grepai-quickstart by yoanbernabeu/grepai-skills
npx skills add https://github.com/yoanbernabeu/grepai-skills --skill grepai-quickstart本技能提供完整指南,帮助您在5分钟内启动 GrepAI 并开始搜索代码。
brew install yoanbernabeu/tap/grepai
curl -sSL https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.sh | sh
irm https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.ps1 | iex
验证安装:grepai version
brew install ollama
ollama serve &
ollama pull nomic-embed-text
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
curl -fsSL https://ollama.com/install.sh | sh
ollama serve &
ollama pull nomic-embed-text
验证:curl http://localhost:11434/api/tags
进入项目目录并初始化 GrepAI:
cd /path/to/your/project
grepai init
这将创建包含默认设置的 .grepai/config.yaml:
nomic-embed-text 模型启动监控守护进程以索引代码:
grepai watch
执行过程:
.gitignore).grepai/index.gob 中首次索引输出:
🔍 GrepAI Watch
Scanning files...
Found 245 files
Processing chunks...
████████████████████████████████ 100%
Indexed 1,234 chunks
Watching for changes...
对于长期运行的项目:
# 在后台启动
grepai watch --background
# 检查状态
grepai watch --status
# 完成后停止
grepai watch --stop
现在可以进行语义搜索:
# 基础搜索
grepai search "authentication flow"
# 限制结果数量
grepai search "error handling" --limit 5
# 脚本使用的 JSON 输出
grepai search "database queries" --json
Score: 0.89 | src/auth/middleware.go:15-45
──────────────────────────────────────────
func AuthMiddleware() gin.HandlerFunc {
return func(c *gin.Context) {
token := c.GetHeader("Authorization")
if token == "" {
c.AbortWithStatus(401)
return
}
// Validate JWT token...
}
}
Score: 0.82 | src/auth/jwt.go:23-55
──────────────────────────────────────────
func ValidateToken(tokenString string) (*Claims, error) {
token, err := jwt.Parse(tokenString, func(t *jwt.Token) (interface{}, error) {
return []byte(secretKey), nil
})
// ...
}
追踪函数关系:
# 谁调用了这个函数?
grepai trace callers "Login"
# 这个函数调用了什么?
grepai trace callees "ProcessPayment"
# 完整依赖关系图
grepai trace graph "ValidateToken" --depth 3
# 1. 安装(一次性)
brew install yoanbernabeu/tap/grepai
brew install ollama && ollama serve & && ollama pull nomic-embed-text
# 2. 设置项目(每个项目一次)
cd /your/project
grepai init
# 3. 索引(在后台运行)
grepai watch --background
# 4. 搜索(按需使用)
grepai search "your query here"
# 5. 追踪(按需使用)
grepai trace callers "FunctionName"
| 命令 | 用途 |
|---|---|
grepai init | 初始化项目配置 |
grepai watch | 启动索引守护进程 |
grepai watch --background | 在后台运行守护进程 |
grepai watch --status | 检查守护进程状态 |
grepai watch --stop | 停止守护进程 |
grepai search "query" | 语义搜索 |
grepai search --json | JSON 输出 |
grepai trace callers "fn" | 查找调用者 |
grepai trace callees "fn" | 查找被调用者 |
grepai status | 索引统计信息 |
grepai version | 显示版本 |
使用描述性语言,而非字面匹配:
描述意图:
使用英语:
掌握基础后:
grepai-embeddings-* 技能grepai-storage-* 技能grepai-search-* 技能grepai-mcp-* 技能快速入门成功:
✅ GrepAI 快速入门完成
项目:/path/to/your/project
已索引文件:245
创建分块:1,234
嵌入器:Ollama (nomic-embed-text)
存储:GOB(本地文件)
尝试以下搜索:
- grepai search "main entry point"
- grepai search "database connection"
- grepai search "error handling"
每周安装量
237
代码仓库
GitHub 星标数
15
首次出现
2026年1月28日
安全审计
已安装于
opencode189
codex182
github-copilot167
gemini-cli166
kimi-cli154
claude-code154
This skill provides a complete walkthrough to get GrepAI running and searching your code in 5 minutes.
brew install yoanbernabeu/tap/grepai
curl -sSL https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.sh | sh
irm https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.ps1 | iex
Verify: grepai version
brew install ollama
ollama serve &
ollama pull nomic-embed-text
curl -fsSL https://ollama.com/install.sh | sh
ollama serve &
ollama pull nomic-embed-text
Verify: curl http://localhost:11434/api/tags
Navigate to your project and initialize GrepAI:
cd /path/to/your/project
grepai init
This creates .grepai/config.yaml with default settings:
nomic-embed-text modelStart the watch daemon to index your code:
grepai watch
What happens:
.gitignore).grepai/index.gobFirst indexing output:
🔍 GrepAI Watch
Scanning files...
