Eric Santos

Relay To Agent

AI 智能体v0.0.2
作者:Eric Santos更新于 2026-07-04共 3 个版本 · 最新版本发布于 2026-07-04relay-to-agent@clawhub_ericsantos/relay-to-agent
多 Agent 协作上下文管理工具调用

据 AlphaMoat 统计,截至 2026-09,Relay To Agent 累计下载 3,872 次、获 6 个星标,在全部 5,078 个 AI 技能中排名第 2,685 位,在「AI 智能体」分类(969 个)中排名第 531 位。

累计安装
172
累计下载
3,872
星标
6
全站排名
#2,685
全站前 53% · 「AI 智能体」前 55%
平台累计安装累计下载星标评论
ClawHub ↗1213,7956-
SkillHub ↗1723,8726—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

主文支持列出 agent、发送消息、重置会话和多轮交互。提示词及保留的会话历史会发送到所配置的第三方端点,历史可能以本地明文保留;确认端点可信、使用 HTTPS,避免发送秘密或受监管数据。 需要 Node、已配置的 agent 和 RELAY_API_KEY。会话转录会以本地明文持久保留,并非仅临时上下文;不需保留时用 --reset 或删除会话文件。发送前确认目标端点和会外传的历史内容。

资料发布于 2026-10-27

可以用来做什么

  • 整理待发送给 agent 的任务提示
  • 检查会话上下文和重置需求
  • 比较不同兼容端点的数据处理要求

什么时候用

  • 需要把任务转交给配置好的 agent 时
  • 发送前核实端点、数据范围和历史保留方式时

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

检查这段提示是否包含秘密或受监管数据,并说明目标端点和会话保留风险;不要发送消息。

月度数据趋势

累计下载3,872
2,6123,2893,9652026-03 · 累计下载 2,7052026-05 · 累计下载 3,1132026-06 · 累计下载 3,2332026-07 · 累计下载 3,5402026-08 · 累计下载 3,6812026-09 · 累计下载 3,87226-0326-09
星标6
5672026-03 · 星标 62026-05 · 星标 62026-06 · 星标 62026-07 · 星标 62026-08 · 星标 62026-09 · 星标 626-0326-09

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。

月份累计下载环比星标
2026-093,872—6
2026-083,681+4.0%6
2026-073,540+9.5%6
2026-063,233+3.9%6
2026-053,113—6
2026-032,705—6

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

3.3 KB · ClawHub v0.0.2
---
name: relay-to-agent
description: "Relay messages to AI agents on any OpenAI-compatible API. Supports multi-turn conversations with session management. List agents, send messages, reset sessions."
homepage: https://platform.openai.com/docs/api-reference/chat
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["node"]},"primaryEnv":"RELAY_API_KEY"}}
---

# Relay To Agent

Send messages to AI agents on any OpenAI-compatible endpoint. Works with Connect Chat, OpenRouter, LiteLLM, vLLM, Ollama, and any service implementing the Chat Completions API.
展开全部(共 100 行)

## List available agents

```bash
node {baseDir}/scripts/relay.mjs --list
```

## Send a message to an agent

```bash
node {baseDir}/scripts/relay.mjs --agent linkedin-alchemist "Transform this article into a LinkedIn post"
```

## Multi-turn conversation

```bash
# First message
node {baseDir}/scripts/relay.mjs --agent connect-flow-ai "Analyze our latest campaign"

# Follow-up (same session, agent remembers context)
node {baseDir}/scripts/relay.mjs --agent connect-flow-ai "Compare with last month"
```

## Reset session

```bash
node {baseDir}/scripts/relay.mjs --agent linkedin-alchemist --reset "Start fresh with this article..."
```

## Options

| Flag | Description | Default |
|------|-------------|---------|
| `--agent ID` | Target agent identifier | (required) |
| `--reset` | Reset conversation before sending | off |
| `--list` | List available agents | — |
| `--session ID` | Custom session identifier | `default` |
| `--json` | Raw JSON output | off |

## Configuration

### agents.json

Configure agents and endpoint in `{baseDir}/agents.json`:

```json
{
  "baseUrl": "https://api.example.com/v1",
  "agents": [
    {
      "id": "my-agent",
      "name": "My Agent",
      "description": "What this agent does",
      "model": "model-id-on-the-api"
    }
  ]
}
```

### Environment variables

```bash
export RELAY_API_KEY="sk-..."          # API key (required)
export RELAY_BASE_URL="https://..."    # Override base URL from config
export RELAY_CONFIG="/path/to/agents.json"  # Custom config path
```

## Compatible Services

- **Connect Chat** — `api.connectchat.ai/api`
- **OpenRouter** — `openrouter.ai/api/v1`
- **LiteLLM** — `localhost:4000/v1`
- **vLLM** — `localhost:8000/v1`
- **Ollama** — `localhost:11434/v1`
- **Any OpenAI-compatible API**

## Session Management

Sessions are stored locally at `~/.cache/relay-to-agent/sessions/`. Each agent+session combination keeps up to 50 messages. Use `--session` for parallel conversations with the same agent.

`--agent` and `--session` values are restricted to `[A-Za-z0-9._-]`; path separators and `..` are rejected so session files stay inside the cache directory.

## Privacy Notice

This skill is a **relay**: each message you send — plus prior session history — is transmitted to the configured OpenAI-compatible endpoint (`baseUrl` / `RELAY_BASE_URL`), which may be a third-party service. Conversation transcripts (up to 50 messages per session) are also **persisted in plaintext** on disk at `~/.cache/relay-to-agent/sessions/`.

- Do not send secrets, credentials, or regulated/sensitive data unless you trust the endpoint and control the machine.
- Use `--reset` to clear a session before sending, or delete files under the cache dir to remove stored history.
- Point `baseUrl`/`RELAY_BASE_URL` only at endpoints you trust.

「AI 智能体」分类下的热门技能

Eric Santos 的其他技能

数据月份:2026-09 · 下载/星标/安装数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。