instagram-marketing
Create, optimize, and automate Instagram content including Reels, Stories, carousels, and feed posts. Use when someone asks to "grow on Instagram", "create Instagram Reels", "Instagram content strategy", "Instagram API integration", "automate Instagram posting", "Instagram analytics", or "Instagram marketing". Covers Reels-first strategy, visual content guidelines, Instagram Graph API, and growth tactics.
What this skill does
# Instagram Marketing
## Overview
This skill helps AI agents create high-performing Instagram content and integrate with the Instagram Graph API. It covers content formats (Reels, Stories, carousels, feed posts), visual guidelines, caption writing, hashtag strategy, API publishing, analytics, and growth strategies for Instagram's visual-first, Reels-dominated algorithm.
## Instructions
### Platform Rules & Algorithm
Instagram algorithm (2025-2026):
- **Reels are king** — 2-3x reach compared to static posts, Instagram's primary growth lever
- **Saves and shares** — strongest signals (more than likes or comments)
- **Watch time** — Reels that are watched fully or replayed get boosted heavily
- **Content type variety** — accounts posting Reels + carousels + Stories rank higher
- **Hashtags are weak** — SEO-style keyword captions matter more now
- **Consistency** — daily Stories + 4-7 feed posts/week
What kills reach:
- Reposting TikTok videos with watermark (Instagram actively suppresses)
- Low-resolution images/video
- Engagement bait ("like for part 2")
- Inactive periods (algorithm deprioritizes dormant accounts)
- Excessive hashtags in caption (looks spammy, 5-10 targeted is better than 30)
### Content Formats
#### Reels (Primary growth format)
- **Duration:** 15-60 seconds optimal (under 90s max, but shorter performs better)
- **Aspect ratio:** 9:16 (1080x1920px) — full vertical
- **Hook:** First 1-2 seconds determine if people keep watching. Text overlay or surprising visual
- **Captions/subtitles:** Mandatory — 85%+ watch without sound
- **Music:** Use trending audio for algorithmic boost (check Reels tab for trending sounds)
- **Cover image:** Custom cover at 1080x1920px, shows in grid — keep it clean with text overlay
- **Text overlays:** Large, bold, centered. Assume people watch on phone
- **CTA:** "Save this for later", "Share with someone who needs this", "Follow for more [topic]"
**Reel types that work:**
- Tutorial/how-to (3-5 step process shown visually)
- Before/after transformation
- Trending audio + your niche twist
- Day in the life / behind the scenes
- List format with text overlays ("5 tools I can't live without")
- POV / relatable scenarios
#### Carousels (Highest save rate)
- **Slides:** 2-10 images/videos per carousel
- **Aspect ratio:** 1:1 (1080x1080px) or 4:5 (1080x1350px) — 4:5 takes more screen space
- **Slide 1:** Hook — bold title, treat it like a thumbnail
- **Slides 2-9:** One idea per slide, large text, clean design
- **Last slide:** CTA (save, share, follow) + your handle/branding
- **Swipe cue:** Add "Swipe →" or arrow on first slide
- **Design consistency:** Same fonts, colors, layout across slides
**Carousel types:**
- Educational (step-by-step tutorial)
- Tips/list (10 things about X)
- Storytelling (narrative across slides)
- Before/after comparison
- Data/stats visualization
#### Stories (Daily engagement tool)
- **Duration:** 15 seconds per story, post 3-7 per day
- **Aspect ratio:** 9:16 (1080x1920px)
- **Stickers:** Use polls, questions, quizzes, countdowns (drive engagement)
- **Links:** Available for all accounts (link sticker)
- **Highlights:** Save best stories to themed highlights on profile
- **Authenticity:** Stories can be less polished than feed — real > perfect
#### Feed Posts (Static images)
- **Aspect ratio:** 1:1 (1080x1080px) or 4:5 (1080x1350px)
- **Quality:** High-res only, consistent visual style/filter
- **Alt text:** Add for accessibility and SEO (Instagram indexes it)
### Caption Writing
```
[Hook line — stops the scroll, shown before "...more"]
[Empty line for spacing]
[Body — value, story, or insight. Written conversationally.]
