Skip to content

skilldrop·docs·How-to

Use the Trackers pack

Install the Trackers pack, run its first task, and follow a typical session step by step.

For leads and PMs who run work in Jira, Linear or GitHub Projects: load a PRD into the tracker, triage the backlog, write the weekly status report, and check the tracker still matches the doc, all from an export or an MCP tool, with the numbers computed rather than estimated.

Reach for it when: A PRD has been agreed and the work is about to live in the tracker for weeks, and you want the tracker, the backlog and the weekly update to stay honest.

1. Install it

npx skilldrop-cli install --pack trackers                 # Claude Code, your user folder
npx skilldrop-cli install --pack trackers --project       # Claude Code, this repo
npx skilldrop-cli install --pack trackers --ide cursor    # or kiro, codex, antigravity, copilot
npx skilldrop-cli install --pack trackers --local         # this repo, hidden from git

In Claude Code you can also add the marketplace once (/plugin marketplace add sananthanarayan/skilldrop) and run /plugin install trackers@skilldrop.

It brings core with it, so the shared skills are there too.

2. Run the first task: triage your backlog before the next refinement session

Before you start:

Paste this into your agent:

Here's our backlog exported from Jira: ./backlog.csv. Refinement is Thursday. Find the duplicates, tell me what isn't ready to pull and why, and propose an order for what we take next. Anything without an update in 30 days counts as stale.

How to tell it worked: backlog-triage runs its script and reports exact counts (duplicate pairs, items with no owner or no acceptance criteria, stale and oversized items), names each duplicate pair with why they match, gives a reason for every position in the ordering, and ends with a change list you can apply.

If nothing happens: If the counts say "n/a", the script didn't find a column: rerun it with --map, e.g. --map owner="Team Lead". If backlog-triage doesn't activate, ask for it by name ("use backlog-triage").

3. A typical session

Bring:

A session takes about About 20 minutes for the import, then 10 to 15 minutes a week.

  1. tracker-brief-sync: Hand over the PRD and name your tracker. You get: A checked import file (Jira CSV, mapped CSV or gh commands) with one epic per goal and one story per requirement, each with acceptance criteria and a link back to its section. You decide: Import as is, or adjust the mapping first.
  2. backlog-triage: Before refinement, give it a fresh export of the backlog. You get: Exact counts, confirmed duplicate pairs, what isn't ready and why, priority conflicts, a reasoned ordering and a change list. You decide: Which changes to apply, and who owns the unowned items.
  3. team-status-report: Each week, give it the export, the period, the plan, and anything the tracker doesn't show about blockers. You get: A one-screen report: shipped, in progress, blocked with blocker and owner, slipped against plan, risks and asks, with a RAG status and the rule that set it.
  4. tracker-brief-sync: Mid-build or before launch, give it the PRD and a fresh export. You get: A drift report: requirements with no issue, issues with no requirement, issues pointing at removed sections, and issues for Won't-have items, each with both ways to resolve it. You decide: Change the tracker, or change the doc.

You end with: A tracker that traces back to the PRD, a groomed backlog, a weekly report built from counted numbers, and a record of where the plan and the work have drifted apart.

Next

Edit this page on GitHub · View source