Found 245 files
Processing chunks...
████████████████████████████████ 100%
Indexed 1,234 chunks
Watching for changes...
For long-running projects:
# Start in background
grepai watch --background
# Check status
grepai watch --status
# Stop when done
grepai watch --stop
Now search semantically:
# Basic search
grepai search "authentication flow"
# Limit results
grepai search "error handling" --limit 5
# JSON output for scripts
grepai search "database queries" --json
Score: 0.89 | src/auth/middleware.go:15-45
──────────────────────────────────────────
func AuthMiddleware() gin.HandlerFunc {
return func(c *gin.Context) {
token := c.GetHeader("Authorization")
if token == "" {
c.AbortWithStatus(401)
return
}
// Validate JWT token...
}
}
Score: 0.82 | src/auth/jwt.go:23-55
──────────────────────────────────────────
func ValidateToken(tokenString string) (*Claims, error) {
token, err := jwt.Parse(tokenString, func(t *jwt.Token) (interface{}, error) {
return []byte(secretKey), nil
})
// ...
}
Trace function relationships:
# Who calls this function?
grepai trace callers "Login"
# What does this function call?
grepai trace callees "ProcessPayment"
# Full dependency graph
grepai trace graph "ValidateToken" --depth 3
# 1. Install (once)
brew install yoanbernabeu/tap/grepai
brew install ollama && ollama serve & && ollama pull nomic-embed-text
# 2. Setup project (once per project)
cd /your/project
grepai init
# 3. Index (run in background)
grepai watch --background
# 4. Search (as needed)
grepai search "your query here"
# 5. Trace (as needed)
grepai trace callers "FunctionName"
| Command | Purpose |
|---|---|
grepai init | Initialize project config |
grepai watch | Start indexing daemon |
grepai watch --background | Run daemon in background |
grepai watch --status | Check daemon status |
grepai watch --stop | Stop daemon |
grepai search "query" | Semantic search |
Be descriptive, not literal:
Describe intent:
Use English:
After mastering the basics:
grepai-embeddings-* skillsgrepai-storage-* skillsgrepai-search-* skillsgrepai-mcp-* skillsSuccessful quickstart:
✅ GrepAI Quickstart Complete
Project: /path/to/your/project
Files indexed: 245
Chunks created: 1,234
Embedder: Ollama (nomic-embed-text)
Storage: GOB (local file)
Try these searches:
- grepai search "main entry point"
- grepai search "database connection"
- grepai search "error handling"
Weekly Installs
237
Repository
GitHub Stars
15
First Seen
Jan 28, 2026
Security Audits
Gen Agent Trust HubFailSocketPassSnykFail
Installed on
opencode189
codex182
github-copilot167
gemini-cli166
kimi-cli154
claude-code154
React 组合模式指南:Vercel 组件架构最佳实践,提升代码可维护性
106,200 周安装
Hugging Face Jobs:云端运行AI工作负载,无需本地GPU,支持数据处理、批量推理和模型训练
232 周安装
MCP服务器构建器:快速创建生产就绪的MCP服务器与ChatGPT小组件
314 周安装
Mapbox样式质量检查与优化工具 - 验证、可访问性、性能优化指南
384 周安装
PDF 生成器 - Deno 自动化 PDF 创建、填充、合并与处理工具
355 周安装
Azure镜像构建器教程:使用Packer创建Azure托管镜像和计算库镜像
346 周安装
Qdrant向量数据库Java集成指南:Spring Boot与LangChain4j语义搜索实战
339 周安装
grepai search --json | JSON output |
grepai trace callers "fn" | Find callers |
grepai trace callees "fn" | Find callees |
grepai status | Index statistics |
grepai version | Show version |