flipside

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Flipside CLI

Query blockchain data, create AI agents, and build automated data pipelines.

查询区块链数据、创建AI Agent并构建自动化数据管道。

First Steps

入门步骤

Always start by checking what's available in the user's organization:

bash

undefined

始终从检查用户组织中可用的资源开始：

bash

undefined

1. Verify authentication and see the current org

1. 验证身份验证并查看当前组织

flipside whoami

2. List available agents (names vary by org)

2. 列出可用的Agent（名称因组织而异）

flipside agents list

3. List available skills

3. 列出可用的Skill

flipside skills list


Agent and skill names are organization-specific. Always run `flipside agents list` to discover what agents are available before trying to use them.

flipside skills list


Agent和Skill的名称是组织特定的。在尝试使用Agent之前，务必运行`flipside agents list`来发现可用的Agent。

Golden Rule

黄金准则

Use Flipside agents for SQL queries. Don't write SQL from scratch—let the agents generate correct queries against Flipside's data warehouse.

Note: The
flipside/data
skill is automatically injected into all agents, providing SQL query tools. You don't need to manually configure this.

bash

undefined

使用Flipside Agent执行SQL查询。不要从头编写SQL——让Agent针对Flipside的数据仓库生成正确的查询。

注意：
flipside/data
Skill会自动注入到所有Agent中，提供SQL查询工具。您无需手动配置。

bash

undefined

One-shot query (no session memory)

一次性查询（无会话记忆）

flipside agents run <org>/<agent_name> --message "Get the top 10 DEX swaps on Ethereum today"

Multi-turn conversation (maintains context between messages)

多轮对话（在消息之间保持上下文）

flipside chat create # get session ID flipside chat send-message --session-id <id> "Get top DEX swaps on Ethereum" flipside chat send-message --session-id <id> "Now filter to only Uniswap"

flipside chat create # 获取会话ID flipside chat send-message --session-id <id> "Get top DEX swaps on Ethereum" flipside chat send-message --session-id <id> "Now filter to only Uniswap"

Always use --title when testing (makes sessions easier to find)

测试时务必使用--title（便于查找会话）

flipside agents run <org>/<agent_name> --message "test query" --title "Testing from Claude Code"

undefined

flipside agents run <org>/<agent_name> --message "test query" --title "Testing from Claude Code"

undefined

Primary Workflows

主要工作流

One-Shot Queries (agents run)

一次性查询（agents run）

For single queries without session memory, use

flipside agents run

bash

undefined

对于无需会话记忆的单个查询，使用

flipside agents run

：

bash

undefined

First, list available agents to find the right one

首先，列出可用的Agent以找到合适的那个

flipside agents list

Run a chat agent with a message

运行聊天型Agent并发送消息

flipside agents run <org>/<agent_name> --message "Show me the largest ETH transfers today"

Run a sub agent with structured JSON input

使用结构化JSON输入运行子Agent

flipside agents run <org>/<agent_name> --data-json '{"chain": "ethereum", "limit": 10}'

Add a title for easier session tracking

添加标题以便于会话跟踪

flipside agents run <org>/<agent_name> --message "Query request" --title "My analysis"


**IMPORTANT:** Agent names MUST use the `org/agent_name` format. Get the exact names from `flipside agents list`.

flipside agents run <org>/<agent_name> --message "Query request" --title "My analysis"


**重要提示：** Agent名称必须使用`org/agent_name`格式。从`flipside agents list`获取准确名称。

Multi-Turn Conversations (chat)

多轮对话（chat）

For conversations that need session memory (follow-up questions, context from previous messages), use chat:

bash

undefined

对于需要会话记忆的对话（后续问题、参考之前消息的上下文），使用chat功能：

bash

undefined

Create a new chat session

创建新的聊天会话

flipside chat create

Returns: Session ID: abc123...

返回：Session ID: abc123...

Send messages to the session (maintains context)

向会话发送消息（保持上下文）

flipside chat send-message --session-id <session-id> "What were the top DEX swaps on Ethereum yesterday?"

