agentleFS
fliqrlabsfliqrlabs/instagram-creator-skills/skills/launch-campaign/SKILL.md

launch-campaign

Skill5 starsChanged 18 days agoMITView on GitHub

Plan a 7-21 day Instagram launch for a course, product, cohort, ebook, event or brand drop: warm-up, waitlist keyword, open-cart days, honest urgency and close, with a day-by-day calendar of reels, carousels, stories and lives, plus every comment-to-DM and story automation it needs (set up through the Fliqr AI connector after approval). Use when the creator says "launch", "launching my course", "product drop", "pre-launch", "waitlist", "open cart", "sell out my cohort", "holiday sale", or "festival sale".

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Read: the creator profile, ../instagram-playbook/algorithm.md, ../instagram-playbook/safety.md, ../instagram-playbook/connectors.md.

    line 23
  2. Very specific:

    When cart opens, update the warm-up automations' DMs to point at checkout (update_automation): people who comment on an old warm-up reel …

    line 53

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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-campaign

Launches fail in two ways: nobody knew it was coming, or everyone knew and nothing made them act. This skill builds the three phases that fix both, and it wires each one to a keyword, so interest becomes a list of people who raised their hand.

Read: the creator profile, ../instagram-playbook/algorithm.md, ../instagram-playbook/safety.md, ../instagram-playbook/connectors.md.

Inputs (one batch)

What's launching and the price · launch date and cart-close date · seat or stock limits (only real ones) · the bonus for early buyers (only a real one) · a lead magnet for warm-up (or build one with lead-magnet) · who the buyer is.

The three phases

WARM-UP  (7-14 days before)   teach the problem, show proof, grow the waitlist
   keyword: WAITLIST / NOTIFY → DM: "You're on the list. You'll hear first + get the early price."
OPEN CART (3-5 days)          the offer, objections answered, social proof, live Q&A
   keyword: JOIN / LINK → DM: offer + button to checkout
CLOSE    (last 24-48 hours)   honest deadline, final FAQ, last call
   story automation: reply LAST → DM with the link

Content mix:

  • Warm-up: 70% teaching (reels and carousels on the problem the product solves), 30% story (why you built it, behind the scenes). No hard selling yet.
  • Open cart: daily stories (story-funnel), one objection-crusher reel a day ("Do I need X to join? No, here's why"), a results or proof post (real only), a live on day 1 or 2 (live-funnel).
  • Close: a countdown sticker, a "doors close tonight" reel, and the FAQ answered in stories.

Urgency, honestly

Only real deadlines, real seat limits and real bonuses. "Only 3 spots left" when it isn't true breaks trust. Consumer-protection rules in many countries treat fake scarcity and false countdowns as misleading practices or "dark patterns" (for example the FTC in the US, the CMA in the UK, the EU's Unfair Commercial Practices rules, and India's 2023 dark-pattern guidelines). Good honest urgency: early-bird pricing that actually ends, a cohort start date, a bonus live call for the first 48 hours.

Automations to set up

List every automation the campaign needs, each with its keyword, the post it's attached to (or is_next), and its DM. Build each one with comment-to-dm or story-funnel. Each one is approved and created paused. Then, each step on its own yes (approval for the plan doesn't approve the individual changes):

  • Activate warm-up automations as their posts go live.
  • When cart opens, update the warm-up automations' DMs to point at checkout (update_automation): people who comment on an old warm-up reel should now get the open-cart offer. Show each patch first.
  • After close, update the DMs again ("Doors are closed. Join the waitlist for next time"), or pause them (set_automation_status: paused). Never leave a "buy now" DM pointing at a closed cart. Put the close-day changes in the plan as a reminder, because nothing switches over by itself.

Output

LAUNCH  ·  {product} {price}  ·  warm-up {dates} · open {dates} · close {date}

DAY   PHASE    FEED                                   STORIES                      AUTOMATION
-10   warm-up  Reel: "{hook}" (#13)                   poll: problem check          WAITLIST on this reel [new]
…
 0    OPEN     Carousel: what's inside + price        5-frame sell sequence        JOIN on carousel [new] · WAITLIST DMs → checkout [update]
…
+4    CLOSE    Reel: "Doors close tonight"            countdown · FAQ · last call  story LAST [new]
+5    after    —                                       thank-you + results          pause JOIN · WAITLIST → next-cohort list [update]

AUTOMATIONS: 4 new · 2 updates · 1 pause. Each needs your yes when it's built.
METRICS to watch: waitlist triggers / day · JOIN triggers vs sales · reel saves on objection posts

Then offer to build day 1 (reel-script and comment-to-dm).

<!-- brand:footer -->

Part of Instagram Creator Skills by Fliqr AI. Live Instagram data and comment-to-DM automations come from the Fliqr AI connector (fliqr.ai).

<!-- /brand:footer -->

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.