Plan an Instagram carousel slide by slide, up to 10 slides
Instagram Carousel Planner

Plan an Instagram carousel slide by slide, up to 10 slides, with a hook slide that opens a loop, value slides that front-load the payoff, and a payoff slide that earns the save and follow. Picks a 2026 carousel formula (listicle,…
--- name: ig-carousel-planner description: "Plan an Instagram carousel slide by slide, up to 10 slides, with a hook slide that opens a loop, value slides that front-load the payoff, and a payoff slide that earns the save and follow. Picks a 2026 carousel formula (listicle, before/after, myth-buster, framework) by goal (saves, shares, follows), drafts each slide's text plus the caption, then publishes the images you supply via Publora. Use to structure a multi-slide carousel. Not for single-image captions (use ig-caption-writer)." --- # Instagram Carousel Planner Plan a carousel that gets swiped to the end and saved. The whole game is slide 1 (the swipe-earning hook) and the last slide (the saveable payoff). This skill maps every slide, writes the on-image text, and drafts the caption that frames it. ## When to use - User wants to turn a topic or notes into a multi-slide carousel - User has a list, a framework, or a transformation to teach - User wants a slide-by-slide structure, not just a caption
Overview
Plan a carousel that gets swiped to the end and saved. The whole game is slide 1 (the swipe-earning hook) and the last slide (the saveable payoff). This skill maps every slide, writes the on-image text, and drafts the caption that frames it.
Manual install (npx, ZIP)
npx skills add sergebulaev/instagram-skills --skill ig-carousel-planner -g -a claude-codemkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/sergebulaev/instagram-skills/tar.gz/2919f0a6d8b1 \
| tar -xz -C ~/.claude/skills --strip-components=4 instagram-skills-2919f0a6d8b1/.codex-marketplace/instagram-skills/skills/ig-carousel-plannerNew-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/fd8c79e6b7e5ce351a79/ig-carousel-planner.zip" -OutFile "$env:TEMP\ig-carousel-planner.zip"; Expand-Archive "$env:TEMP\ig-carousel-planner.zip" -DestinationPath "$HOME\.claude\skills" -ForceConnects with Agent Alley MCP · agentalley.io/mcp
Files included
SKILL.md6.8 KBreferences/1 file · 3.4 KB
Read the files here
sergebulaev/
Shared references6SKILL.md reads these from elsewhere in the repo. Not in the ZIP.
- algorithm-heuristics.md.codex-marketplace/instagram-skills/references/7.9 KB
- hashtag-strategy.md.codex-marketplace/instagram-skills/references/4.4 KB
- hook-formulas.md.codex-marketplace/instagram-skills/references/11.4 KB
- media-workflow.md.codex-marketplace/instagram-skills/references/3.9 KB
- voice-profile.md.codex-marketplace/instagram-skills/references/1.6 KB
- illustration.md.codex-marketplace/instagram-skills/skills/ig-humanizer/sub-skills/3.7 KB
Show the full text124 lines
Instagram Carousel Planner
Plan a carousel that gets swiped to the end and saved. The whole game is slide 1 (the swipe-earning hook) and the last slide (the saveable payoff). This skill maps every slide, writes the on-image text, and drafts the caption that frames it.
When to use
- User wants to turn a topic or notes into a multi-slide carousel
- User has a list, a framework, or a transformation to teach
- User wants a slide-by-slide structure, not just a caption
Formulas this skill uses (carousel shapes)
| Code | Formula | Primary goal | Best for |
|---|---|---|---|
| IG5 | Listicle Carousel | saves | a numbered teaching list, one item per slide |
| IG6 | Before/After Transformation | saves, follows | proof of a result with the steps between |
| IG7 | Myth-Buster | shares | correcting beliefs your niche holds |
| IG8 | Steal-This Framework | saves | a named, repeatable framework |
Full skeletons in ../../references/hook-formulas.md.
Slide architecture (the 10-slide spine)
A carousel is 2-10 slides (API limit). The reliable spine:
| Slide | Role |
|---|---|
| 1 (hook) | the promise + an open loop ("most miss #4"). Earns the swipe. Big text, one idea. |
| 2-3 | the strongest value, front-loaded (swipe-through decays with depth). |
| 4 to N-1 | one point per slide, each standing alone, each readable in 2 seconds. |
| N (payoff) | the one-slide summary (the saveable artifact) + one clear ask (save / follow). |
6-10 slides is the sweet spot for a teaching carousel. Fewer than 4 is usually a
single image. See references/slide-architecture.md for per-formula spines.