Follow up (the session remembers previous context)

跟进（会话会记住之前的上下文）

flipside chat send-message --session-id <session-id> "Now show me the same for Arbitrum"

List your sessions

列出您的会话

flipside chat list

Resume an existing session interactively

交互式恢复现有会话

flipside chat resume


Use chat when you need:
- Follow-up questions that reference previous answers
- Multi-step analysis where context matters
- Building on previous query results

flipside chat resume


在以下场景使用chat功能：
- 需要参考之前答案的后续问题
- 上下文至关重要的多步骤分析
- 基于之前查询结果进行扩展

Running SQL Directly

直接运行SQL

For known queries, you can run SQL directly:

bash

undefined

对于已知的查询，您可以直接运行SQL：

bash

undefined

Create and execute a query

创建并执行查询

flipside query create "SELECT * FROM ethereum.core.fact_blocks LIMIT 10"

Execute an existing saved query

执行已保存的现有查询

flipside query execute <query-id>

Get results from a query run

获取查询运行的结果

flipside query-run result <run-id>

undefined

flipside query-run result <run-id>

undefined

Command Reference

命令参考

Agents

bash

flipside agents list                              # List available agents
flipside agents init my_agent                     # Create agent YAML template
flipside agents validate my_agent.agent.yaml      # Validate before deploy
flipside agents push my_agent.agent.yaml          # Deploy agent
flipside agents run <org>/<agent> --message "..." # Run chat agent
flipside agents run <org>/<agent> --data-json '{}' # Run sub agent
flipside agents describe <org>/<agent>            # Show agent details
flipside agents pull <org>/<agent>                # Download agent YAML
flipside agents delete <org>/<agent>              # Delete an agent

bash

flipside agents list                              # 列出可用的Agent
flipside agents init my_agent                     # 创建Agent YAML模板
flipside agents validate my_agent.agent.yaml      # 部署前验证
flipside agents push my_agent.agent.yaml          # 部署Agent
flipside agents run <org>/<agent> --message "..." # 运行聊天型Agent
flipside agents run <org>/<agent> --data-json '{}' # 运行子Agent
flipside agents describe <org>/<agent>            # 显示Agent详情
flipside agents pull <org>/<agent>                # 下载Agent YAML
flipside agents delete <org>/<agent>              # 删除Agent

Chat

bash

flipside chat                                     # Start interactive chat
flipside chat --run <run-id>                      # Chat about an automation run
flipside chat resume                              # Resume previous chat
flipside chat list                                # List chat sessions
flipside chat send-message --session-id <id> "x" # Programmatic message

bash

flipside chat                                     # 启动交互式聊天
flipside chat --run <run-id>                      # 针对自动化运行进行聊天
flipside chat resume                              # 恢复之前的聊天
flipside chat list                                # 列出聊天会话
flipside chat send-message --session-id <id> "x" # 程序化发送消息

Queries

bash

flipside query create "SELECT ..."                # Create saved query
flipside query list                               # List saved queries
flipside query get <query-id>                     # Get query details
flipside query execute <query-id>                 # Execute query (creates run)
flipside query runs <query-id>                    # List runs for a query
flipside query-run result <run-id>                # Get query results
flipside query-run status <run-id>                # Check run status
flipside query-run poll <run-id>                  # Poll until complete

bash

flipside query create "SELECT ..."                # 创建已保存查询
flipside query list                               # 列出已保存查询
flipside query get <query-id>                     # 获取查询详情
flipside query execute <query-id>                 # 执行查询（创建运行实例）
flipside query runs <query-id>                    # 列出查询的运行实例
flipside query-run result <run-id>                # 获取查询结果
flipside query-run status <run-id>                # 检查运行状态
flipside query-run poll <run-id>                  # 轮询直到完成

