Skip to content
SkillModel-led2,717 tokens in use

ManyChat IG Lead Magnet

Builds an Instagram comment or Story reply lead magnet in ManyChat that delivers a resource only after verified newsletter signup, with tracking and approval gates.

3,862 stars on the repository MIT Licenseericosiu/ai-marketing-skills · manychat-ig-lead-magnet
npx skills add ericosiu/ai-marketing-skills -s manychat-ig-lead-magnet
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing ManyChat IG Lead Magnet costs

37tokens idle
2,717tokens in use
7,054tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure23/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity88
  • Maintenance44
  • Community56
  • Maturity28
  • Momentum40

ManyChat IG Lead Magnet walks an agent through the full path from an Instagram post to a delivered resource: picking trigger keywords, preparing the PDF or link, duplicating a working ManyChat automation, adding tracking tags and writing the DM and consent copy.

Delivery is gated on explicit newsletter consent and a verified subscribed status. Anything external-facing, such as updating a live flow or sending a Slack message, waits for explicit approval.

What You Get

  • One primary keyword and two to four backups, with a list of terms too broad to use
  • A launch packet with DM copy, email capture and consent copy, tracking tags and fields, and an attachment plan
  • A ManyChat automation duplicated from a working base, with the trigger, tracking and DM sequence set
  • A test matrix that covers consent declined, invalid email, pending confirmation and returning subscribers
  • A final report of what was prepared, what changed, the evidence checked and the approval still needed

Common Use Cases

  • Offering a PDF or guide to people who comment a keyword on a reel
  • Adding a separate Story reply trigger for the same resource
  • Triaging resource requesters across client, partnership, sponsorship, M&A and recruiting lanes with a human reviewing the result

What Makes It Unique

Most lead magnet recipes send the file as soon as someone comments. This one holds the resource until a supported readback shows the person is subscribed to the right publication, treats API or Zap acceptance as weaker evidence than subscribed status, never reactivates an unsubscribed contact, and separates a saved flow from a published one from an enabled trigger. Lead-fit tiers stay advisory and unknown is kept apart from a mismatch.

Under The Hood

The skill is instructions plus four reference documents and no scripts. It tells the agent to run the repository’s version check script from the shell and to follow the user’s existing telemetry choice. The ManyChat steps are driven through a browser or computer-use session, where the agent signs in, edits automations and checks saved state, and the user completes any login or passkey prompt. The agent may build a PDF with an available builder, host a file, inspect a Zapier run history and read back newsletter status. It must stop for explicit approval before sending Slack or email messages, uploading to a live flow, publishing, enabling a trigger or changing account permissions.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers