Use tracker-brief-sync

Turn a brief or PRD (such as prd-draft output) into tracker-ready epics and issues

Turn a brief or PRD (such as prd-draft output) into tracker-ready epics and issues — title, description, acceptance criteria, labels and a link back to the doc section — as a CSV for Jira, a mapped CSV for other importers, or gh commands for GitHub; and in reverse, report drift between the doc and the tracker (issues with no section, sections with no issue, issues for Won't-have requirements).

Reach for it when the user wants to load a PRD into Jira, Linear or GitHub, says "create tickets from this brief", or asks "does the tracker still match the PRD?".

Install it

npx skilldrop-cli install tracker-brief-sync                 # Claude Code, your user folder
npx skilldrop-cli install tracker-brief-sync --project       # Claude Code, this repo
npx skilldrop-cli install tracker-brief-sync --ide cursor    # or kiro, codex, antigravity, copilot

It is part of the Trackers pack: --pack trackers installs it with its neighbours.

It ships scripts, so it needs Python 3 (standard library only, nothing to install). What they may touch is declared in its manifest.

Ask for it

Say it the way you would to a colleague. Requests like these route to it:

• "Turn this PRD into Jira epics and stories as a CSV I can import"
• "Create GitHub issues from this brief, each linked back to the section it came from"
• "Does our Linear project still match the PRD? Find tickets with no requirement and requirements with no ticket"
• "Load the guest checkout requirements into our tracker with acceptance criteria and labels"

Requests like these belong to a different skill, so it shouldn't answer them:

• "Draft a PRD for guest checkout from these interview notes"
• "Break the guest checkout epic into thin vertical slices with a build order"
• "Find duplicates and stale items in our Jira backlog"

If another skill answers instead, ask for this one by name: "use tracker-brief-sync".

Check what you get

A good result:

• Every issue links back to its doc section with a Source line the drift check can read.
• Every story has acceptance criteria that restate the doc's requirement, testably, without adding behaviour.
• Won't-have requirements and non-goals produce no issues, and are listed as not created.
• The import file passes the spec check before it's handed over, and comes with the import steps for the user's tracker.
• Drift names each item and what happened, from the issue's own text or status, with both ways to resolve it.
• The doc and the tracker are treated as equals. Drift is a disagreement, not proof the tracker is wrong.
• Nothing is invented: no requirements, numbers, owners or reasons that aren't in the doc or the export.

See a worked example

• guest checkout sync
• prd guest checkout

Use something else when

• Writing the PRD itself; use prd-draft, then bring its output here
• Slicing one epic into stories with a build order; use user-story-splitter
• Cleaning up an existing backlog (duplicates, stale items, ordering); use backlog-triage

Next

• SKILL.md, the instructions the agent reads
• Its page on the site
• Related: backlog-triage, prd-draft, user-story-splitter

Edit this page on GitHub · View source