Automations

bash

flipside automations list                         # List automations
flipside automations init my_pipeline             # Create automation YAML
flipside automations validate <file>              # Validate before deploy
flipside automations push <file>                  # Deploy automation
flipside automations run <id>                     # Trigger automation
flipside automations run <id> -i '{"key":"val"}'  # Run with inputs
flipside automations runs list <id>               # List runs
flipside automations runs result <run-id>         # Get run results

bash

flipside automations list                         # 列出自动化任务
flipside automations init my_pipeline             # 创建自动化YAML模板
flipside automations validate <file>              # 部署前验证
flipside automations push <file>                  # 部署自动化任务
flipside automations run <id>                     # 触发自动化任务
flipside automations run <id> -i '{"key":"val"}'  # 带输入参数运行
flipside automations runs list <id>               # 列出运行实例
flipside automations runs result <run-id>         # 获取运行结果

Skills

bash

flipside skills list                              # List available skills
flipside skills init my_skill                     # Create skill YAML
flipside skills push my_skill.skill.yaml          # Deploy skill

bash

flipside skills list                              # 列出可用的Skill
flipside skills init my_skill                     # 创建Skill YAML模板
flipside skills push my_skill.skill.yaml          # 部署Skill

Utilities

实用工具

bash

flipside whoami                                   # Show current user/org
flipside --help                                   # Full command help
flipside <command> --help                         # Help for specific command
flipside update                                   # Update CLI to latest version

bash

flipside whoami                                   # 显示当前用户/组织
flipside --help                                   # 完整命令帮助
flipside <command> --help                         # 特定命令的帮助
flipside update                                   # 将CLI更新到最新版本

When to Load References

何时加载参考文档

Load the detailed reference files when you need:

AGENTS.md - Agent YAML schema, chat vs sub agents, deployment
AUTOMATIONS.md - Pipeline steps, DAG edges, scheduling
SKILLS.md - Creating reusable tool bundles
TABLES.md - Common tables by chain (Ethereum, Solana, etc.)
QUERIES.md - SQL patterns, result handling

在以下场景加载详细的参考文件：

AGENTS.md - Agent YAML schema、聊天型Agent vs 子Agent、部署
AUTOMATIONS.md - 管道步骤、DAG边、调度
SKILLS.md - 创建可复用工具包
TABLES.md - 各链的常用表（以太坊、Solana等）
QUERIES.md - SQL模式、结果处理

Creating New Agents

创建新Agent

bash

undefined

bash

undefined

1. Create a template

1. 创建模板

flipside agents init my_agent

2. Edit the generated YAML file

2. 编辑生成的YAML文件

my_agent.agent.yaml

Note: flipside/data skill is auto-injected - SQL tools work out of the box

注意：flipside/data Skill会自动注入 - SQL工具开箱即用

3. Validate before deploying

3. 部署前验证

flipside agents validate my_agent.agent.yaml

4. Deploy

4. 部署

flipside agents push my_agent.agent.yaml

undefined

flipside agents push my_agent.agent.yaml

undefined

Templates

模板

Starter templates are available in

assets/

```
assets/agent.template.yaml
```
- Basic agent config
```
assets/automation.template.yaml
```
- Basic automation config
```
assets/skill.template.yaml
```
- Basic skill config

Copy and customize these for new projects.

入门模板位于

assets/

目录中：

```
assets/agent.template.yaml
```
- 基础Agent配置
```
assets/automation.template.yaml
```
- 基础自动化配置
```
assets/skill.template.yaml
```
- 基础Skill配置

复制并自定义这些模板以用于新项目。

Troubleshooting

故障排除

If a command fails:

Check authentication:
```
flipside whoami
```
Check CLI version:
```
flipside --version
```
and
```
flipside update
```
Use verbose mode:
```
flipside --verbose <command>
```
Check JSON output for details:
```
flipside --json <command>
```

如果命令执行失败：

检查身份验证：
```
flipside whoami
```
检查CLI版本：
```
flipside --version
```
并运行
```
flipside update
```
使用详细模式：
```
flipside --verbose <command>
```
检查JSON输出以获取详细信息：
```
flipside --json <command>
```