agentleFS
Eleven-MEleven-M/flowmind/skills/resource-bind/SKILL.md

resource-bind

Skill1 starsChanged 3 months agoMITView on GitHub

Resource binding and connection management skill for FlowMind. Bind and manage database, Redis, and API resource connections and MCP credentials (资源绑定/连接管理). Not for deployment or pipeline execution.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep binding records in local learning files so users do not need to re-enter the same setup repeatedly

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Resource Bind Skill

Bind and manage database, Redis, API, and other external resource connections.

Features

🗄️ Database Management

  • MySQL/PostgreSQL connections
  • Connection pooling
  • Query execution
  • Schema inspection

📦 Redis Management

  • Redis connections
  • Key operations
  • Cache management

🔌 API Integration

  • REST API connections
  • Authentication management
  • Request/response handling

🧠 Business Binding Memory

  • Save MCP server, address, token, namespace, project, and similar connection fields by business
  • Reuse learned bindings automatically when the same business appears again
  • Keep binding records in local learning files so users do not need to re-enter the same setup repeatedly

Trigger Patterns

"数据库", "database", "SQL"
"redis", "缓存", "cache"
"API连接", "API绑定", "DB连接", "接口连接"
"资源绑定", "资源", "resource"
"连接配置", "connection"

Resource Types

Database

{
  "type": "mysql",
  "host": "localhost",
  "port": 3306,
  "database": "mydb",
  "username": "user",
  "password": "pass"
}

Redis

{
  "type": "redis",
  "host": "localhost",
  "port": 6379,
  "password": "",
  "db": 0
}

API

{
  "type": "rest",
  "baseUrl": "https://api.example.com",
  "auth": {
    "type": "bearer",
    "token": "xxx"
  }
}

Output Format

┌─────────────────────────────────────────────────────┐
│ Resource Connection                                 │
├─────────────────────────────────────────────────────┤
│ Type: {resource_type}                               │
│ Status: Connected ✓                                 │
│ Host: {host}:{port}                                 │
├─────────────────────────────────────────────────────┤
│ Available:                                          │
│ • {database1}                                       │
│ • {database2}                                       │
└─────────────────────────────────────────────────────┘

Learning Integration

This skill supports FlowMind learning:

  • Connection Method: Learns preferred connection method
  • Default Database: Learns frequently used databases
  • Query Style: Learns query formatting preferences
  • Business Resource Binding: Learns MCP/address/token configuration by business context
User: "用 source_id 连接"
FlowMind: ✓ Learned: Use source_id for connections

User: [Next connection]
FlowMind: [Uses source_id automatically]

Example 3: Business Binding

User: 绑定零售业务 mcp=yapi-mcp 地址=https://yapi.example.com token=xxx project=retail

FlowMind:
✓ Saved learned binding for business: 零售

User: 同步零售业务接口到 YApi

FlowMind:
[Reuses learned YApi MCP/address/project binding automatically]

Examples

Example 1: Database Connection

User: 连接数据库查询用户表

FlowMind:
┌─────────────────────────────────────────────────────┐
│ Database Connection                                 │
├─────────────────────────────────────────────────────┤
│ Type: MySQL                                         │
│ Host: localhost:3306                                │
│ Database: mydb                                      │
│ Status: Connected ✓                                 │
├─────────────────────────────────────────────────────┤
│ Tables:                                             │
│ • users (1000 rows)                                 │
│ • orders (5000 rows)                                │
│ • products (200 rows)                               │
└─────────────────────────────────────────────────────┘

Example 2: Redis Operations

User: 查看 Redis 缓存状态

FlowMind:
┌─────────────────────────────────────────────────────┐
│ Redis Status                                        │
├─────────────────────────────────────────────────────┤
│ Host: localhost:6379                                │
│ Status: Connected ✓                                 │
│ Keys: 1,234                                         │
│ Memory: 45.2 MB                                     │
├─────────────────────────────────────────────────────┤
│ Recent Keys:                                        │
│ • user:123 (TTL: 3600s)                             │
│ • session:abc (TTL: 1800s)                          │
│ • cache:products (TTL: 300s)                        │
└─────────────────────────────────────────────────────┘

Configuration

{
  "resources": {
    "database": {
      "enabled": true,
      "type": "mysql",
      "connection": {
        "host": "localhost",
        "port": 3306,
        "database": "mydb"
      }
    },
    "redis": {
      "enabled": true,
      "connection": {
        "host": "localhost",
        "port": 6379
      }
    },
    "api": {
      "enabled": true,
      "baseUrl": "https://api.example.com"
    }
  }
}

Connection Methods

Direct Connection

{
  "method": "direct",
  "host": "localhost",
  "port": 3306
}

Source ID Connection

{
  "method": "source_id",
  "sourceId": "your-source-id"
}

Connection String

{
  "method": "connection_string",
  "url": "mysql://user:pass@host:3306/db"
}

Security

  • Passwords are encrypted at rest
  • Connections use TLS when available
  • Credentials are never logged
  • Connection pooling prevents exhaustion

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.