agentleFS
Sign inStart free
ejwhite7ejwhite7/product-release-checklist/skills/launch-assets/SKILL.md

launch-assets

Skill0 starsChanged 35 days agoMITView on GitHub

Draft launch assets in the release checklist studio from the message house. Covers the founder announcement, video script, social posts, employee kit, creator briefs, in-app copy, banner, landing page, changelog, KB article, YouTube tutorial, webinar, paid ads, lifecycle emails, app store copy, and the support, CS and internal packs. Use for "Draft assets" requests, or when someone asks for launch copy.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If they're installed, use these skills for voice and craft:

    line 16
  2. Distinctive:

    lifecycle: every non-adopter email exits on the activation event.

    line 33
  3. Very specific:

    Add UTMs to every CTA URL using measure.utm, with utm_content set to the asset id.

    line 36

≈ “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 Assets

Writes Markdown drafts into assets.<id>.body, and sets status: "draft" and updatedBy: "claude". Draft only the assets the request lists, or every asset for the tier that has no body yet. ASSETS in studio/model.mjs gives each asset's spec, its tier and the checklist item it completes. Read that spec, then apply the craft notes below.

The message is the source. If message.status isn't approved, draft anyway, but open each body with > Based on an unapproved message house. Never introduce a claim that isn't in the pillars' proof.

If they're installed, use these skills for voice and craft:

  • human-first-writing for all copy
  • engaging-writing for the founder post
  • website-and-ad-copywriter for ads and the landing page
  • ugc-video-script-writing for creator briefs
  • customerio-in-app-components when the client's in-app tool is Customer.io

Craft notes by asset

  • founder-announcement: the beehiiv product-update format.
    • An outcome-led headline, then a short personal opening: why we built it, what we heard from customers.
    • For each feature: a benefit subhead, 2–4 sentences, a [VISUAL: …] placeholder, who it's for, and a deep-link CTA.
    • Close with what's next and a sign-off.
    • Match the founder voice samples in the context file. Put the outcome before the mechanism. No internal names.
  • social-founder / social-company: one native post per platform the ICP actually uses. The context file says which. If the ICP isn't on X or LinkedIn, say so and weight toward TikTok, IG, YouTube and Facebook.
  • in-app: include targeting (eligible plans only) and a frequency cap, plus an ineligible-plan upsell variant when the feature is gated.
  • kb-article: one task per article, eligibility first, written so the AI support bot (often Intercom Fin) can answer from it.
  • paid-ads: separate hooks per audience. Exclude users who've already activated from the adoption ads.
  • lifecycle: every non-adopter email exits on the activation event. Exclude the holdout from every send.
  • support-pack / cs-pack: state the limitations plainly, and include the exact ticket tag.

Add UTMs to every CTA URL using measure.utm, with utm_content set to the asset id.

Consistency check (always run it after drafting)

Re-read every draft against message. Fix any draft that adds a claim missing from proof, uses an avoid-word, gets eligibility wrong, or has a CTA without UTMs. Report any you couldn't fix in chat.

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.

Check your setup, free