agentleFS
ejwhite7ejwhite7/product-release-checklist/skills/launch-messaging/SKILL.md

launch-messaging

Skill0 starsChanged 35 days agoMITView on GitHub

Write a launch's message house (feature name, one-liner, job-to-be-done, pillars with proof, objections, limits, CTAs per audience) in the release checklist studio. It's the single source every launch asset is written from. Use for "Write message house" requests, or when someone asks for positioning or "how do we talk about this feature".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Job first: Write the job in the customer's words, not the product's.

    line 18
  2. Very specific:

    Pillars: No more than 3. Each pillar needs proof: a number, a quote or a 5-second demo moment.

    line 21
  3. Distinctive:

    CTAs: Write separate CTAs for prospects, eligible customers, ineligible-plan users and churned users.

    line 24
  4. Very specific:

    Leave status: "draft". The user approves in the Messaging tab, and approving completes the message-house item.

    line 27
  5. Distinctive:

    If the message house was already approved and you change it, say in chat which assets need redrafting.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Launch Messaging

Fills message in the launch JSON. Every asset is generated from it, so make it sharp before anything else.

Inputs

  • The launch brief, and the company context file (ICP, voice, words to avoid)
  • The project's .claude/product-marketing-context.md, if it exists
  • The PRD or spec, beta feedback, support tickets, feature requests (from links in brief.links, or ask)
  • How competitors name and pitch the same capability (use web search if it's available)

Method

  1. Job first. Write the job in the customer's words, not the product's. "Get paid faster without chasing clients", not "invoicing automation".
  2. The real competitor is what users do today (brief.alternative). Write before and after against it.
  3. One-liner. Draft 5 candidates of 12 words or fewer, outcome-first. Put the best in oneLiner and list the other four in chat.
  4. Pillars. No more than 3. Each pillar needs proof: a number, a quote or a 5-second demo moment. If you don't have proof, leave proof empty. The studio flags it; don't invent it.
  5. Objections. The top 5, including the company-specific ones (price, AI trust, "will it break what I have?", switching cost).
  6. Feature name. It should be plain-language, searchable and translatable. If the current name fails, put alternatives in chat.
  7. CTAs. Write separate CTAs for prospects, eligible customers, ineligible-plan users and churned users.
  8. Limits. What it doesn't do yet, said honestly. Support needs this more than marketing does.

Leave status: "draft". The user approves in the Messaging tab, and approving completes the message-house item. If the message house was already approved and you change it, say in chat which assets need redrafting.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.