── SKILL
launch-plan✓ APPROVED

Ship the launch with assets done and owners named.

Builds a tiered go-to-market launch plan sized to what the release actually deserves.

Inside: The tiering, the audiences, channel-to-asset mapping, a back-planned timeline, and win metrics.

01 / HOW TO USE

Install it in one line, or paste it in.

1
In Claude Code (one command)
Copy the install line, paste it into your terminal, and restart Claude Code. The skill installs itself to ~/.claude/skills/ and runs automatically when it is relevant.
2
In Claude, ChatGPT, or a Project (no terminal)
Open the file, then upload it to your chat or paste its contents in. A skill is just a markdown file of instructions, so any capable AI can follow it.
New to skills? A skill is a plain-text file that teaches your AI a workflow. Point any capable assistant at it and it follows the steps, on your data.
02 / MAKE IT YOURS

Connect your context. Set it to your motion.

CONNECT YOUR CONTEXT · AND WHY IT HELPS
a CRM or a marketing tool

it sizes real audience segments and picks the channels that reached them last time.

a web-analytics tool

it sets baseline metrics from your real traffic, so the win condition is grounded, not guessed.

a content or social tool

it can slot the assets into a real publishing calendar instead of a static list.

SET IT TO YOUR MOTION

This was built for a B2B product team shipping features and products. Set these to your stack:

Pick the tier honestly. A T3 feature dressed as a T1 launch burns the team and the audience's attention. The skill recommends a tier and tells you why.

Set thisWhat it isExample
WHATthe thing you are launchinga featurea producta rebrand
TIERthe size of the pushT1 majorT2 standardT3 minor
AUDIENCESwho needs to hear itexisting usersprospectspress
CHANNELSwhere you will reach thememailblogsocialin-appsales
CRMyour audience-data connectora CRMa marketing tool
ANALYTICSyour web-analytics connectora web-analytics tool
LEAD_TIMEdays from kickoff to launch14 (re-tune to the tier)
03 / THE FULL SKILL

Everything the skill does, in full.

── WHAT THIS DOES

Turns "we are shipping something" into a plan someone can run. It sizes the launch to a tier, then fills in the audiences to reach, the channels to reach them, the assets each channel needs, a timeline with a real launch day, the owner for every piece, and the handful of metrics that decide whether it worked. No orphaned tasks, no launch day where the assets are not done.

── THE METHOD
  1. 1
    Tier the launch (T1 / T2 / T3)

    First decision, everything follows from it. T1 is a major bet: full channel push, sales enablement, press. T2 is a standard feature: email, blog, social, in-app. T3 is a minor update: changelog and one in-app note. The skill recommends a tier from WHAT and lets you override.

  2. 2
    Audiences

    Names who needs to hear it, in priority order: existing users who benefit today, prospects it unblocks, and internal teams (sales, support) who field the questions. Real segment sizes when a CRM is connected, named segments when not.

  3. 3
    Channels and assets

    Maps each audience to the channels that reach them, and each channel to the exact asset it needs: the email, the blog post, the social thread, the in-app note, the sales one-pager. Every asset has a channel and every channel has an audience. Nothing floats.

  4. 4
    Timeline and owners

    Back-plans from launch day across LEAD_TIME: asset drafts, reviews, a go or no-go, launch, and follow-up. Every item has a named owner. An unowned task is flagged before it becomes a launch-day surprise.

  5. 5
    Win metrics

    Two or three metrics that decide success, matched to the tier and the goal: adoption of the feature, signups from the campaign, pipeline influenced. Baselines come from a connected analytics tool, or are labeled "set a baseline" when none is connected. A launch with no win condition is just noise.

── QUALITY GATES
  • Every asset has a channel, an owner, and a due date before launch day. No orphans.
  • The tier is stated and justified. A T3 does not get a T1 budget.
  • Win metrics are named up front, with a baseline or a clear "set a baseline" flag.
  • Illustrative audience sizes and metric targets are marked as examples, never presented as your real data.
── OUTPUT (EXAMPLE)
EXAMPLE OUTPUT
LAUNCH PLAN · shipping: bulk-export feature · recommended tier: T2

Audiences (priority):
  1. Existing power users (benefit today)
  2. Prospects who asked for export
  3. Support + sales (will field questions)

Channels -> assets -> owner -> due:
  Email      release note to power users     PMM    L-2
  Blog       how-to with screenshots         PMM    L-3
  In-app     tooltip on the export button    PM     L-1
  Social     3-post thread                   PMM    L-day
  Sales      one-pager + talk track          PMM    L-2

Timeline (LEAD_TIME 14):
  L-14 kickoff  ->  L-5 drafts done  ->  L-2 review + go/no-go
  ->  L-day ship  ->  L+7 follow-up post

Win metrics (T2):
  - Feature adoption among power users (set a baseline)
  - Export-related tickets down (set a baseline)

Next: connect a CRM to size the power-user segment for real.
── EXAMPLE CHAT
EXAMPLE CHAT
You
We're shipping a bulk-export feature in three weeks. Build the launch plan.
CLAUDE
Tiered it T2, timeline backward-planned from launch day. Channels -> assets -> owner -> due: Email release note to power users PMM L-2 Blog how-to with screenshots PMM L-3 In-app tooltip on export button PM L-1 Win metrics: feature adoption among power users (set a baseline) The catch worth naming: I tiered this T2, not T1, because a bulk-export feature reaching existing power users doesn't need a press push, and a T3 would starve it of the sales one-pager it actually needs to field support questions. Getting the tier wrong either burns the team on a small feature or leaves a real one under-resourced. One sharpener: connect a web-analytics tool so the adoption metric has a real baseline instead of "set a baseline" sitting there as a placeholder.
04 / GO FURTHER

Where an operator takes this next.

The plan is step one. Here is where an operator takes it once the manual version proves out.

You built the plan once, now the system tracks whether it worked.

01
Track every asset to done, automatically

Sync the owner-and-due list into Linear or Asana so L-2 and L-3 deadlines show up where the team already works, not just in this doc.

02
Pull real segment sizes

Connect Salesforce or HubSpot so "existing power users" becomes an actual count instead of a named-but-unsized audience.

03
Grade the launch after the fact

Run a scheduled Claude task at L+14 that pulls the win metrics from Amplitude and reports whether the launch actually hit, so the next tier call is calibrated on results, not gut feel.

05 / PART OF A BIGGER PLAY

One skill is the on-ramp.

── GET NEW SKILLS IN YOUR INBOX

One operator-built skill a week. Free.