Set up
Try a plugin
The Product Management plugin ships with /stakeholder-update as a starting point, already structured to pull at-risk and blocked items from your tools and report green, yellow, or red. If your admin manages plugins and it's not available yet, skip this step. The prompt below works with the skill or without it.
/stakeholder-updateWrite a status update for your audience, with blockers pulled from your tracker and chat/metrics-reviewInvestigate a sudden spike or drop in a metric and compare it against targetsConnect your tools
Claude is more powerful when it works directly with your systems. You control permissions and access. Learn about tool access(opens in new tab).
Add a connector(opens in new tab) for each tool you want Claude to use.
Set your working folder
Drag the files you'll use (the PRD, the GTM brief, the launch checklist template, the retros from your last two launches) into one folder on your machine, then give Claude access to it(opens in new tab) in the Claude desktop app. Claude reads from it and writes the readiness checklist back to it. If you run launches regularly, create a project(opens in new tab) from that folder so your checklist template, prior retros, and memory stay attached.
The prompt
Copy this into Claude
Sweep launch readiness for the saved-views launch. Produce the launch checklist with status and owner per item, give a red/yellow/green readiness call overall, name the blockers, and note anything that matches what went well or wrong in our last two launches.
Why this works
Give it every source at once. PRD, epic, Slack, and GTM brief each hold a different slice of the truth; sweeping them at once is what catches the item that's "done" in Linear but still being argued in the channel.
Ask for an owner on every line. A checklist with a name on every line is actionable in launch standup; a checklist without owners is a wish list.
Ask for a verdict with reasons. Asking for an overall red/yellow/green forces a judgment, and "name the specific blockers" means yellow comes with the two things that have to clear, not a vibe.
Compare against your own history. Pointing Claude at your past retros lets it check this launch against what's gone wrong before. Otherwise it's evaluating in isolation.
Get a better draft
Add an example to match. Drop an example you like into the folder and Claude matches your structure and voice.
Ask it to flag uncertainty. Add "flag anything you're not confident about" so you know where to look first when you review the draft.
Make Claude work for you
Tell Claude your own rules for this task, such as your checklist owners and your color criteria, then save what you've done as a skill of your own. A few minutes of conversation and it runs with your standards from then on.
Make what we've done in this task so far into a skill called /launch-sweep.
Review the skill, and save it if Claude hasn't already.
Make it repeatable
Run it daily during launch week
Readiness changes by the hour in the final stretch. Ask Claude to set up a scheduled task, or open Scheduled in the sidebar, and /launch-sweep writes a fresh checklist every morning of launch week so standup opens with the current picture.
Set up a scheduled task for every weekday at 8am through Sep 3: run /launch-sweep for the saved-views launch and write the checklist to Launches/saved-views as readiness-<date>.md, with a one-line color change vs yesterday.
Runs /launch-sweep against the PRD, Linear epic, Slack channel, and GTM brief and writes the dated checklist with the overall color to the launch folder.
To use a folder on your computer during a scheduled task, keep your computer on and awake with the Claude desktop app open so Claude can access it.
Share with your teammates
Your /launch-sweep skill now carries your checklist template, your owners, and your color criteria. Share it so every launch lead runs the same sweep, and the go/no-go meeting reads one consistent format no matter which feature is shipping.