agentleFS
nicojunknicojunk/claude-ig/skills/ig-carousel/SKILL.md

ig-carousel

Skill17 starsChanged 8 months agoMITView on GitHub

Plan Instagram carousel posts with optimized slide structure, compelling cover hooks, and save-driven CTAs. Scores the carousel against engagement benchmarks before delivery.

11 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use ig-profile, ig-dm and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JakeschincariolSkill

    ig-profile

    Score an Instagram profile out of 100 against a 12-part rubric and rewrite the parts that lose points - name field, bio, link, highlights, pinned three, grid. Use when the user says "optimize my profile", "fix my bio", "score my Instagram", "why don't people follow me", or pastes their profile and asks how it reads.

    Also in 8 projects that use this

  • JakeschincariolSkill

    ig-dm

    Write Instagram DMs that get replies - the keyword delivery, the first message to someone who engaged, the collab pitch, and the two follow-ups. Use when the user says "DM this person", "what do I send them", "outreach message", "how do I follow up", "pitch this brand", or is reaching out to someone specific.

    Also in 8 projects that use this

  • vava2684Skill

    ig-reply

    Instagram 貼文留言智慧回覆。抓某篇貼文底下的新留言,由 Claude 在對話裡依貼文內容與留言者語言生成友善回覆,再透過 Graph API 自動送出。觸發時機:使用者說「回覆留言」「處理 IG 留言」「回 IG」「IG 自動回覆」「抓留言來回」「回我 IG 那篇」等。

    Also in 7 projects that use this

  • +3 more from Jakeschincariol

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check hook-library.md for the highest-performing hook category matching this topic.

    line 29
  2. Distinctive:

    Must create a curiosity gap or emotional trigger

    line 37
  3. Distinctive:

    Use one of these proven patterns from hook-library.md:

    line 38
  4. Distinctive:

    No logo or branding on the cover (it kills curiosity)

    line 45
  5. Distinctive:

    Document the chosen hook pattern and exact cover text.

    line 47
  6. Distinctive:

    Follow the Hook > Content > Reveal > CTA arc:

    line 51
  7. Distinctive:

    One idea per slide: If you need a comma, you need a new slide.

    line 62
  8. Distinctive:

    Write a caption that complements (not repeats) the carousel content:

    line 90
  9. Distinctive:

    If below 7.0, identify the weakest criterion and revise before delivery.

    line 113

“Common” is measured: kept by at least 6 in 10 of the 10 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

IG Carousel -- Plan high-performing Instagram carousels

Key references:

  • references/format-specs.md -- dimensions, slide count limits, text sizing
  • references/hook-library.md -- proven hook patterns with performance data
  • references/content-rules.md -- brand voice, banned topics, caption rules
  • references/scoring-system.md -- engagement scoring criteria and thresholds

Phase 1: Context

  1. Confirm the topic and goal (educate, convert, build authority, entertain).
  2. Identify the target audience segment if not obvious.
  3. Load all key reference files before proceeding.
  4. Check hook-library.md for the highest-performing hook category matching this topic.

Phase 2: Cover Slide Hook

The cover slide follows the same rules as Reel hooks: it must stop the scroll within 1 second.

Cover Hook Rules

  • Maximum 8 words on the cover image
  • Must create a curiosity gap or emotional trigger
  • Use one of these proven patterns from hook-library.md:
    • Contrarian: "Hoer auf mit [common advice]"
    • Numbered list: "5 Fehler, die dein Training ruinieren"
    • Before/After: Visual transformation tease
    • Question: "Warum nimmst du nicht ab?"
    • Bold claim: "Das veraendert ALLES"
  • Font must be large, bold, and readable at thumbnail size
  • No logo or branding on the cover (it kills curiosity)

Document the chosen hook pattern and exact cover text.

Phase 3: Slide Structure

Follow the Hook > Content > Reveal > CTA arc:

SlideRoleRules
1Hook / CoverMax 8 words, curiosity gap, see Phase 2
2-3Problem / SetupEstablish the pain point or question
4-7Content / ValueOne idea per slide, max 15 words on-slide
8-9Reveal / PayoffDeliver the insight or transformation
10CTASave-focused or "Part 2" tease

Slide Content Rules

  • One idea per slide. If you need a comma, you need a new slide.
  • Max 15 words per slide (text overlay). Fewer is better.
  • Visual consistency: same background style, font, and color palette across all slides.
  • Reading direction: top-to-bottom, left-to-right. No scattered text.
  • Swipe motivation: each slide must create a reason to see the next one.

Build out each slide with:

  1. Slide number
  2. Headline text (on-slide, max 15 words)
  3. Supporting visual description
  4. Swipe motivation note (why they will swipe to the next slide)

Phase 4: Last Slide CTA

The final slide determines whether the post gets saved or shared. Choose one:

CTA TypeWhen to UseExample (German)
Save CTAEducational content"Speichere dir das fuer spaeter"
Share CTARelatable content"Teile das mit jemandem, der das braucht"
Part 2 TeaseSeries content"Teil 2 kommt morgen. Folgen, damit du es nicht verpasst"
Comment CTAOpinion content"Welcher Punkt trifft auf dich zu? Schreib 1, 2 oder 3"
DM CTALead generation"Schreib mir PLAN und ich schick dir meinen Guide"

The CTA must be specific. Never use generic "Link in Bio" as the primary CTA.

Phase 5: Caption

Write a caption that complements (not repeats) the carousel content:

  • First line: hook that works even without seeing the carousel
  • Body: expand on one point from the carousel, add personal perspective
  • End: CTA matching the last slide
  • Hashtags: 3-5 niche hashtags, no generic ones (#fitness, #motivation are banned)
  • Max 300 words

Phase 6: Scoring

Score the carousel using scoring-system.md criteria:

CriterionWeightScore (1-10)
Hook strength25%
Slide flow / swipe motivation20%
Value density20%
CTA effectiveness15%
Visual consistency10%
Caption quality10%

Minimum passing score: 7.0 weighted average.

If below 7.0, identify the weakest criterion and revise before delivery.

Phase 7: Delivery

Output format:

## Carousel Brief

**Topic:** [topic]
**Goal:** [goal]
**Slides:** [count]
**Hook Pattern:** [pattern from hook-library.md]
**Score:** [X.X / 10]

### Slide Breakdown

#### Slide 1 (Cover)
- Text: "[cover text]"
- Visual: [description]

#### Slide 2
- Text: "[text]"
- Visual: [description]
- Swipe motivation: [why they swipe]

...

### Caption
[full caption text]

### Production Notes
- [design notes, asset needs, font/color suggestions]

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.