Jira
Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.
$ npx claude-code-templates@latest --skill="ai-research/jira" --yesRequires Claude Code. The command adds this skill to your project's .claudedirectory — nothing runs on ToolZip's servers.
What's inside this skill
Component source
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 KEYorjira open KEY - MCP:
mcp__atlassian__jira_get_issuewith the key
Workflow
Creating tickets:- Research context if user references code/tickets/PRs
- Draft ticket content
- Review with user
- Create using appropriate backend
- Fetch issue details first
- Check status (careful with in-progress tickets)
- Show current vs proposed changes
- Get approval before updating
- Add comment explaining changes
Before Any Operation
Ask yourself:
- What's the current state? — Always fetch the issue first. Don't assume status, assignee, or fields are what user thinks they are.
- Who else is affected? — Check watchers, linked issues, parent epics. A "simple edit" might notify 10 people.
- Is this reversible? — Transitions may have one-way gates. Some workflows require intermediate states. Description edits have no undo.
- 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 call
lookupJiraAccountIdfirst, or assignment silently fails.
- NEVER edit description without showing original — Jira has no undo. User must see what they're replacing.
- NEVER use
--no-inputwithout all required fields (CLI) — Fails silently with cryptic errors. Check project's required fields first.
- NEVER assume transition names are universal — "Done", "Closed", "Complete" vary by project. Always get available transitions first.
- NEVER bulk-modify without explicit approval — Each ticket change notifies watchers. 10 edits = 10 notification storms.
Safety
- Always show the command/tool call before running it
- Always get approval before modifying tickets
- Preserve original information when editing
- Verify updates after applying
- Always surface authentication issues clearly so the user can resolve them
No Backend Available
If neither CLI nor MCP is available, guide the user:
To use Jira, you need one of:
1. **jira CLI** (recommended):
https://github.com/ankitpokhrel/jira-cli
Install: brew install ankitpokhrel/jira-cli/jira-cli
Setup: jira init
2. **Atlassian MCP**:
Configure in your MCP settings with Atlassian credentials.
Deep Dive
LOAD reference when:- Creating issues with complex fields or multi-line content
- Building JQL queries beyond simple filters
- Troubleshooting errors or authentication issues
- Working with transitions, linking, or sprints
- Simple view/list operations (Quick Reference above is sufficient)
- Basic status checks (
jira issue view KEY) - Opening issues in browser
| Task | Load Reference? |
|---|---|
| View single issue | No |
| List my tickets | No |
| Create with description | Yes — CLI needs /tmp pattern |
| Transition issue | Yes — need transition ID workflow |
| JQL search | Yes — for complex queries |
| Link issues | Yes — MCP limitation, need script |
References:
- CLI patterns:
references/commands.md - MCP patterns:
references/mcp.md
Related Claude Code Skills
Agents Langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
Agent Memory Systems
"Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm"
Ai Agents Architect
"Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling."
Prompt Engineering
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.
Context7 Auto Research
Automatically fetch latest library/framework documentation for Claude Code via Context7 API
Catalog data and component content are sourced from the open-source davila7/claude-code-templates project (MIT license). ToolZip curates the listing and writes original descriptions; every component links back to its original source. Claude Code is a product of Anthropic. ToolZip is an independent catalog and is not affiliated with or endorsed by Anthropic.