sqry-gemini

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

sqry for Gemini CLI

适用于Gemini CLI的sqry

This skill configures the Gemini CLI agent to use sqry's MCP server for AST-based semantic code search across 37 languages.

本skill用于配置Gemini CLI Agent，使其可以使用sqry的MCP服务器，实现对37种语言的基于AST的语义代码搜索功能。

Setup

设置步骤

1. Install sqry

1. 安装sqry

bash

undefined

bash

undefined

Recommended: signed release installer

推荐：签名版本安装器

curl -fsSL https://raw.githubusercontent.com/verivus-oss/sqry/main/scripts/install.sh | bash -s -- --component all

Fallback: build from source

备用方案：从源码构建

cargo install sqry-cli cargo install sqry-mcp

Alternative package manager

其他包管理器安装方式

brew install verivus-oss/sqry/sqry

undefined

brew install verivus-oss/sqry/sqry

undefined

2. Index your project

2. 为项目构建索引

bash

cd /path/to/your/project
sqry index .

bash

cd /path/to/your/project
sqry index .

3. Configure MCP server

3. 配置MCP服务器

Recommended:

bash

sqry mcp setup --tool gemini
sqry mcp status

This writes a global entry to

~/.gemini/settings.json

json

{
  "mcpServers": {
    "sqry": {
      "command": "/absolute/path/to/sqry-mcp",
      "args": [],
      "env": {}
    }
  }
}

Gemini uses CWD-based workspace discovery by default. Start Gemini from the project directory you want to analyze.

推荐操作：

bash

sqry mcp setup --tool gemini
sqry mcp status

这会在

~/.gemini/settings.json

中写入一条全局配置：

json

{
  "mcpServers": {
    "sqry": {
      "command": "/absolute/path/to/sqry-mcp",
      "args": [],
      "env": {}
    }
  }
}

Gemini默认基于当前工作目录(CWD)发现工作区，请从你要分析的项目目录启动Gemini。

4. Verify

4. 验证配置

After restarting Gemini CLI, test with:

"Use sqry to show graph stats for this project"

重启Gemini CLI后，使用以下指令测试：

"Use sqry to show graph stats for this project"

Skill Dependency

Skill依赖

This skill covers Gemini CLI setup and integration patterns. Also load the
sqry-semantic-search
skill for tool selection guidance, query syntax, and disambiguation strategies.

sqry-semantic-search uses tiered discovery to save tokens: it loads a compact Quick Tool Selection guide first. If you need full parameter details, load

sqry-semantic-search/references/tool-reference.md

. For advanced workflows (security audit, pre-change analysis), load

sqry-semantic-search/references/workflows.md

. Only load what you need.

本skill涵盖Gemini CLI的设置和集成模式。请同时加载
sqry-semantic-search
skill以获取工具选择指南、查询语法和歧义消除策略。

sqry-semantic-search采用分层发现机制节省token：它会优先加载精简的快速工具选择指南。如果你需要完整的参数说明，请加载

sqry-semantic-search/references/tool-reference.md

。对于高级工作流（安全审计、变更前分析），请加载

sqry-semantic-search/references/workflows.md

，按需加载即可，无需加载全部内容。

Quick Tool Selection

快速工具选择指南

I know the symbol name and want to...

See its definition →
```
mcp__sqry__get_definition
```

See who calls it →

mcp__sqry__direct_callers

(depth=1) or

mcp__sqry__relation_query

(multi-depth)

See what it calls →
```
mcp__sqry__direct_callees
```
See what breaks if I change it →
```
mcp__sqry__dependency_impact
```
Understand it with context →
```
mcp__sqry__explain_code
```

I want to search for symbols...

By name substring →
```
mcp__sqry__pattern_search
```
By kind/visibility/language →
```
mcp__sqry__semantic_search
```
With RAG-optimized grouping →
```
mcp__sqry__hierarchical_search
```

I want to analyze the codebase...

Circular dependencies →
```
mcp__sqry__find_cycles
```
Dead code →
```
mcp__sqry__find_unused
```
Change impact →
```
mcp__sqry__dependency_impact
```
Trace call path A→B →
```
mcp__sqry__trace_path
```

我知道符号名称，想要...