Steps
Voice profile first (all drafts). If ../../references/voice-profile.md has filled: yes, load it and match the user's voice fingerprint, hard rules, and CTA/link style throughout. If it is not filled, mention once that ig-humanizer --mode profile can learn their voice from a few posts, then proceed with the generic voice rules.
- Gather inputs. Topic, the list/framework/transformation, target audience, and the goal (saves / shares / follows).
- Pick the formula. Use the goal table; suggest 2-3 that fit and let the user choose.
- Set the slide count. Match it to the real content (6-10 typical). Never pad to hit 10; viewers feel filler and bail.
- Write slide 1. The promise plus the loop. Big, single-idea on-image text. Front-load a number if one fits.
- Map the value slides. Put the strongest point on slide 2 or 3. One point per slide, each able to stand alone. Draft the on-image text for each (keep it short, it has to read in 2 seconds on a 4:5 frame).
- Write the payoff slide. A one-slide recap that is worth saving on its own, plus a single ask (save it / follow for more).
- Write the caption. The caption supports the carousel (it can be short),
restates the hook for the fold, and carries the hashtags. Hand off to
ig-hashtag-strategistor apply the 3-5 sized set. - Humanizer pass on the on-image text and caption. Scrub 2026 AI vocab
by density (per slide, per caption paragraph), cap em dashes (at most one
per slide, about one per 100 words in the caption; never swap one for a
period), break stacked triads and reveal bridges. Slides are short by
design: never chop or pad a slide for rhythm. Canonical rules:
ig-humanizerV3. - Approval card. Show: formula, slide-by-slide outline with each slide's text, the caption, hashtag set, primary goal, and a reminder that the user supplies 2-10 images (all images, no mixed media) in this order.
- On approval, publish with media. Call
lib.publish(kind="carousel", draft_text=<approved caption>, target_url="https://www.instagram.com/", media=[<slide image paths in order>], platforms=[<INSTAGRAM_PLATFORM_ID>], scheduled_time=<iso_or_None>). The wrapper uploads each image in order and schedules. With no media or no Publora key it returns the plan as a copy-paste block plus the slide order.
Hard rules
Global voice rules: see root SKILL.md Voice rules. Additional skill-specific
rules:
- Slide 1 is a promise with an open loop, never a bare title.
- Front-load value to slides 2-3; never bury the best point at the end.
- One point per slide, readable in 2 seconds on a portrait 4:5 frame.
- 2-10 slides only. Never pad to a round number.
- All images, no mixed media (the API rejects an image+video carousel).
- The last slide must earn the save with a one-slide summary and one ask.
Anti-patterns (skill will refuse)
- A title-only slide 1 with no promise or loop.
- A 10-slide carousel padded from a 4-point idea.
- The strongest point saved for the final slide.
- Three competing CTAs on the payoff slide.
- Mixing images and a video in one carousel.
- On-image walls of text that cannot be read in a swipe.
- Em dashes above the cap (more than one on a slide), AI vocab clusters, stacked or hollow rule-of-three.
- "The result?" reveals and staccato stacks added for punch.
Resources
../../references/hook-formulas.md- the carousel formulas (IG5-IG8) with skeletons../../references/algorithm-heuristics.md- 2026 carousel ranking and swipe-through rules../../references/hashtag-strategy.md- the 3-5 sized hashtag recipe../../references/media-workflow.md- uploading 2-10 images in orderreferences/slide-architecture.md- per-formula slide spines and on-image text rules
Optional illustration
Offer a generated image when a visual would lift reach. Draft a prompt and call
lib.illustrate(prompt, kind="carousel"), pulling brand handle/color from Voice &
Brand Profile section 6 for a pixel-exact overlay. Show the returned url + cost,
attach it as your Instagram media via media_urls=[url] in one shot (Publora fetches the hosted URL server-side): a single image posts as a photo, and the carousel planner can pass 2-10 URLs for a carousel. For a Reel cover instead, set platformSettings.instagram.coverUrl. Full workflow (incl. quote-cards):
../ig-humanizer/sub-skills/illustration.md. No Pixfaro key -> it drafts the prompt for you to generate manually.
