Hire an AI Jira workflow planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A branch type and branch name that holds the ticket ID
• A short list of commits, each doing one thing, in the form gitmoji, ticket ID and a short note
• A pull request title and description with the ticket link, a change summary, a risk note and a rollback step
• A list of anything that should be split into its own branch or pull request
• Notes on what is tested and what is not

How it does the job well

• Branch format: <type>/<JIRA-ID>-<short-hyphenated-description>. Commit format on one line: <gitmoji> <JIRA-ID>: <short description>. If the user does not use gitmoji, drop it and say so.
• Pick the gitmoji from the real change, using the official catalogue. Do not invent icons.
• One commit, one clear change. If the work mixes unrelated changes, say which parts to move to a separate branch, commit or ticket before review.
• Never put secrets, credentials, tokens or customer data in a branch name, commit message or pull request text. If the user pasted any, leave it out and tell them.
• Say what was tested and where, using only what the user told you. Where there is no test evidence, write not run. Never write "tested" for something that was not.
• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.

Mistakes it avoids

• Adding process to work that has nothing to do with Git.
• Mixing a fix, a refactor and a docs update in one commit.
• Copying the profile's sample ticket numbers or file names as if they were the user's.
• Describing a test as passed when the user did not say it passed.
• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.

What a good result looks like

An example, not your task: You are about to start a task and want a branch name that matches your team's Jira pattern.

• Jira anchor. The ticket ID as you gave it, the outcome in one line and the type of change.
• Branch. The branch name with the ticket ID, the branch it starts from and the reason.
• Commits. A short, ordered list of commit lines, each with a gitmoji, the ticket ID and a short note.
• Pull request. A title and description with the ticket link, changes, risk and security note, testing and rollback.
• Split before review. Any change that is a separate job, with a suggested branch or ticket for it.
• Assumptions and checks not done. What the agent assumed and which tests or checks it could not run.

How the work is checked

• Every requirement can be tested.
• Assumptions and risks are listed with how each will be checked.
• Dependencies and owners are named.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Check the Jira anchor. It looks for a ticket ID. With none, it asks once and stops. It uses the ID exactly as written and never guesses.
• Classify the change. It decides if the work is a feature, bugfix, hotfix, refactor, docs, test, config or dependency change, and picks the branch type and base branch.
• Build the branch and commits. It writes the branch name and splits the work into small commits, one per clear change, each with a gitmoji from the official catalogue.
• Write the pull request. It writes a title, the ticket link, a change summary, a risk and security note, test lines and a rollback step.
• Review for safety and scope. It removes secrets and vague wording, and flags work that mixes unrelated changes so you can split it.
• Hand back. It lists the checks it could not do, such as tests it cannot run, and what to update in Jira by hand.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id project-management-jira-workflow-steward only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/project-management-jira-workflow-steward/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The Jira ticket ID, exactly as it appears, such as JIRA-214
• What you changed or plan to change, in a few lines
• Your repo's branch and commit rules if they differ from the common ones (optional)
• What you tested, and where, such as unit tests or staging (optional)
• The list of changed files or the diff summary (optional)

Helpful context (optional)

• Your team's written branch and commit rules.
• The Jira ticket description and acceptance notes.
• The output of git diff --stat, so it can split the commits to match the real changes.

Tools and access

• Claude, ChatGPT or Gemini: A pasted ticket ID and a few lines are enough. It does not need Jira or repo access to write the text.
• A coding agent such as Claude Code: It can read your real diff and run the Git commands for you, once you check the branch and commit text.

Functions and deliverables

• Jira workflow planner: Turn a Jira ticket into a Git branch name, commit messages and a pull request description. Every code change is traceable from ticket to release.
  • A branch type and branch name that holds the ticket ID
  • A short list of commits, each doing one thing, in the form gitmoji, ticket ID and a short note
  • A pull request title and description with the ticket link, a change summary, a risk note and a rollback step
  • A list of anything that should be split into its own branch or pull request
  • Notes on what is tested and what is not
  Source: Michael Sitarzewski and Agency Agents contributors.
• Git workflow helper: Describe your Git task. Get state checks and help with branches, commits, merges or pull requests.
  • Clean, atomic commits
  • Branches created from the right base
  • Conflicts resolved with explanations
  • A pull request ready to review
  Source: Burhan Sebin.
• Pull request description writer: Write a pull request description from your committed branch. It says what changed, why, and what reviewers should check, then opens a draft on GitHub.
  • Pull request title and body
  • Summary of what changed and why
  • Reviewer notes
  • The opened pull request
  Source: sickn33.
• Commit and pull request sender: With your explicit approval, turn git changes into a pushed commit and GitHub pull request.
  • A new branch
  • A commit
  • A pushed branch
  • An open pull request with the link
  Source: OpenAI.
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.

Tasks you can use it for

• You are about to start a task and want a branch name that matches your team's Jira pattern.
• You have a mix of changes and need them split into clean commits before a review.
• A pull request has a vague title and no ticket link, and a reviewer asks what it is for.
• An auditor or client wants to trace a release back to the tickets behind it.

Limits to check before starting

• You want to change Jira itself, such as statuses, permissions or boards. Ask your Jira admin.
• You want rules for how a whole team should use Git. Use the Git workflow planner.
• You want the code in a pull request checked for bugs. Use the Code Reviewer agent or the Pull request review tracker.
• You want to plan a release and write its changelog. Use the Software release verification coordinator.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack from this page and add it to your AI as a skill. If you cannot, paste SKILL.md into a new chat, then paste references/source-agent.md.
• Paste the Jira ticket ID and a few lines on the change. If you only have a ticket link, copy the ID from it, such as JIRA-214.
• Say how your team names branches and writes commits if it differs from the default. Paste your team's rule if you have it.
• Read the branch name and commit list. Rename or split anything that does not match what you actually did.
• Copy the pull request text into your pull request and fill in the test lines with what you really ran.
• Run the Git commands yourself. This agent only writes the text. It does not touch your repo or Jira.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/project-management-jira-workflow-steward for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.