[Break long paragraphs into 2-3 sentences max.]
[Include searchable keywords naturally — Instagram now does SEO]
[CTA — question, save prompt, or share prompt]
.
.
.
[Hashtags below dot spacers — or in first comment]
```
**Caption rules:**
- First line is the hook (shown before truncation)
- 150-300 words for educational posts (dwell time matters)
- Write conversationally — Instagram is personal
- Use line breaks and spacing (no text walls)
- Include keywords naturally (Instagram's search is now keyword-based)
- 5-15 hashtags — mix of niche (10K-500K posts) and medium (500K-5M)
- Put hashtags in caption OR first comment (both work, test what's better)
### Instagram Graph API
#### Authentication
```typescript
// Instagram Graph API uses Facebook's OAuth
// Requires: Facebook Page + Instagram Professional account linked
// Step 1: Get Facebook User Access Token via Facebook Login
const FB_AUTH_URL = 'https://www.facebook.com/v19.0/dialog/oauth';
const params = new URLSearchParams({
client_id: process.env.FB_APP_ID,
redirect_uri: process.env.REDIRECT_URI,
scope: 'instagram_basic,instagram_content_publish,instagram_manage_insights,pages_show_list,pages_read_engagement',
response_type: 'code',
});
// Redirect to: FB_AUTH_URL + '?' + params
// Step 2: Exchange code for token
const tokenRes = await fetch(`https://graph.facebook.com/v19.0/oauth/access_token?client_id=${FB_APP_ID}&client_secret=${FB_APP_SECRET}&redirect_uri=${REDIRECT_URI}&code=${code}`);
const { access_token } = await tokenRes.json();
// Step 3: Get long-lived token (60 days)
const longLivedRes = await fetch(`https://graph.facebook.com/v19.0/oauth/access_token?grant_type=fb_exchange_token&client_id=${FB_APP_ID}&client_secret=${FB_APP_SECRET}&fb_exchange_token=${access_token}`);
const { access_token: longLivedToken } = await longLivedRes.json();
// Step 4: Get Instagram Business Account ID
const pagesRes = await fetch(`https://graph.facebook.com/v19.0/me/accounts?access_token=${longLivedToken}`);
const { data: pages } = await pagesRes.json();
const pageId = pages[0].id;
const igRes = await fetch(`https://graph.facebook.com/v19.0/${pageId}?fields=instagram_business_account&access_token=${longLivedToken}`);
const { instagram_business_account: { id: igAccountId } } = await igRes.json();
```
#### Publish Content
```typescript
// Publish single image
// Step 1: Create media container
const containerRes = await fetch(`https://graph.facebook.com/v19.0/${igAccountId}/media`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
image_url: 'https://example.com/image.jpg', // Must be public URL
caption: 'Your caption here\n\n#hashtag1 #hashtag2',
access_token: longLivedToken,
}),
});
const { id: containerId } = await containerRes.json();
// Step 2: Publish
await fetch(`https://graph.facebook.com/v19.0/${igAccountId}/media_publish`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
creation_id: containerId,
access_token: longLivedToken,
}),
});
// Publish carousel
const mediaIds = [];
for (const imageUrl of imageUrls) {
const res = await fetch(`https://graph.facebook.com/v19.0/${igAccountId}/media`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
image_url: imageUrl,
is_carousel_item: true,
access_token: longLivedToken,
}),
});
const { id } = await res.json();
mediaIds.push(id);
}
const carouselRes = await fetch(`https://graph.facebook.com/v19.0/${igAccountId}/media`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
media_type: 'CAROUSEL',
children: mediaIds,
caption: 'Carousel caption...',
access_token: longLivedToken,
}),
});
const { id: carouselId } = await carouselRes.json();
await fetch(`https://graph.facebook.com/v19.0/${igAccountId}/media_publish`, {
method: 'POST',
body: JSON.stringify({ creation_id: carouselId, access_token: longLivedToken }),
});
// Publish Reel
const reelContainer = await fetch(`https://graph.facebook.com/v19.0/${igAccountId}/media`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
media_type: 'REELS',
video_url: 'https://examplRelated in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".