查看其定义 →
```
mcp__sqry__get_definition
```
查看调用它的对象 →
```
mcp__sqry__direct_callers
```
（深度=1）或
```
mcp__sqry__relation_query
```
（多深度）
查看它调用的对象 →
```
mcp__sqry__direct_callees
```
查看修改它会影响哪些内容 →
```
mcp__sqry__dependency_impact
```
结合上下文理解代码含义 →
```
mcp__sqry__explain_code
```

我想要搜索符号...

通过名称子串搜索 →
```
mcp__sqry__pattern_search
```
通过类型/可见性/语言搜索 →
```
mcp__sqry__semantic_search
```
使用RAG优化的分组方式搜索 →
```
mcp__sqry__hierarchical_search
```

我想要分析代码库...

查找循环依赖 →
```
mcp__sqry__find_cycles
```
查找死代码 →
```
mcp__sqry__find_unused
```
分析变更影响 →
```
mcp__sqry__dependency_impact
```
追踪A到B的调用路径 →
```
mcp__sqry__trace_path
```

Handling Ambiguous Symbols

歧义符号处理

When using

mcp__sqry__direct_callers

mcp__sqry__direct_callees

, or

mcp__sqry__call_hierarchy

with common names (

handle

new

init

process

run

), the tool may fail or return wrong results.

Always disambiguate by providing

file_path

json

{
  "symbol": "handle",
  "file_path": "src/api/router.rs"
}

Or use a qualified name:

"symbol": "UserService::authenticate"

If relation tools fail, fall back to

mcp__sqry__get_references

with a

path

filter to scope results.

当对常用名称（

handle

、

new

、

init

、

process

、

run

）使用

mcp__sqry__direct_callers

、

mcp__sqry__direct_callees

或

mcp__sqry__call_hierarchy

时，工具可能运行失败或返回错误结果。

请始终通过提供
file_path
来消除歧义：

json

{
  "symbol": "handle",
  "file_path": "src/api/router.rs"
}

或者使用限定名称：

"symbol": "UserService::authenticate"

如果关系工具运行失败，请回退到使用带有

path

过滤器的

mcp__sqry__get_references

来限定结果范围。

Tool Naming in Gemini CLI

Gemini CLI中的工具命名规则

Gemini CLI uses the

mcp__sqry__

prefix for sqry MCP tools:

mcp__sqry__semantic_search
mcp__sqry__relation_query
mcp__sqry__dependency_impact
mcp__sqry__explain_code
mcp__sqry__trace_path
...

Gemini CLI为sqry MCP工具添加

mcp__sqry__

前缀：

mcp__sqry__semantic_search
mcp__sqry__relation_query
mcp__sqry__dependency_impact
mcp__sqry__explain_code
mcp__sqry__trace_path
...

Recommended GEMINI.md Addition

Code Search

代码搜索

Use sqry MCP tools for semantic code search:

```
mcp__sqry__semantic_search
```
- Find symbols by structure
```
mcp__sqry__relation_query
```
- Find callers, callees, imports
```
mcp__sqry__dependency_impact
```
- Analyze change impact
```
mcp__sqry__explain_code
```
- Understand a symbol with context

Use grep/rg for literal text search. Use sqry for everything structural.

undefined

使用sqry MCP工具进行语义代码搜索：

```
mcp__sqry__semantic_search
```
- 按结构查找符号
```
mcp__sqry__relation_query
```
- 查找调用方、被调用方、导入关系
```
mcp__sqry__dependency_impact
```
- 分析变更影响范围
```
mcp__sqry__explain_code
```
- 结合上下文理解符号含义

使用grep/rg进行字面量文本搜索，所有结构相关搜索都使用sqry。

undefined

Workflow

工作流

Use
```
mcp__sqry__semantic_search
```
for fast discovery before reading files manually.
Use
```
mcp__sqry__dependency_impact
```
before modifying shared symbols.
Run focused tests first; run broader checks for shared graph, query, or plugin paths.
In handoff, always include changed files, impact summary, and tests run.

