home / skills / composiohq / awesome-claude-skills / atlassian-automation

atlassian-automation skill

safe

/atlassian-automation

This skill automates Atlassian tasks via Rube MCP, discovering current tool schemas before execution to ensure up-to-date tooling and safe workflows.

npx playbooks add skill composiohq/awesome-claude-skills --skill atlassian-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.9 KB

---
name: atlassian-automation
description: "Automate Atlassian tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Atlassian Automation via Rube MCP

Automate Atlassian operations through Composio's Atlassian toolkit via Rube MCP.

**Toolkit docs**: [composio.dev/toolkits/atlassian](https://composio.dev/toolkits/atlassian)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Atlassian connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `atlassian`
- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas

## Setup

**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `atlassian`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. Confirm connection status shows ACTIVE before running any workflows

## Tool Discovery

Always discover available tools before executing workflows:

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "Atlassian operations", known_fields: ""}]
session: {generate_id: true}
```

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

## Core Workflow Pattern

### Step 1: Discover Available Tools

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Atlassian task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["atlassian"]
session_id: "your_session_id"
```

### Step 3: Execute Tools

```
RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"
```

## Known Pitfalls

- **Always search first**: Tool schemas change. Never hardcode tool slugs or arguments without calling `RUBE_SEARCH_TOOLS`
- **Check connection**: Verify `RUBE_MANAGE_CONNECTIONS` shows ACTIVE status before executing tools
- **Schema compliance**: Use exact field names and types from the search results
- **Memory parameter**: Always include `memory` in `RUBE_MULTI_EXECUTE_TOOL` calls, even if empty (`{}`)
- **Session reuse**: Reuse session IDs within a workflow. Generate new ones for new workflows
- **Pagination**: Check responses for pagination tokens and continue fetching until complete

## Quick Reference

| Operation | Approach |
|-----------|----------|
| Find tools | `RUBE_SEARCH_TOOLS` with Atlassian-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `atlassian` |
| Execute | `RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs |
| Bulk ops | `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` |
| Full schema | `RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef` |

---
*Powered by [Composio](https://composio.dev)*

Overview

This skill automates Atlassian tasks by orchestrating Composio’s Atlassian toolkit through a Rube MCP server. It provides a reliable pattern for discovering tool schemas, managing connections, and executing operations while avoiding common pitfalls. The workflow emphasizes always searching tools first and verifying connection status before executing actions.

How this skill works

The skill queries RUBE_SEARCH_TOOLS to discover available Atlassian tool slugs, input schemas, and recommended plans. It then ensures an active Atlassian connection via RUBE_MANAGE_CONNECTIONS and runs operations with RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk jobs), always including a memory object and reusing session IDs across the workflow. It also supports fetching full schemas with RUBE_GET_TOOL_SCHEMAS when schemaRef is available.

When to use it

Automating repetitive Atlassian tasks like issue creation, updates, or project management.
Building agent-driven workflows that must adapt to changing tool schemas.
Running bulk operations across Jira or Confluence via Composio tooling.
Orchestrating multi-step processes that require session state and pagination handling.
Integrating Claude-based agents with Atlassian via an MCP endpoint.

Best practices

Always call RUBE_SEARCH_TOOLS first to get current tool slugs and exact input schemas.
Verify the Atlassian connection status with RUBE_MANAGE_CONNECTIONS and follow auth links if not ACTIVE.
Include an explicit memory object (even empty) in RUBE_MULTI_EXECUTE_TOOL calls.
Reuse session IDs for a single workflow and generate new ones for separate workflows.
Respect schema field names and types exactly; do not hardcode arguments.
Handle pagination tokens in responses and continue fetching until complete.

Example use cases

Create or update Jira issues using the discovered issue-management tool slug and schema.
Bulk migrate pages in Confluence using RUBE_REMOTE_WORKBENCH and run_composio_tool().
Build an agent that checks connection health, searches tools, and applies label/tag changes across projects.
Retrieve full tool definitions with RUBE_GET_TOOL_SCHEMAS before constructing complex payloads.
Automate recurring report generation by chaining multi-execute tool calls within a session.

FAQ

Do I need API keys to use Rube MCP?

No API keys are required; add https://rube.app/mcp as an MCP server in your client configuration.

What if a tool schema changes mid-workflow?

Always call RUBE_SEARCH_TOOLS at the start of a workflow and before executing new steps to fetch the current schema; do not rely on cached slugs or argument shapes.