---
title: "Distributed Skills — One Playbook, Every Agent | AgentRQ"
url: https://agentrq.com/features/distributed-skills
description: "Agent skills live in AgentRQ, not in a directory on one machine. Agents find and load them over MCP, so every agent in every workspace runs the same current playbook."
---

Human-in-the-Loop Task Manager for AI Agents

Distributed Skills

# One Playbook Every Agent Loads

A skill is a playbook an agent follows when a task matches it. Keep yours in AgentRQ instead of in a directory on one machine, and every agent — any model, any workspace, any computer — loads the same current version. Nothing to copy, nothing to keep in sync.

app.agentrq.com/workspaces/.../settings

![The Skills tab in AgentRQ workspace settings, showing a workspace's skills as a grid of cards with their descriptions and sizes, each stamped with the GitHub repository and commit it was imported from](https://agentrq.com/assets/feature-distributed-skills-poster.png)

The Skills tab in workspace settings. These came from one GitHub link — every skill stamped with the commit it was imported from.

## How It Works

Four skill tools on the workspace MCP server, and an agent that fetches only what the task needs.

1

### The Agent Searches First

Every agent that connects is told to call **searchSkills** at the start of a task. It gets names and descriptions — enough to choose, not enough to cost context.

2

### It Loads Only What Matches

**loadSkill** fetches one file. The checklist a skill mentions in step one arrives in step one — not before, and never for a skill this task did not need.

3

### It Writes Back What It Learned

When an agent finds a better way, **saveSkill** puts it in the workspace's own skill — so the next agent starts from the improvement instead of rediscovering it.

## Shared, Not Copied

Share a skill with another workspace in your account and it is not duplicated — the other workspace reads the same skill, live. Fix a step once and every workspace it is shared with is already correct, because there was only ever one of them.

Only the workspace that owns a skill can change or delete it; everywhere else it is read-only. That is the difference between a shared playbook and five playbooks that agree for now.

![A skill's own page in settings, showing its SKILL.md with clickable references to preflight.md and rollback.md, its file tree, and the workspaces it can be shared with, billing-web ticked](https://agentrq.com/assets/feature-distributed-skills-skill.png)

![The GitHub import picker for a repository too large to import whole, listing its skills with checkboxes and sizes, one greyed out with the reason its SKILL.md exceeds the 96 KiB limit](https://agentrq.com/assets/feature-distributed-skills-import.png)

## Bring the Skills You Already Have

It is the same `SKILL.md` format Claude Code and Antigravity use, so your existing skills work unchanged. Paste a public GitHub link in **Settings → Skills** and import a whole repository or a single skill's folder. Plugin manifests are honoured.

A repository too large to take whole is listed instead: tick the skills you want and only their files are downloaded. The import report names everything it skipped and why — a size, a binary, a name already taken — because an import that quietly brings in most of something is worse than one that refuses.

## Why It Matters

Playbooks that belong to your work rather than to whichever laptop happened to write them.

### One Current Version

Editing the skill is the deployment. There is no second step where the fix reaches the machines — they ask each time.

### Keep As Many As You Need

Procedures in a config file tax every task. A skill the task does not match costs its one-line description and nothing else.

### Any Machine, Any Model

Laptop, office box, a task firing at 3am. Same workspace, same skills, nothing installed in anyone's home directory.

### They Get Better

Agents write improvements back, so your playbooks ratchet forward instead of resetting to zero every task.

Clear limits, refused rather than truncated. A `SKILL.md` holds up to 96 KiB, every other file up to 64 KiB of UTF-8 text, and a skill up to 64 files. Anything over is rejected with a message saying what to change — a playbook silently cut in half is one with the last step missing. Skill content is stored on the AgentRQ server, in a local directory or an S3-compatible bucket of your choosing, with only metadata in the database. Sharing is limited to workspaces in the same account.

Free During Beta

## Stop Copying Playbooks Around

Connect an agent to a workspace and it has the skill tools already. Ask it what skills the workspace has, then give it one.

More Features

[Workspace Memory Notes that outlive the task](https://agentrq.com/features/workspace-memory) [MCP Integration One config line, every tool](https://agentrq.com/features/mcp-integration) [Workspaces One per repo, client or project](https://agentrq.com/features/workspace)