Related skills
ig-caption-writer- when the idea is a single image, not a carouselig-hashtag-strategist- build the sized hashtag setig-humanizer- scrub the on-image text and captionig-hook-extractor- reverse-engineer a carousel you admire
| 1 | |
| 2 | name ig-carousel-planner |
| 3 | description "Plan an Instagram carousel slide by slide, up to 10 slides, with a hook slide that opens a loop, value slides that front-load the payoff, and a payoff slide that earns the save and follow. Picks a 2026 carousel formula (listicle, before/after, myth-buster, framework) by goal (saves, shares, follows), drafts each slide's text plus the caption, then publishes the images you supply via Publora. Use to structure a multi-slide carousel. Not for single-image captions (use ig-caption-writer)." |
| 4 | |
| 5 | |
| 6 | # Instagram Carousel Planner |
| 7 | |
| 8 | Plan a carousel that gets swiped to the end and saved. The whole game is slide 1 |
| 9 | (the swipe-earning hook) and the last slide (the saveable payoff). This skill |
| 10 | maps every slide, writes the on-image text, and drafts the caption that frames |
| 11 | it. |
| 12 | |
| 13 | ## When to use |
| 14 | |
| 15 | User wants to turn a topic or notes into a multi-slide carousel |
| 16 | User has a list, a framework, or a transformation to teach |
| 17 | User wants a slide-by-slide structure, not just a caption |
| 18 | |
| 19 | ## Formulas this skill uses (carousel shapes) |
| 20 | |
| 21 | | Code | Formula | Primary goal | Best for | |
| 22 | |---|---|---|---| |
| 23 | | IG5 | Listicle Carousel | saves | a numbered teaching list, one item per slide | |
| 24 | | IG6 | Before/After Transformation | saves, follows | proof of a result with the steps between | |
| 25 | | IG7 | Myth-Buster | shares | correcting beliefs your niche holds | |
| 26 | | IG8 | Steal-This Framework | saves | a named, repeatable framework | |
| 27 | |
| 28 | Full skeletons in `../../references/hook-formulas.md`. |
| 29 | |
| 30 | ## Slide architecture (the 10-slide spine) |
| 31 | |
| 32 | A carousel is 2-10 slides (API limit). The reliable spine: |
| 33 | |
| 34 | | Slide | Role | |
| 35 | |---|---| |
| 36 | | **1 (hook)** | the promise + an open loop ("most miss #4"). Earns the swipe. Big text, one idea. | |
| 37 | | **2-3** | the strongest value, front-loaded (swipe-through decays with depth). | |
| 38 | | **4 to N-1** | one point per slide, each standing alone, each readable in 2 seconds. | |
| 39 | | **N (payoff)** | the one-slide summary (the saveable artifact) + one clear ask (save / follow). | |
| 40 | |
| 41 | 6-10 slides is the sweet spot for a teaching carousel. Fewer than 4 is usually a |
| 42 | single image. See `references/slide-architecture.md` for per-formula spines. |
| 43 | |
| 44 | ## Steps |
| 45 | |
| 46 | **Voice profile first (all drafts).** If `../../references/voice-profile.md` has `filled: yes`, load it and match the user's voice fingerprint, hard rules, and CTA/link style throughout. If it is not filled, mention once that `ig-humanizer --mode profile` can learn their voice from a few posts, then proceed with the generic voice rules. |
| 47 | |
| 48 | **Gather inputs.** Topic, the list/framework/transformation, target audience, |
| 49 | and the goal (saves / shares / follows). |
| 50 | **Pick the formula.** Use the goal table; suggest 2-3 that fit and let the |
| 51 | user choose. |
| 52 | **Set the slide count.** Match it to the real content (6-10 typical). Never |
| 53 | pad to hit 10; viewers feel filler and bail. |
| 54 | **Write slide 1.** The promise plus the loop. Big, single-idea on-image text. |
| 55 | Front-load a number if one fits. |
| 56 | **Map the value slides.** Put the strongest point on slide 2 or 3. One point |
| 57 | per slide, each able to stand alone. Draft the on-image text for each (keep it |
| 58 | short, it has to read in 2 seconds on a 4:5 frame). |
| 59 | **Write the payoff slide.** A one-slide recap that is worth saving on its own, |
| 60 | plus a single ask (save it / follow for more). |
| 61 | **Write the caption.** The caption supports the carousel (it can be short), |
| 62 | restates the hook for the fold, and carries the hashtags. Hand off to |
| 63 | `ig-hashtag-strategist` or apply the 3-5 sized set. |
| 64 | **Humanizer pass** on the on-image text and caption. Scrub 2026 AI vocab |
| 65 | by density (per slide, per caption paragraph), cap em dashes (at most one |
| 66 | per slide, about one per 100 words in the caption; never swap one for a |
| 67 | period), break stacked triads and reveal bridges. Slides are short by |
| 68 | design: never chop or pad a slide for rhythm. Canonical rules: |
