Jira
Talk to Jira in natural language—view, create, transition, assign issues, and check sprint or backlog status via CLI or Atlassian MCP.
Overview
Jira is an agent skill most often used in Build (also Operate iterate) that connects natural-language requests to Jira issues through the jira CLI or Atlassian MCP backends.
Install
npx skills add https://github.com/softaworks/agent-toolkit --skill jiraWhat is this skill?
- Mandatory backend detection: jira CLI first, then Atlassian MCP tools, else setup guidance
- CLI quick reference for view, list, create, move, assign, and unassign issues
- Triggers on jira, issue, ticket, sprint, backlog, and PROJ-123-style keys
- Supports filter patterns such as my in-progress issues via jira me
- Split reference docs for CLI commands versus MCP usage
- 3-tier backend detection order: CLI, MCP, then setup guidance
- 8 CLI intents documented in the quick-reference table
Adoption & trust: 538 installs on skills.sh; 2k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You mention a ticket key or sprint in chat but your agent cannot fetch status, update transitions, or file issues without you context-switching to the browser.
Who is it for?
Solo or tiny teams standardizing on Jira who want issue keys, sprints, and backlog queries inside Claude Code, Cursor, or Codex.
Skip if: Builders without a Jira site or those who refuse CLI/MCP setup when neither backend is available.
When should I use this skill?
User mentions Jira issues (e.g. PROJ-123), tickets, sprints, backlog, or asks to create, view, update, or manage Jira workflow.
What do I get? / Deliverables
Issues are viewed, listed, created, moved, and assigned from the agent session using the detected CLI or MCP backend.
- Updated Jira issue records
- Issue lists filtered by assignee or status
- Newly created issues with type, summary, and description
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Primary shelf is Build + PM because issue and sprint management is how most solo builders track implementation work during active development. PM covers ticket workflow, assignments, and sprint visibility—the exact intents in the quick-reference command table.
Where it fits
Create a story and assign it to yourself before starting a feature branch.
Pull the latest comment thread on a production bug key while fixing an incident.
Transition launch-blocker tickets and list what is still In Progress before release day.
How it compares
Jira workflow integration via CLI or MCP—not a standalone issue tracker or Linear replacement skill.
Common Questions / FAQ
Who is jira for?
Developers and solo founders who already use Jira Cloud and want ticket operations from their AI coding agent instead of only the web UI.
When should I use jira?
During Build when creating or updating implementation tickets and checking sprint scope; during Operate when triaging production issues; whenever conversation includes issue keys or words like sprint, backlog, or ticket.
Is jira safe to install?
It can run shell commands and call external Atlassian APIs with your credentials—review the Security Audits panel on this Prism page and scope tokens minimally.
SKILL.md
READMESKILL.md - Jira
# Jira Natural language interaction with Jira. Supports multiple backends. ## Backend Detection **Run this check first** to determine which backend to use: ``` 1. Check if jira CLI is available: → Run: which jira → If found: USE CLI BACKEND 2. If no CLI, check for Atlassian MCP: → Look for mcp__atlassian__* tools → If available: USE MCP BACKEND 3. If neither available: → GUIDE USER TO SETUP ``` | Backend | When to Use | Reference | |---------|-------------|-----------| | **CLI** | `jira` command available | `references/commands.md` | | **MCP** | Atlassian MCP tools available | `references/mcp.md` | | **None** | Neither available | Guide to install CLI | --- ## Quick Reference (CLI) > Skip this section if using MCP backend. | Intent | Command | |--------|---------| | View issue | `jira issue view ISSUE-KEY` | | List my issues | `jira issue list -a$(jira me)` | | My in-progress | `jira issue list -a$(jira me) -s"In Progress"` | | Create issue | `jira issue create -tType -s"Summary" -b"Description"` | | Move/transition | `jira issue move ISSUE-KEY "State"` | | Assign to me | `jira issue assign ISSUE-KEY $(jira me)` | | Unassign | `jira issue assign ISSUE-KEY x` | | Add comment | `jira issue comment add ISSUE-KEY -b"Comment text"` | | Open in browser | `jira open ISSUE-KEY` | | Current sprint | `jira sprint list --state active` | | Who am I | `jira me` | --- ## Quick Reference (MCP) > Skip this section if using CLI backend. | Intent | MCP Tool | |--------|----------| | Search issues | `mcp__atlassian__searchJiraIssuesUsingJql` | | View issue | `mcp__atlassian__getJiraIssue` | | Create issue | `mcp__atlassian__createJiraIssue` | | Update issue | `mcp__atlassian__editJiraIssue` | | Get transitions | `mcp__atlassian__getTransitionsForJiraIssue` | | Transition | `mcp__atlassian__transitionJiraIssue` | | Add comment | `mcp__atlassian__addCommentToJiraIssue` | | User lookup | `mcp__atlassian__lookupJiraAccountId` | | List projects | `mcp__atlassian__getVisibleJiraProjects` | See `references/mcp.md` for full MCP patterns. --- ## Triggers - "create a jira ticket" - "show me PROJ-123" - "list my tickets" - "move ticket to done" - "what's in the current sprint" --- ## Issue Key Detection Issue keys follow the pattern: `[A-Z]+-[0-9]+` (e.g., PROJ-123, ABC-1). When a user mentions an issue key in conversation: - **CLI:** `jira issue view KEY` or `jira open KEY` - **MCP:** `mcp__atlassian__jira_get_issue` with the key --- ## Workflow **Creating tickets:** 1. Research context if user references code/tickets/PRs 2. Draft ticket content 3. Review with user 4. Create using appropriate backend **Updating tickets:** 1. Fetch issue details first 2. Check status (careful with in-progress tickets) 3. Show current vs proposed changes 4. Get approval before updating 5. Add comment explaining changes --- ## Before Any Operation Ask yourself: 1. **What's the current state?** — Always fetch the issue first. Don't assume status, assignee, or fields are what user thinks they are. 2. **Who else is affected?** — Check watchers, linked issues, parent epics. A "simple edit" might notify 10 people. 3. **Is this reversible?** — Transitions may have one-way gates. Some workflows require intermediate states. Description edits have no undo. 4. **Do I have the right identifiers?** — Issue keys, transition IDs, account IDs. Display names don't work for assignment (MCP). --- ## NEVER - **NEVER transition without fetching current status** — Workflows may require intermediate states. "To Do" → "Done" might fail silently if "In Progress" is required first. - **NEVER assign using display name (MCP)** — Only account IDs work. Always