atlassian-automation
by ComposioHQatlassian-automation is a Claude skill for Workflow Automation with Atlassian via Composio Rube MCP. It guides agents to install Rube MCP, verify an active Atlassian connection, run RUBE_SEARCH_TOOLS first, and execute Jira or Atlassian tasks using current schemas.
This skill scores 70/100, which means it is acceptable for directory listing but should be presented as a lightweight MCP workflow guide rather than a fully packaged automation skill. Directory users get enough evidence to understand when to install it—Atlassian operations through Rube MCP with live tool discovery—but should expect limited built-in examples and no supporting files beyond the main SKILL.md.
- Clear activation scope: the description and prerequisites identify Atlassian automation through Composio/Rube MCP and require searching current tool schemas first.
- Provides a usable setup path, including adding the Rube MCP endpoint, checking `RUBE_SEARCH_TOOLS`, and managing an Atlassian connection before execution.
- Includes a repeatable workflow pattern for discovery, connection checking, and schema-aware execution, reducing guesswork compared with a generic Atlassian prompt.
- No support files, examples, scripts, or README are provided beyond SKILL.md, so adoption depends on the agent interpreting the written workflow correctly.
- The skill delegates much of the operational detail to live Rube tool discovery, which is flexible but leaves fewer concrete Atlassian task examples for users evaluating fit.
Overview of atlassian-automation skill
What atlassian-automation does
atlassian-automation is a Claude skill for running Atlassian operations through Composio’s Rube MCP server. It is designed for workflows where the agent must first discover the current Atlassian tool schema, verify an active Atlassian connection, and then execute Jira or related Atlassian tasks with less guesswork than a plain prompt.
Best-fit users and jobs
This skill is best for teams that already use Atlassian products and want an AI agent to help with operational tasks such as issue lookup, ticket updates, project maintenance, or workflow-driven Atlassian actions. It fits users who are comfortable authorizing an external MCP connection and who need repeatable automation rather than one-off text advice.
Key differentiator: tool discovery first
The main value of the atlassian-automation skill is not a fixed list of hardcoded Atlassian commands. It instructs the agent to call RUBE_SEARCH_TOOLS first so it can retrieve current tool slugs, input schemas, execution plans, and pitfalls from Rube MCP. That matters because Composio tool schemas can change, and guessing fields is a common cause of failed automation.
Adoption considerations
You need Rube MCP available in your client and an active Atlassian connection through RUBE_MANAGE_CONNECTIONS with toolkit atlassian. The repository for this skill is intentionally minimal: the primary source is SKILL.md, with no extra scripts, rules, or reference files. Install it when you want a compact MCP workflow pattern; avoid it if you need a full Atlassian business-process library.
How to Use atlassian-automation skill
atlassian-automation install context
Install from the Composio skill collection:
npx skills add ComposioHQ/awesome-claude-skills --skill atlassian-automation
Then add Rube MCP as a server in your client configuration using:
https://rube.app/mcp
The skill requires the MCP capability rube. Before expecting useful output, confirm that RUBE_SEARCH_TOOLS responds. Next, use RUBE_MANAGE_CONNECTIONS with toolkit atlassian; if the connection is not ACTIVE, complete the returned authorization flow.
Inputs the skill needs
A weak prompt such as “update Jira” leaves too much unresolved. Provide the Atlassian product area, task goal, identifiers, constraints, and desired safety behavior.
Stronger prompt pattern:
Use the atlassian-automation skill. First call
RUBE_SEARCH_TOOLSfor the current schema. I need to update Jira issuePROJ-184by changing status toIn Progress, adding the comment “Backend investigation started,” and assigning it to[email protected]. Check the Atlassian connection before execution. If any field or transition is unavailable, stop and explain the missing requirement instead of guessing.
This gives the agent enough context to discover the right tools, validate schemas, and avoid unsafe assumptions.
Practical workflow for reliable usage
A good atlassian-automation usage flow is:
- Ask the agent to invoke the atlassian-automation skill explicitly.
- Require
RUBE_SEARCH_TOOLSbefore any Atlassian action. - Reuse the session ID returned by tool discovery when running follow-up steps.
- Confirm the Atlassian connection is
ACTIVE. - Execute the smallest safe action first, especially for updates or bulk changes.
- Ask for a short execution summary with changed entities and unresolved items.
For read-only tasks, the agent can usually proceed after schema discovery. For write operations, include whether it should ask for confirmation before modifying issues, comments, statuses, assignees, or project data.
Repository files to read first
Start with composio-skills/atlassian-automation/SKILL.md. It contains the entire operational model: prerequisites, Rube MCP setup, tool discovery, and the core workflow pattern. There are no README.md, rules/, resources/, references/, or helper scripts in this skill folder, so do not expect additional local examples. If you need broader toolkit details, use the linked Composio Atlassian toolkit documentation from the skill.
atlassian-automation skill FAQ
Is atlassian-automation only for Jira?
The skill targets Composio’s Atlassian toolkit through Rube MCP, so the exact available operations depend on the tools returned by RUBE_SEARCH_TOOLS. Many users will apply it to Jira-style tasks, but the safe answer is to discover available Atlassian tools at runtime rather than assuming a fixed product list.
How is this better than an ordinary prompt?
A normal prompt may invent tool names or use stale input fields. The atlassian-automation skill tells the agent to discover current schemas first, check connection state, and follow the returned execution plan. That makes it more suitable for live Atlassian operations where field names, transitions, and permissions matter.
Is it beginner-friendly?
It is beginner-friendly if Rube MCP is already configured by your organization. New users should know that this is not a standalone Atlassian app and not a no-auth automation bot. It depends on an MCP-capable client, Rube availability, and an authorized Atlassian connection.
When should I not use this skill?
Do not use it for tasks requiring hidden business rules that are not expressed in the prompt, bulk destructive changes without review, or environments where external MCP access is not allowed. Also avoid it if you only need Atlassian strategy advice; the skill is most useful when the agent can actually call Rube MCP tools.
How to Improve atlassian-automation skill
Improve atlassian-automation prompts
Better results come from turning business intent into executable constraints. Include issue keys, project keys, target fields, allowed changes, confirmation rules, and fallback behavior. For example, “move all stale tickets” is risky; “find issues in project OPS with status Blocked and no update in 14 days, then draft a proposed comment without posting it” is safer and easier to validate.
Prevent common failure modes
The most common failures are skipped tool discovery, inactive Atlassian connection, guessed schemas, missing issue identifiers, and unclear write permissions. Prevent them by telling the agent: “Search tools first, verify connection, do not infer required field values, and ask before making write changes.” This aligns directly with the skill’s Rube-first design.
Iterate after the first output
After the first run, ask for the tool slug used, key input fields, entities touched, and any skipped actions. If the result is wrong, refine the next prompt with the exact schema fields or tool recommendations returned by RUBE_SEARCH_TOOLS. For repeated workflows, save a prompt template that includes your project keys, naming conventions, and approval policy.
Extend the skill for team use
Teams can improve the atlassian-automation skill by adding local guidance around their Atlassian workflow: status transition rules, required custom fields, ticket naming conventions, safe bulk limits, and when human approval is mandatory. Keep those additions separate from schema assumptions, because the skill should still rely on Rube MCP discovery for current tool definitions.