Atlassian Setup logo

Atlassian Setup

Community
davekilleen
atlassian-setup

Connect Jira and Confluence for project tracking and knowledge search. Use when the user says 'connect Jira', 'hook up Confluence', 'my tickets/board'. Not for a personal task app like Todoist/Things/Trello; use `todoist-setup`/`things-setup`/`trello-setup`.

Overview

Publisherdavekilleen
RepositoryDex
Skill nameatlassian-setup
Stars
481
Forks
130
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by davekilleen on GitHub. Read the source before you install it.

Installation

Install the Atlassian Setup AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/davekilleen/Dex.git /tmp/Dex
mkdir -p .claude/skills
cp -r /tmp/Dex/packages/dex-agent-plugin/skills/atlassian-setup .claude/skills/atlassian-setup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Atlassian Setup in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Atlassian Setup on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Atlassian Setup is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Atlassian Setup

Connect your Jira and Confluence to Dex so your daily plans, project health checks, meeting prep, and weekly reviews get richer context from your Atlassian workspace.

What This Enables

Once connected, Dex can:

  • Daily Plan: See your Jira sprint status, assigned tickets, and overdue items
  • Project Health: Sprint velocity, epic progress, blocked tickets across projects
  • Meeting Prep: Surface Jira tickets and Confluence docs relevant to attendees
  • Week Review: Tickets closed this week, sprint progress, velocity trends
  • Task Sync: Bi-directional sync between Dex tasks and Jira issues (optional)

Privacy

  • Dex reads Jira issues and Confluence pages on demand -- nothing is stored permanently
  • Data is fetched, summarized, and discarded after the session
  • Only YOUR workspace data is accessible (scoped to your OAuth permissions)
  • The OAuth token stays local on your machine and is gitignored

When to Run

  • User types /atlassian-setup
  • User asks about connecting Jira or Confluence
  • User wants Jira context in daily plans, project health, or meeting prep
  • During /integrate-mcp if Jira or Confluence is mentioned

Setup Flow

Step 1: Check if Already Connected

  1. Check System/integrations/config.yaml for atlassian.enabled: true
  2. If enabled, read System/.atlassian-oauth-token.json and test the token:
    • Call https://api.atlassian.com/oauth/token/accessible-resources with the stored token
    • If valid, skip to Step 6 (Configure Projects)
  3. If the token is missing, expired, or invalid, continue to Step 2

Step 2: Explain What We're Setting Up

Say:

**Let's connect Jira and Confluence to Dex.**

This uses Atlassian's OAuth flow to securely connect your Atlassian Cloud workspace.
No API tokens to manage -- it uses the standard Atlassian authorization flow.

**What you'll need:**
- An Atlassian Cloud account (e.g., yourcompany.atlassian.net)
- Permission to authorize third-party apps (check with your admin if unsure)
- About 3 minutes

**What gets connected:**
- **Jira:** Your assigned issues, sprint status, project health
- **Confluence:** Search for docs relevant to meetings and projects (read-only)

**Ready to go?**

Wait for confirmation.

Step 3: Add the Atlassian MCP Server

Check the user's MCP configuration. If an Atlassian MCP server is not listed:

  1. Explain what we're adding:
I need to add the Atlassian connector to your Dex configuration.

This uses the official Atlassian Remote MCP server which handles OAuth
authentication and provides secure access to your Jira and Confluence data.
  1. Add to the user's .mcp.json:
json
{
  "atlassian": {
    "command": "npx",
    "args": ["-y", "mcp-remote@latest", "https://mcp.atlassian.com/v1/sse"]
  }
}
  1. Tell the user the MCP server needs to restart for changes to take effect.

Step 4: Authenticate

Guide the user through the OAuth flow:

  1. The Atlassian MCP server will open a browser window for authorization
  2. User logs in to Atlassian and grants access
  3. The MCP server stores the token locally

After auth completes, verify:

  • Call the accessible-resources endpoint to confirm the token works
  • Save token data to System/.atlassian-oauth-token.json

If authentication succeeds:

Connected! I can see your Atlassian workspace: [workspace-name]

If it fails:

Hmm, that didn't work. A few things to check:

1. **Are you logged in to Atlassian Cloud?** (Not Server/Data Center -- Cloud only)
2. **Does your account have permission to authorize apps?** Check with your admin
3. **Try the auth flow again** -- sometimes it takes two tries

Want to retry?

Retry up to 2 times, then offer to skip and come back later.

Step 5: Select Cloud Site

If the user has access to multiple Atlassian sites:

You have access to multiple Atlassian sites:

1. acme-corp.atlassian.net
2. acme-sandbox.atlassian.net

Which site should Dex connect to?

Save the selected cloud_id for API calls.

Step 6: Configure Jira Project

**Which Jira project should Dex sync with?**

This is the project where your tasks and issues live. I'll use it for:
- Sprint status in your daily plan
- Task sync (if you enable it)
- Project health checks

**Enter a project key** (e.g., ACME, PROD, ENG) or say "show me what's available"

If they say "show me what's available":

  • Call the Jira projects API to list accessible projects
  • Show the list and let them pick

Step 7: Configure Confluence Space (Optional)

**Want to connect Confluence too?** (Optional)

If connected, Dex will search Confluence docs when prepping for meetings --
finding relevant pages shared with attendees or related to your projects.

**Enter a space key** (e.g., TEAM, DOCS, KB) or say "skip" or "show me what's available"

If they say "show me what's available":

  • Call the Confluence spaces API to list accessible spaces
  • Show the list and let them pick

Step 8: Configure Task Sync Trust Level

**How should Dex handle Jira task sync?**

When you create tasks in Dex or complete issues in Jira, Dex can keep them in sync.

Choose your trust level:

1. **Auto-sync** -- Dex automatically syncs issues and tasks (recommended for personal projects)
2. **Ask each time** -- Dex shows you what changed and asks before syncing
3. **Read-only** -- Dex reads Jira data but never writes back (safest)

Which do you prefer? [1/2/3]

Step 9: Save Configuration

Write to System/integrations/config.yaml -- update the atlassian section:

yaml
atlassian:
  enabled: true
  configured_at: YYYY-MM-DD
  cloud_id: <cloud-id>
  site_url: <site>.atlassian.net
  jira:
    project_key: ACME
    issue_type: Task
    task_sync: true
    trust_level: auto  # auto | ask | readonly
  confluence:
    enabled: true
    space_key: TEAM
  pillar_map:
    deal_support: SALES
    thought_leadership: CONTENT
    product_feedback: PROD
  features:
    daily_sprint: true
    project_health: true
    meeting_prep: true
    week_review: true

If the file already exists, only update the atlassian: section. Preserve other integration configs.

Step 10: Test the Connection

Run quick tests to confirm everything works:

  1. Jira: Fetch the configured project to verify access
  2. Jira: Search for issues assigned to the user
  3. Confluence (if enabled): Search the configured space

Show a brief summary:

**Quick test results:**
- Jira project [KEY]: Found, [N] open issues assigned to you
- Confluence space [KEY]: Found, [N] pages accessible
- Sprint status: [Current sprint name], [N] days remaining

Everything looks good!

If any test fails, troubleshoot before proceeding.

Step 11: Confirm

**Atlassian is connected!**

Here's what changes now:

- **Daily Plan** (`/daily-plan`) shows Jira sprint status and assigned tickets
- **Project Health** (`/project-health`) includes sprint velocity and blocked tickets
- **Meeting Prep** (`/meeting-prep`) surfaces Jira tickets and Confluence docs for attendees
- **Week Review** (`/week-review`) includes tickets closed and sprint progress

Trust level: [auto/ask/read-only]

You can adjust settings anytime by running `/atlassian-setup` again.

Capability Cascade

When Atlassian is connected, these skills automatically gain new powers:

SkillWhat Atlassian Adds
/daily-planSprint status, assigned tickets, overdue issues
/project-healthSprint velocity, epic progress, blocked tickets
/meeting-prepJira tickets involving attendees, Confluence docs
/week-reviewTickets closed, sprint velocity, progress trends
/triageIncoming Jira issues to triage alongside inbox

Troubleshooting

Token Expired

Atlassian OAuth tokens expire periodically. If you see auth errors:

  1. Run /atlassian-setup
  2. It will detect the expired token and guide you through re-auth
  3. Takes about 30 seconds

"No accessible resources"

Your Atlassian account may not have the right permissions:

  • You need at least read access to the Jira project
  • For Confluence, you need read access to the space
  • Check with your Atlassian admin if you're missing permissions

Rate Limiting

Atlassian Cloud allows about 100 requests per minute. If you see rate limit errors, wait 60 seconds and retry. This rarely happens during normal use.

"Atlassian MCP not found"

The server might not be in your configuration. Re-run /atlassian-setup and it will detect and fix this.

Jira Server / Data Center

This integration only supports Atlassian Cloud. Jira Server and Data Center use different APIs and authentication. If you're on-premise, this setup won't work.


Reconfiguration

If the user runs /atlassian-setup when already configured:

  1. Check current status by testing the token
  2. Show current config from System/integrations/config.yaml
  3. Offer options:
    • Change Jira project
    • Change Confluence space
    • Update trust level
    • Update pillar mapping
    • Re-authenticate (if token expired)
    • Disconnect Atlassian

Disconnect Flow

If user wants to disconnect:

  1. Update System/integrations/config.yaml:
    yaml
    atlassian:
      enabled: false
  2. Confirm: "Atlassian is disconnected. Your daily plans and meeting prep will no longer include Jira/Confluence context. Run /atlassian-setup anytime to reconnect."

Frequently asked questions

What does the Atlassian Setup AI skill do?

Connect Jira and Confluence for project tracking and knowledge search. Use when the user says 'connect Jira', 'hook up Confluence', 'my tickets/board'. Not for a personal task app like Todoist/Things/Trello; use `todoist-setup`/`things-setup`/`trello-setup`.

Why use Atlassian Setup on TypingMind?

Because you install it once and use it with any model. Atlassian Setup is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Atlassian Setup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davekilleen/Dex/tree/main/packages/dex-agent-plugin/skills/atlassian-setup. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Atlassian Setup?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Atlassian Setup?

As many as you like. As long as a model supports skills, you can use Atlassian Setup with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Atlassian Setup AI skill free?

It is published on GitHub by davekilleen. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