手动阅读文件前先使用
```
mcp__sqry__semantic_search
```
快速发现目标内容。
修改共享符号前先使用
```
mcp__sqry__dependency_impact
```
分析影响。
优先运行聚焦测试，针对共享图、查询或插件路径运行更全面的检查。
交接工作时，始终包含修改的文件、影响摘要和已运行的测试信息。

Common Gemini Patterns

常用Gemini使用模式

Explore a codebase

探索代码库

1. mcp__sqry__get_graph_stats    (overview: languages, node/edge counts)
2. mcp__sqry__list_files         (what files are indexed)
3. mcp__sqry__semantic_search    query: "kind:function", filters: {visibility: "public"}

1. mcp__sqry__get_graph_stats    （概览：语言、节点/边数量）
2. mcp__sqry__list_files         （已索引的文件列表）
3. mcp__sqry__semantic_search    query: "kind:function", filters: {visibility: "public"}

Trace a call chain

追踪调用链

1. mcp__sqry__get_definition     symbol: "handle_request"
2. mcp__sqry__direct_callees     symbol: "handle_request"
3. mcp__sqry__trace_path         from_symbol: "handle_request", to_symbol: "db_query"

1. mcp__sqry__get_definition     symbol: "handle_request"
2. mcp__sqry__direct_callees     symbol: "handle_request"
3. mcp__sqry__trace_path         from_symbol: "handle_request", to_symbol: "db_query"

Pre-change safety check

变更前安全检查

1. mcp__sqry__dependency_impact  symbol: "UserService", max_depth: 3
2. mcp__sqry__find_cycles        (check for circular deps)
3. Make changes
4. mcp__sqry__semantic_diff      base: {ref: "main"}, target: {ref: "HEAD"}

1. mcp__sqry__dependency_impact  symbol: "UserService", max_depth: 3
2. mcp__sqry__find_cycles        （检查循环依赖）
3. 进行代码修改
4. mcp__sqry__semantic_diff      base: {ref: "main"}, target: {ref: "HEAD"}

Gemini Context Notes

Gemini上下文说明

Gemini defaults to loading
```
GEMINI.md
```
for project context.
sqry MCP tools provide deeper structural understanding than what context files alone offer.
Use
```
mcp__sqry__hierarchical_search
```
to get RAG-optimized results that include file and container grouping — this pairs well with Gemini's context window management.

Gemini默认会加载
```
GEMINI.md
```
获取项目上下文。
sqry MCP工具比单独的上下文文件能提供更深层次的结构理解能力。
使用
```
mcp__sqry__hierarchical_search
```
可以获取包含文件和容器分组的RAG优化结果，这与Gemini的上下文窗口管理能力适配性很好。

Recent Features (since v6.0)

新功能（v6.0版本起）

Plugin cost tiering

插件成本分层

Plugins classified as
```
Fast
```
(default) or
```
HighWallClock
```
High-cost plugins (JSON, ServiceNow XML) excluded from default index

CLI:

--include-high-cost

--exclude-high-cost

--enable-plugin ID

--disable-plugin ID

Env:
```
SQRY_INCLUDE_HIGH_COST=1
```

插件分为
```
Fast
```
（默认）和
```
HighWallClock
```
两类
高成本插件（JSON、ServiceNow XML）默认不纳入索引

CLI参数：

--include-high-cost

--exclude-high-cost

，

--enable-plugin ID

--disable-plugin ID

环境变量：
```
SQRY_INCLUDE_HIGH_COST=1
```

Time-expensive MCP operations

耗时较长的MCP操作

```
rebuild_index
```
: 10min timeout, full graph rebuild -- only when index stale
```
semantic_diff
```
: creates git worktrees + indexes -- scope with file/kind filters
```
find_cycles
```
,
```
complexity_metrics
```
: can timeout on large graphs -- scope to files
```
find_duplicates
```
: quadratic scaling -- filter by file/language/kind
```
call_hierarchy
```
depth>2,
```
dependency_impact
```
depth>3: exponential growth

```
rebuild_index
```
：10分钟超时，全量重建图结构——仅在索引过期时使用
```
semantic_diff
```
：创建git工作树+构建索引——通过文件/类型过滤器限定范围
```
find_cycles
```
、
```
complexity_metrics
```
：大型图结构上可能超时——限定到指定文件范围
```
find_duplicates
```
：二次方时间复杂度——通过文件/语言/类型过滤
```
call_hierarchy
```
深度>2、
```
dependency_impact
```
深度>3：指数级复杂度增长

