blitzreels-carousels

blitzreels-carousels is a skill for Claude Code from blitzreels/agent-skills. It costs 32 tokens per session (368 once invoked), scanned A, original, MIT.

A tool for creating swipeable still-image carousels, with one exported image for each slide. It supports prompted backgrounds or importing existing media, then checks the slide layout before exporting a ZIP of images.

In plain words
What is it for?
Use it for multi-image social posts, photo-mode posts, or swipe decks. It can create, preview, revise, and export carousel slides for a chosen platform and aspect ratio.
Why use it?
It organizes carousel creation into a project with ordered slides and helps catch problems such as bad cropping, unreadable text, low contrast, or unsafe placement near platform edges.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the blitzreels plugin — 5 skills, 1 MCP server shipped together

Good fit Use it for multi-image social posts, photo-mode posts, or swipe decks. It can create, preview, revise, and export carousel slides for a chosen platform and aspect ratio.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blitzreels/agent-skills/blitzreels-carousels
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add blitzreels/agent-skills --skill blitzreels-carousels
Clone the repo
git clone --depth 1 https://github.com/blitzreels/agent-skills

Made for: Claude Code.

Or install blitzreels, the plugin that ships this one along with the rest of its 5 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for blitzreels-carousels

README.md
[![agentmods](https://agentmods.dev/badge/skills/blitzreels/agent-skills/blitzreels-carousels/github.svg)](https://agentmods.dev/skills/blitzreels/agent-skills/blitzreels-carousels)
Your own site
<a href="https://agentmods.dev/skills/blitzreels/agent-skills/blitzreels-carousels"><img src="https://agentmods.dev/badge/skills/blitzreels/agent-skills/blitzreels-carousels/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for blitzreels-carousels

Your own site · 80×15
<a href="https://agentmods.dev/skills/blitzreels/agent-skills/blitzreels-carousels"><img src="https://agentmods.dev/badge/skills/blitzreels/agent-skills/blitzreels-carousels.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00368
Opus 5 $0.00016 $0.00184
Sonnet 5 $0.00006 $0.00074
Haiku 4.5 $0.00003 $0.00037

Measured 11d ago against content hash fe6a7d39a588, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

blitzreels-carousels scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/blitzreels-carousels/SKILL.md · 37 lines

What it actually says

BlitzReels Carousels

Build a carousel project and export individual slide images. Do not assume platform ranking behavior or hardcode a generation model or price.

Workflow

  1. Confirm platform, aspect ratio, slide count, source material, and whether text should be baked into the slides.
  2. Draft one purpose per slide: hook, ordered value, and final action when relevant.
  3. Create a project with project_type: "carousel" and current platform-safe metadata.
  4. Load the current carousel-generation schema from OpenAPI.
  5. Choose the build path.
    • Use one-call generation for prompted, solid, gradient, or mixed backgrounds.
    • Use media import plus timeline placement when every image already exists and manual control is needed.
  6. If generation returns a job ID, poll it to a terminal state before preview or export.
  7. Read timeline context and render representative slides. Check order, crop, text wrapping, contrast, and safe areas.
  8. Fix the project, then export a ZIP of slide images unless the user explicitly requests a video.
  9. Poll the export and verify the archive format and slide count.

Content rules

  • Preserve the user's voice and claims; do not add unsupported performance promises.
  • