Jira Workflow Kit
From your terminal. From your phone.
AI and humans develop together.
$ claude → /develop
🎤 "Run standup"
The gap between business and engineering
Hard to get right
BAs, Product Owners, and stakeholders know what they want — but writing well-structured, testable acceptance criteria takes time and expertise
Slow feedback loops
Weeks between requirement → implementation → review. Stakeholders lose context, developers lose momentum
Idle capacity
Approved tickets sit in the backlog. Developer machines idle 16 hours a day. Time zones don't align.
AI and humans develop together
Jira Workflow Kit bridges business and engineering.
AI structures requirements, writes code, runs tests — humans review, co-develop, and steer.
Nothing happens without human approval.
Human in the loop — always
Describes requirements
Provides the idea in natural language. AI structures it into a proper Epic with testable acceptance criteria.
Reviews & prioritizes
Validates stories in Jira. Adjusts scope, adds comments, refines criteria. Sets status to "Approved" when ready.
Comments & validates
Reviews tickets in Jira at any time. Leaves feedback. AI processes it via /feedback and adjusts the plan.
Executes approved work
Only touches code after explicit approval. Plans, implements, tests, creates PRs — all traceable in Jira.
No coding without approval. The "Approved" status is the gate. AI never bypasses it.
From requirement to PR
$ /idea "Customers need two-factor authentication on login"
→ AI analyzes codebase, creates Epic + Stories in Jira
→ PO reviews, stakeholders comment, team approves in Jira
$ /plan PROJ-42
→ Deep code analysis, creates implementation subtasks
$ /develop PROJ-42
→ Implements subtask by subtask
→ Commits, pushes, updates Jira — each step
$ /qa PROJ-42
→ Tests against acceptance criteria, creates PR
→ Human reviews and merges
Your Jira board — always in sync
AI and human developers work on the same board. Labels separate projects. Status updates are automatic.
Every decision documented in Jira
AI and human — side by side
The workflow integrates into your existing Jira process.
Developers and AI work on the same board, same branch, same conventions.
Handles via /develop
- Reads the subtask from Jira
- Implements following codebase patterns
- Runs tests, commits, pushes
- Updates Jira with full audit trail
Works alongside AI
- Picks up subtasks from the board
- Implements with full context
- Same branch, same conventions
- AI handles the rest in parallel
AI augments your team — it doesn't replace it. Humans stay in the driver's seat.
/autopilot
The team goes home. AI keeps working.
Plans, develops, tests, creates PRs — overnight.
What it does
- Picks up approved tickets
- Creates sprints automatically
- Plans → develops → QA → PR
- Runs projects in parallel (one agent per repo)
- Pipelines within a project: plans next ticket while developing current
When stuck
- Documents the question in Jira
- Parks the ticket for team review
- Moves to the next ticket
- Sleeps through rate limits
- Never guesses — asks via Jira
Meridiem
All of this — from your iPhone.
The engine runs on your server. You steer it from anywhere.
iPhone → Jira
User describes a feature. AI creates a structured Epic with 6 stories. Ready for review.
Human feedback → AI adjusts
PO comments in Jira
"Automatic promotions should be in scope"
AI processes feedback
Adjusts scope, updates 4 stories, expands acceptance criteria. No code yet — ready for re-approval.
Real conversation. Real adjustments. All documented in Jira.
Talk to your development workflow
Standard Mode
Full Claude Code power with voice I/O. Deep analysis, MCP tools, multi-turn conversations.
"Run standup" → full sprint briefing, spoken back
Realtime Mode
Sub-second voice-to-voice via OpenAI Realtime API. Quick lookups, status checks, natural conversation.
"What's the status of MVP-42?" → answer in <1 second
From your car. From your couch. From a walk.
Development oversight without opening a laptop.
Two interfaces, one engine
One Jira board with labels for project separation. Multi-project, multi-repo.
Terminal for power users. iPhone for oversight on the go.
