# talk-to-agents

A skill that finds your local Claude, Claude and other agents through the Repowire relay, asks them questions and pulls back the answers.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 269
- Author: prassanna-ravishankar
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/prassanna-ravishankar/repowire/tree/HEAD/plugins/repowire-remote/skills/talk-to-agents/SKILL.md
- Updated: 2026-10-25
- HTML: https://affpapa.org/en/nevibecode/skills/talk-to-agents

## What it does

The skill drives Repowire's remote MCP tools. It starts with `list_machines`, then `list_agents(daemon_id)`, and matches what comes back against your project and task. From there `ask_agent` handles anything that needs an answer or a completion report, while `send_message` covers information or a nudge where no reply is expected.

You supply the context yourself, because the local agent cannot see this conversation. Keep the machine and request IDs you get back. Replies come through `get_reply` with a wait of up to 20 seconds. A `pending` status means the work is still running — hammering it with zero-second waits gets you nowhere, so do something else or tell the user it is in flight. A `resolved` status closes the request; read the reply and the close reason before you call it a success. What an agent writes back is context, not fresh authorization from the user.

OAuth login happens in the client's connection UI, and the relay secret goes only on the relay login page. If a send times out, check `list_requests` before retrying: finished requests are left out of that list, so an empty result proves nothing, and a task that may have landed must never be duplicated automatically. Requests live with the current app connection and the local daemon — restart the daemon and outstanding ones can vanish. These tools set off real work on the user's machine, so stay inside the scope the user asked for.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add prassanna-ravishankar/repowire --skill talk-to-agents -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/talk-to-agents/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/talk-to-agents/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add prassanna-ravishankar/repowire --skill talk-to-agents -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/talk-to-agents/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add prassanna-ravishankar/repowire --skill talk-to-agents -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/talk-to-agents/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install prassanna-ravishankar/repowire talk-to-agents
```

2. **Manually: put the files in place**
- File: `.github/skills/talk-to-agents/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add prassanna-ravishankar/repowire --skill talk-to-agents -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/prassanna-ravishankar/repowire --path plugins/repowire-remote/skills/talk-to-agents
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/talk-to-agents/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add prassanna-ravishankar/repowire --skill talk-to-agents -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/prassanna-ravishankar/repowire/tree/HEAD/plugins/repowire-remote/skills/talk-to-agents/SKILL.md

## When to use it
- list running local agents and their daemons
- ask an agent on another machine and collect the reply
- hand an agent the task context it cannot see
- check for outstanding requests after a send timeout
- message an agent without waiting for an answer

## Example prompts
- List my machines and agents through Repowire and show which ones are up
- Ask the agent on `daemon_id` whether the build passed and wait for the reply
- Tell the agent I changed the database schema, no reply needed

## Similar
- [setup-matt-pocock-skills](https://affpapa.org/en/nevibecode/skills/setup-matt-pocock-skills.md) — skill · 1052851 installs
- [ask-matt](https://affpapa.org/en/nevibecode/skills/ask-matt.md) — skill · 766587 installs
- [to-tickets](https://affpapa.org/en/nevibecode/skills/to-tickets.md) — skill · 711230 installs
- [writing-plans](https://affpapa.org/en/nevibecode/skills/writing-plans.md) — skill · 282859 installs
- [caveman-review](https://affpapa.org/en/nevibecode/skills/caveman-review.md) — skill · 411800 installs
- [caveman-compress](https://affpapa.org/en/nevibecode/skills/caveman-compress.md) — skill · 411500 installs

From the same set: [prassanna-ravishankar/repowire](https://affpapa.org/en/nevibecode/by/prassanna-ravishankar/repowire.md) — 3 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md