| 69 | `ig-humanizer` V3. |
| 70 | **Approval card.** Show: formula, slide-by-slide outline with each slide's |
| 71 | text, the caption, hashtag set, primary goal, and a reminder that the user |
| 72 | supplies 2-10 images (all images, no mixed media) in this order. |
| 73 | **On approval, publish with media.** Call `lib.publish(kind="carousel", |
| 74 | draft_text=<approved caption>, target_url="https://www.instagram.com/", |
| 75 | media=[<slide image paths in order>], platforms=[<INSTAGRAM_PLATFORM_ID>], |
| 76 | scheduled_time=<iso_or_None>)`. The wrapper uploads each image in order and |
| 77 | schedules. With no media or no Publora key it returns the plan as a |
| 78 | copy-paste block plus the slide order. |
| 79 | |
| 80 | ## Hard rules |
| 81 | |
| 82 | Global voice rules: see root `SKILL.md` Voice rules. Additional skill-specific |
| 83 | rules: |
| 84 | |
| 85 | Slide 1 is a promise with an open loop, never a bare title. |
| 86 | Front-load value to slides 2-3; never bury the best point at the end. |
| 87 | One point per slide, readable in 2 seconds on a portrait 4:5 frame. |
| 88 | 2-10 slides only. Never pad to a round number. |
| 89 | All images, no mixed media (the API rejects an image+video carousel). |
| 90 | The last slide must earn the save with a one-slide summary and one ask. |
| 91 | |
| 92 | ## Anti-patterns (skill will refuse) |
| 93 | |
| 94 | A title-only slide 1 with no promise or loop. |
| 95 | A 10-slide carousel padded from a 4-point idea. |
| 96 | The strongest point saved for the final slide. |
| 97 | Three competing CTAs on the payoff slide. |
| 98 | Mixing images and a video in one carousel. |
| 99 | On-image walls of text that cannot be read in a swipe. |
| 100 | Em dashes above the cap (more than one on a slide), AI vocab clusters, stacked or hollow rule-of-three. |
| 101 | "The result?" reveals and staccato stacks added for punch. |
| 102 | |
| 103 | ## Resources |
| 104 | |
| 105 | `../../references/hook-formulas.md` - the carousel formulas (IG5-IG8) with skeletons |
| 106 | `../../references/algorithm-heuristics.md` - 2026 carousel ranking and swipe-through rules |
| 107 | `../../references/hashtag-strategy.md` - the 3-5 sized hashtag recipe |
| 108 | `../../references/media-workflow.md` - uploading 2-10 images in order |
| 109 | `references/slide-architecture.md` - per-formula slide spines and on-image text rules |
| 110 | |
| 111 | ## Optional illustration |
| 112 | |
| 113 | Offer a generated image when a visual would lift reach. Draft a prompt and call |
| 114 | `lib.illustrate(prompt, kind="carousel")`, pulling brand handle/color from Voice & |
| 115 | Brand Profile section 6 for a pixel-exact overlay. Show the returned `url` + `cost`, |
| 116 | attach it as your Instagram media via `media_urls=[url]` in one shot (Publora fetches the hosted URL server-side): a single image posts as a photo, and the carousel planner can pass 2-10 URLs for a carousel. For a Reel cover instead, set `platformSettings.instagram.coverUrl`. Full workflow (incl. quote-cards): |
| 117 | `../ig-humanizer/sub-skills/illustration.md`. No Pixfaro key -> it drafts the prompt for you to generate manually. |
| 118 | ## Related skills |
| 119 | |
| 120 | `ig-caption-writer` - when the idea is a single image, not a carousel |
| 121 | `ig-hashtag-strategist` - build the sized hashtag set |
| 122 | `ig-humanizer` - scrub the on-image text and caption |
| 123 | `ig-hook-extractor` - reverse-engineer a carousel you admire |
| 124 |
Details
- Updated
- Sep 17, 2026
- License
- MIT
- Stars on the repo
- ★ 138
- Checked
- Source
- sergebulaev/instagram-skills ↗
- Creator
- sergebulaev · 77 listings
Similar skills
See all →
SkillGenerate a branded slide-by-slide LinkedIn carouselGemini carousel
SkillBuild a LinkedIn document postLi carousel
SkillDraft an Instagram caption with the hook in the first 125Instagram Caption Writer
SkillSocial media campaign analysis and performance trackingSocial media analyzer
SkillScore a LinkedIn post using real performance dataPost scorer
SkillVideo caption generatorMore from sergebulaev
SkillBy density per paragraph, not per wordAI Tells — Complete Blacklist (V3, 2026-09)
SkillFifteen rules from the linkedin-humanizer packageAI-Tell Rules: Tier-Classified Reference
SkillPattern data from MagicPost LinkedIn analysisEmoji Patterns — AI vs. Human
SkillRead your Instagram niche and profile from real dataInstagram Audience Insights
SkillDraft an Instagram caption with the hook in the first 125Instagram Caption Writer
SkillPlan, draft, audit, and publish posts and threads for XX (Twitter) Marketing Skills