11 skills, full lifecycle
| Command | Purpose | Mode | 📱 |
|---|---|---|---|
| /idea | Structure requirements → Epic + Stories in Jira | Interactive | ✓ |
| /feedback | Process stakeholder feedback from Jira comments | Interactive | ✓ |
| /plan | Codebase analysis → implementation subtasks | Interactive | ✓ |
| /develop | Implement subtask by subtask with auto-push | Interactive | ✓ |
| /qa | Test, validate acceptance criteria, create PR | Interactive | ✓ |
| /bug | Investigate root cause, quick-fix or ticket | Interactive | ✓ |
| /autopilot | Autonomous overnight development | Autonomous | ✓ |
| /standup | Morning briefing with overnight summary | Read-only | ✓ |
| /status | Sprint overview or ticket detail | Read-only | ✓ |
| /deploy | Build, test, deploy a project | Interactive | ✓ |
| /retro | Sprint wrap-up + learning capture | Interactive | ✓ |
Every skill works from both Terminal and iPhone. Same engine, same results.
Jira is the single source of truth
Every change tracked
Each commit links to a subtask. Each subtask has a Jira comment with what was done, files changed, and test results.
Status always current
Ticket status updates at every phase transition. No stale boards, no "forgot to move the card." Stakeholders see real-time progress.
Decisions documented
Even in autopilot mode, every decision is logged as a Jira comment. Full audit trail for compliance and review.
Your existing Jira workflows, boards, and permissions stay intact.
The kit plugs in — it doesn't replace your process.
The AI gets better over time
Every session builds on the last. The AI remembers architecture decisions, user preferences,
debugging patterns, and project conventions — permanently.
Persistent Memory
Memory files survive across sessions. Architecture patterns, tech stack details, known issues — always available.
MEMORY.md
diemcrm.md
working-style.md
debugging.md
/retro captures learnings
After each session, the AI analyzes what worked, what was painful, and updates its memory with verified insights.
✓ Debug solutions saved
✓ Preferences recorded
✓ Noise filtered out
/feedback closes the loop
Human corrections in Jira are processed and incorporated. The AI adjusts plans, requirements, and code — learning what matters.
→ plan adjusted
→ next time: done right
Context accumulates
Each /plan builds codebase understanding. Each /develop follows discovered patterns. Knowledge compounds.
Session 5: knows patterns
Session 20: moves like a team member
Before vs. After
Without
- BAs write vague requirements manually
- Requirements lost in translation
- Weeks from idea to working code
- Jira status always outdated
- No work happens outside business hours
- Every session starts from zero
With Workflow Kit + Meridiem
- AI helps BAs write structured, testable tickets
- Codebase-aware acceptance criteria
- Hours from approval to PR
- Jira always in sync, automatically
- Autopilot develops overnight
- Persistent memory across sessions
- Oversee everything from your phone
PRs ready for review — by morning
develop from feature/PROJ-42-login-2fa
- Add TOTP-based two-factor authentication to customer login flow
- QR code enrollment endpoint for initial 2FA setup
- Recovery codes fallback (8-character codes per PO feedback)
- ☑ Unit tests: 12 new, all passing
- ☑ Integration tests: 4 new, all passing
- ☑ Acceptance criteria validated (5/5)
Wake up to /standup
$ /standup
Good morning. Here's what happened:
Autopilot overnight:
Completed: PROJ-42, PROJ-43, PROJ-44
Parked: PROJ-45
Sprint: 3/5 done, 1 parked
Recent: 11 commits across 2 projects
Built on proven tools, with guardrails
Engine
- Claude Code CLI (Anthropic)
- Jira via Model Context Protocol
- Native Git operations
- Any tech stack — learns your patterns
Mobile
- Native iOS (SwiftUI)
- Node.js backend (Express 5)
- WebSocket streaming
- OpenAI Realtime API + TTS/STT
- Docker deployment
Safety
- No coding without "Approved" status
- Never force-push or delete branches
- Tests mandatory before completion
- Stops after 3 consecutive failures
- Full audit trail in Jira comments
Your team + AI. Together, faster.
Approved tickets don't have to wait.
Not for morning. Not for the next sprint.
Not for you to be at your desk.
PRs ready by morning.
"Run standup"
Review from anywhere.
github.com/diem2001/jira-workflow-kit
Commit:
a3f8c21Files: src/auth/totp-enrollment.ts, src/routes/auth.ts
Tests: 4 new, all passing