybrid-Retrieval-QA-System.git
cd Hybrid-Retrieval-QA-System
# 安装Python依赖
pip install -r requirments.txt
# 或使用虚拟环境
python -m venv venv
source venv/bin/activate # Linux/Mac
# venv\Scripts\activate # Windows
pip install -r requirments.txt
# 复制配置文件模板
cp config.ini.example config.ini
# 编辑配置文件(填写你的实际配置)
# 需要配置:MySQL连接、Redis连接、阿里云API密钥等
# 开发模式(热重载)
uvicorn app:app --host 0.0.0.0 --port 8001 --reload
# 生产模式
uvicorn app:app --host 0.0.0.0 --port 8001 --workers 4
同步问答:POST /api/query
curl -X POST "http://localhost:8001/api/query" \
-H "Content-Type: application/json" \
-d '{"query": "Python是什么编程语言?", "session_id": "optional"}'
流式问答:WebSocket /ws
const ws = new WebSocket('ws://localhost:8001/ws');
ws.send(JSON.stringify({query: "请详细解释机器学习", session_id: "123"}));
上传文档:POST /api/upload
# 单文件上传
curl -X POST "http://localhost:8001/api/upload" \
-F "[email protected]" \
-F "source=ai"
# 多文件上传
curl -X POST "http://localhost:8001/api/upload" \
-F "[email protected]" \
-F "[email protected]" \
-F "source=java"
# ZIP压缩包上传
curl -X POST "http://localhost:8001/api/upload" \
-F "[email protected]" \
-F "is_zip=true" \
-F "source=bigdata"
知识库统计:GET /api/knowledgebase/stats
curl "http://localhost:8001/api/knowledgebase/stats"
查询日志:GET /api/upload/logs
curl "http://localhost:8001/api/upload/logs?source=ai&limit=10&offset=0"
回滚操作:`POST /api/upload/rollback/{log_id}"
curl -X POST "http://localhost:8001/api/upload/rollback/123"
npx claudepluginhub spongebobgit/hybrid-retrieval-qa-systemHarness-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.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review