jira-ticket-creator
Skill24 starsChanged 9 months agoMITView on GitHub
Create Jira tickets from meeting notes, user stories, or quick lists. Use this skill when: - User says "create tickets", "make Jira tickets from", "push to Jira" - User has meeting action items to convert to tickets - User has user stories from a spec to push to the backlog - User wants to batch-create tasks, stories, or bugs
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- create-skillSkill
- sync-skillsSkill
- better-waySkill
- confluence-to-mdSkill
- diagram-generatorSkill
- draft-emailSkill
- md-to-confluenceSkill
- presentation-builderSkill
- teach-meSkill
- youtube-transcriptSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 64
Always confirm before creating
- Distinctive: line 69
Don't create tickets without user confirmation
- Distinctive: line 70
Don't guess assignees — ask if unclear
- Distinctive: line 71
Don't create more than 15 tickets at once
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Jira Ticket Creator
Parse any input into structured Jira tickets. Works with meeting action items, user stories from specs, or free-text lists.
Input Sources
- Meeting action items
- User stories from spec files
- Free-text lists ("Create tickets for: X, Y, Z")
- Sprint planning output
Field Mapping
| Field | Source | Default |
| Summary | First line or action item text | Required |
| Description | Context, acceptance criteria if available | Empty |
| Type | Infer from content | Story |
| Priority | From context | Medium |
| Story Points | Estimate from complexity | Blank |
| Assignee | Match name to team directory | Unassigned |
| Epic | Link if specified in input | None |
| Sprint | Specified or current sprint | Current |
Type inference:
- Contains "bug", "fix", "broken", "error" -> Bug
- Contains "investigate", "research", "spike" -> Task
- Everything else -> Story
Workflow
- Parse — extract individual ticket items from input
- Enrich — add type, priority, assignee, epic from context
- Present — show ticket table to user for confirmation
- Confirm — user reviews, edits, approves
- Create — create tickets via Jira REST API
- Log — report created tickets with keys
Confirmation Format
| # | Summary | Type | Priority | Assignee | Points | Epic |
|---|---------|------|----------|----------|--------|------|
| 1 | Implement feature X | Story | High | [name] | 5 | [Epic] |
| 2 | Fix login bug | Bug | Medium | [name] | 1 | [Epic] |
Total: 2 tickets, 6 story points
Proceed? (y/n/edit)Rules
- Maximum 15 tickets per batch (split larger lists)
- Always confirm before creating
- Show total story points in confirmation
Anti-Patterns
- Don't create tickets without user confirmation
- Don't guess assignees — ask if unclear
- Don't create more than 15 tickets at once
Quality Checklist
- Every ticket has a clear summary
- Type correctly inferred or specified
- User confirmed before creation
- Total story points shown
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.