Instagram Growth logo

Instagram Growth

Organization
social-media-skills
instagram-growth

Use to grow an Instagram account — the Instagram-specific growth strategy that diagnoses where growth is stuck (reach, follow-conversion, retention, or shares) and orchestrates the other skills to fix it. Run when the user says "grow on Instagram," "Instagram growth," "get more followers/reach on Instagram," "my Instagram isn't growing," "Instagram strategy," or wants more reach/followers on IG. Reads brand-profile, social-strategy, and audience first. Built on the 2026 reality that Instagram is a discovery engine where watch time and sends (DM shares) drive non-follower reach. Diagnoses the broken stage of the growth loop and routes to the right skill (reels-script, carousel-writer, profile-optimization, content-calendar, hashtag-strategy, trend-jacking). Judges via native Instagram Insights — not WoopSocial analytics — and treats follower count as vanity.

Overview

Publishersocial-media-skills
Repositoryskills
Skill nameinstagram-growth
Stars
215
Forks
44
Bundled files
5
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by social-media-skills on GitHub. Read the source before you install it.

Installation

Install the Instagram Growth AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/social-media-skills/skills/tree/main/skills/instagram-growth
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/social-media-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/instagram-growth .claude/skills/instagram-growth
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Instagram Growth in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Instagram Growth on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Instagram Growth is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Instagram Growth

This is the Instagram-specific growth system — not another content skill. It diagnoses where growth is stuck and routes to the skills that fix it, on top of the 2026 reality of how Instagram actually distributes content.

Three truths shape everything:

  1. Instagram is a discovery engine, not a follower feed. ~94% of distribution is AI recommendations; most reach comes from non-followers via Reels and Explore. Reach is earned per post — follower count is a vanity number.
  2. Watch time and sends drive reach. The top signals are watch time (the first ~3 seconds decide a Reel) and sends-per-reach (DM shares), which are ~3–5× more valuable than likes for reaching new people. Strong hook + send-worthy content = travel.
  3. Each surface has its own algorithm. Reels = discovery, Feed = followers, Stories = retention, Explore = discovery. Match the format to the surface's signal.

(Full model: references/the-growth-engine.md.)

Step 0 — Read the foundation + the current state

Load brand-profile.md, social-strategy.md, audience.md. Get the goal (reach / follows / leads) and the current state from WoopSocial post analytics (views, impressions, saves, shares, likes) plus native Insights for non-follower reach, profile visits, follows, and watch time — those are not stored in WoopSocial. Never fabricate.

Step 1 — Diagnose the broken stage (the growth loop)

Find which stage is stuck: Reach → Follow-conversion → Retention/Sends → Sustainability. A growth problem is almost always one specific stage — diagnose it before prescribing. See the diagnosis table in references/format-and-diagnosis.md.

Step 2 — Fix the reach engine (Reels-led)

If reach is the issue: prioritize Reels (the non-follower engine), nail the 3-second hook (watch time), and clear the eligibility gates — original, no TikTok watermark, has audio, under the length cap, clear niche (the algorithm must categorize you). Use Trial Reels to test with non-followers risk-free. → reels-script, hook-writer. See references/the-growth-engine.md.

Step 3 — Pull the sends lever

Sends (DM shares) are the dominant discovery signal. Engineer send-worthy content — relatable, useful/reference, conversation-starting — so people forward it. Track sends-per-reach (aim past ~1–2%). See references/the-sends-lever.md.

Step 4 — Run the formats as a system

Reels = reach · carousels = saves/authority · Stories = retention · photos = low discovery. Map each format to the signal its surface rewards; don't post them interchangeably. → reels-script, carousel-writer. See references/format-and-diagnosis.md.

Step 5 — Convert + retain

  • Convert the reach: if views are high but follows are low, the profile is the problem → profile-optimization.
  • Retain the warm audience: Stories (polls/questions/replies) + fast comment/DM replies + a broadcast channel (one-to-many DMs — the highest-attention surface for superfans) + community. This boosts early signals on every new post.

Step 6 — Niche, SEO, cadence, measurement

  • Niche clarity + keywords (caption/on-screen/audio) so Instagram categorizes and surfaces you → hashtag-strategy / social-seo.
  • Sustainable cadence (consistency > volume) → content-calendar.
  • Measure via native Insights (sends-per-reach, saves, watch time, profile visits, follower vs non-follower reach). Never claim WoopSocial analytics; follower count is vanity.

Orchestration map

instagram-growth diagnoses and routes; these execute: reels-script · hook-writer · carousel-writer · caption-writer · profile-optimization · content-calendar · hashtag-strategy · trend-jacking · viral-reverse-engineering · cross-platform-repurposing · scheduling-and-queue.

Quality bar — self-check

  • Did I diagnose the broken stage rather than spray generic tips?
  • Did I center Reels for reach and sends + watch time as the signals?
  • Did I route to the right skills to fix each stage?
  • Did I respect the eligibility gates (original, no watermark, niche clarity)?
  • Did I reframe follower count as vanity toward reach/sends/saves/profile-visits/leads?
  • Sustainable cadence, measurement from WoopSocial post analytics plus native Insights, no fabricated metrics, no growth hacks / no guarantees?

Edge cases & pushback

  • "Get me 10k followers / buy followers" → refuse fake engagement; reframe to reach/sends/leads; follower count is vanity.
  • "Repost my TikToks" → watermark + originality gate throttles them; make native versions.
  • "Guarantee viral growth" → no guarantees; a compounding system stacks the odds.
  • "Lots of views, no follows" → it's the profile → profile-optimization.
  • Multi-niche / unclear lane → tighten the niche (the algorithm must categorize you).
  • Unsustainable schedule → match cadence to capacity → content-calendar.
  • "Which post performs best?" → native Insights; no WoopSocial analytics.

Related skills

  • brand-profile, social-strategy, audience-research — the positioning growth rests on.
  • reels-script, hook-writer, carousel-writer, caption-writer — the content that earns reach.
  • profile-optimization — converts reach to follows; content-calendar — sustainable cadence.
  • hashtag-strategy / social-seo — the keyword/discoverability layer; trend-jacking — trends.
  • viral-reverse-engineering — learn what already gets shared; instagram-reels-publishing + scheduling-and-queue — publish.

References

  • references/the-growth-engine.md — the discovery-engine model, the 3 signals, surfaces, the loop, gates, Trial Reels.
  • references/the-sends-lever.md — sends (DM shares): the dominant discovery signal and how to earn it.
  • references/format-and-diagnosis.md — format→surface jobs, niche/SEO/cadence, and the symptom→stage→fix table.
  • references/examples.md — worked growth diagnoses with routing, plus honest expectations.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Instagram Growth AI skill do?

Use to grow an Instagram account — the Instagram-specific growth strategy that diagnoses where growth is stuck (reach, follow-conversion, retention, or shares) and orchestrates the other skills to fix it. Run when the user says "grow on Instagram," "Instagram growth," "get more followers/reach on Instagram," "my Instagram isn't growing," "Instagram strategy," or wants more reach/followers on IG. Reads brand-profile, social-strategy, and audience first. Built on the 2026 reality that Instagram is a discovery engine where watch time and sends (DM shares) drive non-follower reach. Diagnoses th...

Why use Instagram Growth on TypingMind?

Because you install it once and use it with any model. Instagram Growth is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Instagram Growth in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/instagram-growth. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Instagram Growth?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Instagram Growth?

As many as you like. As long as a model supports skills, you can use Instagram Growth with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Instagram Growth AI skill free?

Yes. It is published on GitHub by social-media-skills under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