ReddRadar
Agent skill
jira-refinement
This skill should be used for Jira backlog refinement via text conversation. It pulls non-ready tickets, facilitates requirements discussion, and marks tickets ready when complete.
Install this agent skill to your Project
npx add-skill https://github.com/kazamatzuri/claude-settings/tree/main/skills/jira-refinement
SKILL.md
Jira Ticket Refinement
Interactive backlog refinement workflow to prepare Jira tickets for sprint planning.
Purpose
Facilitate ticket refinement sessions by pulling non-ready tickets from the backlog, discussing requirements with the user, updating ticket fields, and marking tickets ready when complete.
When to Use
- User requests backlog refinement or ticket grooming
- User wants to review non-ready tickets
- User mentions "refine", "groom", or "ready" in context of tickets
- User says "let's refine the backlog" or "start ticket refinement"
Workflow
Fetch Backlog
cd ~/.claude/skills/jira-refinement && source .venv/bin/activate && python scripts/jira_api.py get-backlog --limit 5
Get Ticket Details
cd ~/.claude/skills/jira-refinement && source .venv/bin/activate && python scripts/jira_api.py get-ticket PROJ-123
Display Format
Present each ticket as:
## PROJ-123: [Summary]
**Status:** Backlog | **Priority:** Medium | **Epic:** PROJ-100
**What it's about:** [Brief colloquial description]
**What's missing:** [Missing fields - acceptance criteria, story points, etc.]
Commands
| User Says | Action | Script |
|---|---|---|
| "Save it" / "Done" / "Ready" | Transition to Ready | transition PROJ-123 --to Ready |
| "Won't do" / "Close it" | Close ticket | transition PROJ-123 --to Done --resolution "Won't Do" |
| "Update description to [text]" | Update description | update-ticket PROJ-123 --description "text" |
| "Set story points to N" | Set estimate | update-ticket PROJ-123 --story-points N |
| "Set priority to [level]" | Set priority | update-ticket PROJ-123 --priority High |
| "Move down N" | Rerank in backlog | move-rank PROJ-123 --down N |
| "Link to [epic]" | Link to epic | link-epic PROJ-123 EPIC-456 |
| "Add comment: [text]" | Add discussion note | add-comment PROJ-123 "text" |
| "Open in browser" | View in Jira | python scripts/display_ticket.py PROJ-123 |
| "Next" / "Skip" | Next ticket | - |
| "End session" | Stop | - |
All script commands run from the skill directory with venv activated:
cd ~/.claude/skills/jira-refinement && source .venv/bin/activate && python scripts/jira_api.py [command]
Ready Ticket Requirements
Before marking a ticket "Ready", load and verify against references/ticket-template.md. A ticket needs:
- Clear problem statement
- Acceptance criteria (outcomes, not tasks)
- Appropriate priority
- Labels and blockers identified
Critical Rules
Use the correct command for each operation:
| Operation | Correct | WRONG |
|---|---|---|
| Mark ready | transition --to Ready |
|
| Update description | update-ticket --description |
|
| Close ticket | transition --to Done |
- NEVER use
add-commentfor status changes or field updates - Comments are ONLY for discussion notes
- NEVER read or check .env files - scripts handle config automatically
- DO NOT write any files - open tickets in browser instead
Error Handling
| Error | Resolution |
|---|---|
| 401 Unauthorized | Credentials may be expired. Ask user to verify their Jira API token. |
| Transition not found | Run get-ticket to see available transitions for that ticket's current state. |
| Field update fails | Some fields may be read-only or require specific values. Check Jira project configuration. |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
kazamatzuri/claude-settings
python-nix-uv
Set up Python projects using nix/direnv with uv for environment management. Use when creating new Python projects, initializing Python environments, or when the user wants automatic Python virtual environment setup with nix flakes.
kazamatzuri/claude-settings
domain-driven-design
This skill should be used whenever domain modeling is taking place. It provides specialized guidance for type-driven and data-driven design based on Rich Hickey and Scott Wlaschin's principles. The skill helps contextualize current modeling within the existing domain model, identifies inconsistencies, builds ubiquitous language, and creates visualizations (Mermaid, Graphviz/DOT, ASCII diagrams) to communicate domain concepts clearly. Use this skill when designing types, modeling business domains, refactoring domain logic, or ensuring domain consistency across a codebase.
kazamatzuri/claude-settings
skill-improver
This skill should be used at natural checkpoints (after completing complex tasks, at session end, or when friction occurs) to reflect on skill and process execution and identify targeted improvements. Use when experiencing confusion, repeated failures, or discovering new patterns that should be codified into skills for smoother future operation.
kazamatzuri/claude-settings
bevy
This skill should be used when working on Bevy game engine projects. It provides specialized knowledge for Bevy's Entity Component System (ECS) architecture, component-driven design patterns, system ordering, UI development, build strategies, and common pitfalls. Use this skill when implementing game features, debugging Bevy code, designing component architectures, or working with Bevy's UI system.
kazamatzuri/claude-settings
strudel
This skill should be used when working with Strudel.cc, a live-coding music environment. Use when creating musical patterns, drum sequences, melodies, basslines, or generative compositions. The user will always want to run Strudel code in the browser, either by copy-pasting or by providing a clickable URL with the code encoded in base64.
kazamatzuri/claude-settings
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Didn't find tool you were looking for?