ai-image-editing
The AI image-editing router — inpainting/object removal, background removal, upscaling, outpainting, old-photo restoration, and retouch, routed task-first to…
Use to write a carousel — a swipeable multi-slide post (Instagram carousel, LinkedIn document/PDF carousel, or TikTok photo carousel) — one of the highest-save, highest-dwell formats. Run when the user says "write a carousel," "carousel post," "slides for X," "LinkedIn
$ npx -y skills add social-media-skills/skills --skill carousel-writer --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/carousel-writerContext preview
The summary Claude sees to decide when to auto-load this skill.
Use to write a carousel — a swipeable multi-slide post (Instagram carousel, LinkedIn document/PDF carousel, or TikTok photo carousel) — one of the highest-save, highest-dwell formats. Run when the user says "write a carousel," "carousel post," "slides for X," "LinkedIn
name: carousel-writer description: >- Use to write a carousel — a swipeable multi-slide post (Instagram carousel, LinkedIn document/PDF carousel, or TikTok photo carousel) — one of the highest-save, highest-dwell formats. Run when the user says "write a carousel," "carousel post," "slides for X," "LinkedIn document/PDF post," "swipe post," "turn this into a carousel," or wants multi-slide teaching or story content. Reads brand-profile and voice first; the cover slide hooks and promises the swipe (via hook-writer); each slide advances one idea and earns the next swipe; ends on a save-leaning CTA. Specifies the design direction and bundles an image-generation prompt pack (Nano Banana / Ideogram) for the slide visuals. Hands the caption to caption-writer and scheduling to scheduling-and-queue. metadata: version: 1.0.0 license: MIT
A carousel is a swipeable teaching-or-story post — and one of the best formats there is for **saves** and **dwell time** (both strong ranking signals). But it only works if people swipe, and they only swipe if each slide earns the next. So this skill is opinionated about the cover, the one-idea-per-slide discipline, and keeping slides legible — not dumping paragraphs onto images.
Three principles:
1. **The cover slide is the whole game.** Slide 1 must hook *and* promise the payoff — it decides whether anyone swipes past it. Treat it like a thread opener or a Reel hook. 2. **One idea per carousel, one idea per slide.** A cohesive arc across slides, each advancing it by one beat. A slide crammed with three points loses the swipe. 3. **It's copy *and* design.** Minimal, legible text per slide; a clear visual hierarchy. A carousel is read at a glance on a phone — walls of text kill it.
Load `brand-profile.md` and `voice.md`. Voice applies to every slide (concise) and to the caption. Carry guardrails and any compliance/disclosure rules.
or TikTok photo carousel. Specs differ (see `references/platform-specs.md`).
Use `hook-writer`. The cover must hook (stop the scroll) **and** promise what the swipe delivers ("5 hooks that actually work →"). It must be legible at a glance and at thumbnail size. No slow-build cover. See `references/slide-craft.md`.
Pick a structure (how-to, listicle, story, before→after, myth-bust, framework — see `references/architecture.md`) and outline the **spine**: the cover's promise and the ordered slides that deliver it. One idea per slide. Decide slide count by the idea, not a target — a tight 6 beats a padded 10.
Each slide: a clear **headline** + at most a short supporting line, front-loaded and legible. Maintain swipe momentum (progress, a small pull forward). Keep every slide in the brand voice and ruthlessly minimal — if it needs a paragraph, it's two slides. See `references/slide-craft.md`.
End with a payoff/summary slide, then a CTA slide. Carousels win on **saves**, so the default CTA is "save this for later" (plus optionally follow/comment). One ask. A link, if any, goes to the caption/bio/first comment per platform.
A carousel is visual. Provide:
(consistency is what makes it look pro).
legible in-image text) to produce on-brand slides, with the exact slide text specified. Or a clean template spec for Canva/a designer. Flag **AI-disclosure** for generated images. See `references/image-prompt-pack.md`. (For deeper visual systems, see `design-and-templates`.)
one. Offer the strongest N, not a quota.
a text argument may be a thread. Say so rather than forcing a carousel.
`cross-platform-repurposing`).
branded background; don't block on production.
Give your AI agent the skills of a top-1% social media team. 106 of them, free.
The AI image-editing router — inpainting/object removal, background removal, upscaling, outpainting, old-photo restoration, and retouch, routed task-first to…
The AI music + sound-design skill for social -- original/licensed audio beds and sound design for Reels/TikToks/Shorts/videos. Use when someone needs…
Use to get a brand and its content CITED and RECOMMENDED by AI answer engines — the GEO (Generative Engine Optimization) / AI-search-visibility skill. Run when…
The model-agnostic AI-video router and brief — the counterpart to image-prompt. Use when someone asks "which AI video tool should I use," "make an AI video,"…
The AI narration / voiceover mini-skill (ElevenLabs-led). Use when someone wants an "AI voiceover," "narration," "text-to-speech for a video," "voice for my…
Social media analytics and reporting — read native platform data honestly and turn it into next actions. Use when someone wants to "check my analytics," "see…