agentleFS
link7373link7373/agentic-sales-marketing/.claude/skills/launch-product/SKILL.md

launch-product

Skill1 starsChanged 3 months agoMITView on GitHub

Take a new product, feature, or version to market — tiering, messaging document, asset plan, enablement pack, launch-day runbook, and the day-7/day-30 reviews. Run when something ships that changes who should buy or why.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Rehearse: Every link, every form, a complete purchase, mobile rendering, email preview.

    line 20
  2. Distinctive:

    No case study available (too new, no permission) → the guarantee and specific proof points do that work instead.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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-product — Ship the Understanding, Not the Announcement

Inputs: what's launching and when, knowledge/offer.md, knowledge/positioning.md, knowledge/audience-profiles.md, knowledge/competitors.md, win-loss notes in knowledge/results-history.md, knowledge/research/social-proof.md. Agents: product-marketer leads; brand-strategist checks positioning consistency; copywriter writes; funnel-builder, campaign-manager, content-marketer, and partnerships-manager execute their channels; growth-analyst instruments. Method: knowledge/methods/product-launch.md.

Steps

  1. Tier it honestly. Does this change who should buy, or why? Tier 1 (new product/segment/repositioning) gets everything below; Tier 2 (significant feature) gets email, social, page updates, and a note to the sales agents; Tier 3 (improvements and fixes) gets a changelog entry and nothing else — and most releases are Tier 3. Recommending "this isn't a launch" is a valid and valuable output.
  2. Write the messaging document. One-sentence description in the customer's language; the problem as they experience it; who it's for and explicitly who it isn't; three proof points with evidence; the before/after; the status shift; objections answered honestly including price; what we're deliberately not claiming. Test the one sentence on someone unfamiliar — if they repeat it back wrong, fix the sentence.
  3. Define success before building. The metric, how it's measured, and the honest expectation given current traffic and list size. Recorded now so day 30 can't be graded on a curve.
  4. Plan the assets by audience. Existing customers, pipeline prospects, cold audience — three different messages. Fill templates/launch-plan.md, then delegate: page → /build-funnel, email → /launch-campaign, social → /create-content, partners and press → /run-partnerships, paid support → /run-ads (only if the money gate covers it).
  5. Build the enablement pack. One-pager (built to be forwarded to whoever wasn't in the conversation), battlecard per real competitor (including where they genuinely win and when to walk away), FAQ/objection library from actual win-loss notes, and a case study if a permitted one exists.
  6. Prime the ground, a week out. Tell existing customers before the public. Brief partners and creators so they can act on day one. PR pitches go now — journalists work ahead.
  7. Rehearse. Every link, every form, a complete purchase, mobile rendering, email preview. Someone uninvolved reads everything cold and reports what confused them. Batch the approvals (publishing for assets, money for any spend) and secure them before the day, not on it.
  8. Run launch day to the runbook. Sequence per method §5: existing customers → page live → email → social spread across the day → partner activation → PR. Reply to everything personally; the launch-day response rate is read as evidence of what dealing with this business is like. Watch for breakage, not for early results.
  9. Day 7 and day 30. Day 7: numbers vs. the metric, and which questions keep recurring (recurring questions are messaging gaps — fix them now, it's nearly free). Day 30: honest verdict, what the market understood differently than intended, what becomes permanent, and a learning line to the method file.

Before you start

  1. Required inputs: knowledge/offer.md and knowledge/positioning.md at seeded+ — a launch inherits positioning; it doesn't invent it. If the launch would change positioning, run /define-positioning first: that's a strategy change, not a launch.
  2. Scan knowledge/decision-log.md for tags launch, offer, positioning, pricing.
  3. Gate check: publishing gate for the asset batch, money gate for any launch spend. The Claims Review Checklist applies to every claim, and hardest to the case study.

If things go wrong

  • The launch date moves → the plan slides whole; never launch with half the assets, because the messaging inconsistency costs more than the delay.
  • Nothing is genuinely newsworthy for PR → skip PR rather than pitching a non-story; a wasted pitch spends a relationship that can only be spent once.
  • Day 7 shows the metric badly missed → diagnose before reacting: wrong audience, wrong message, or wrong expectation? A miss against an inflated expectation is a forecasting error, not a launch failure — say which.
  • No case study available (too new, no permission) → the guarantee and specific proof points do that work instead; never manufacture one.

Outputs

A messaging document, a launch plan, a coordinated launch, an enablement pack that outlives the launch, and the day-7/day-30 reviews. Lives at knowledge/campaigns/YYYY-MM-<slug>-launch.md. Close with the report per templates/skill-report.md.

Writeback

The launch file; enablement assets to knowledge/campaigns/YYYY-MM-<slug>-launch-assets/; results to knowledge/results-history.md; approvals to knowledge/approvals-log.md; launch decisions (tag: launch) to knowledge/decision-log.md; new proof to knowledge/research/social-proof.md; a learning line to knowledge/methods/product-launch.md.

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.