Macro boundary analysis (Rust)

宏边界分析（Rust）

CLI:

sqry cache expand

--enable-macro-expansion

--cfg

--cfg-filter

--include-generated

--macro-boundaries

MCP:
```
mcp__sqry__expand_cache_status
```
tool, macro metadata in search/definition results

CLI参数：

sqry cache expand

、

--enable-macro-expansion

、

--cfg

、

--cfg-filter

、

--include-generated

、

--macro-boundaries

MCP工具：
```
mcp__sqry__expand_cache_status
```
，搜索/定义结果中包含宏元数据

JVM classpath analysis

JVM类路径分析

CLI:

--classpath

--classpath-depth

--classpath-file

MCP:
```
include_classpath
```
parameter on search tools,
```
provenance
```
field in results

CLI参数：

--classpath

、

--classpath-depth

、

--classpath-file

MCP：搜索工具支持
```
include_classpath
```
参数，结果中包含
```
provenance
```
字段

Security defaults

安全默认配置

MCP redaction preset now
```
"minimal"
```
by default (was
```
"none"
```
)
Override:
```
SQRY_REDACTION_PRESET=none
```
Index timeout: 600s, query timeout: 60s

MCP脱敏预设默认值现在为
```
"minimal"
```
（之前为
```
"none"
```
）
覆盖配置：
```
SQRY_REDACTION_PRESET=none
```
索引超时：600秒，查询超时：60秒

Other

其他

37 language plugins (added JSON, ServiceNow XML)
Snapshot format V7 -- rebuild index on major version upgrade
Multi-root VS Code workspace support

37个语言插件（新增JSON、ServiceNow XML支持）
快照格式V7——大版本升级后需要重建索引
支持多根目录VS Code工作区

Troubleshooting

故障排查

No tools visible: Restart Gemini CLI after running
```
sqry mcp setup --tool gemini
```
Empty results: Run
```
sqry index .
```
to build the index
Stale results: Run
```
sqry index --force .
```
to force rebuild
Snapshot version mismatch: Run
```
rm -rf .sqry/graph && sqry index .
```
after major upgrades
Missing JSON/ServiceNow symbols: Rebuild with
```
sqry index --include-high-cost
```
Check health: Call
```
mcp__sqry__get_index_status
```

看不到工具：运行
```
sqry mcp setup --tool gemini
```
后重启Gemini CLI
结果为空：运行
```
sqry index .
```
构建索引
结果过期：运行
```
sqry index --force .
```
强制重建索引
快照版本不匹配：大版本升级后运行
```
rm -rf .sqry/graph && sqry index .
```
缺少JSON/ServiceNow符号：使用
```
sqry index --include-high-cost
```
重建索引
检查运行状态：调用
```
mcp__sqry__get_index_status
```

sqry-gemini

Original

Translation

sqry for Gemini CLI

适用于Gemini CLI的sqry

Setup

设置步骤

1. Install sqry

1. 安装sqry

Recommended: signed release installer

推荐：签名版本安装器

Fallback: build from source

备用方案：从源码构建

Alternative package manager

其他包管理器安装方式

2. Index your project

2. 为项目构建索引

3. Configure MCP server

3. 配置MCP服务器

4. Verify

4. 验证配置

Skill Dependency

Skill依赖

Quick Tool Selection

快速工具选择指南

Handling Ambiguous Symbols

歧义符号处理

Tool Naming in Gemini CLI

Gemini CLI中的工具命名规则

Recommended GEMINI.md Addition

推荐添加到GEMINI.md的内容

Code Search

代码搜索

Workflow

工作流

Common Gemini Patterns

常用Gemini使用模式

Explore a codebase

探索代码库

Trace a call chain

追踪调用链

Pre-change safety check

变更前安全检查

Gemini Context Notes

Gemini上下文说明

Recent Features (since v6.0)

新功能（v6.0版本起）

Plugin cost tiering

插件成本分层

Time-expensive MCP operations

耗时较长的MCP操作

Macro boundary analysis (Rust)

宏边界分析（Rust）

JVM classpath analysis

JVM类路径分析

Security defaults

安全默认配置

Other

其他

Troubleshooting

故障排查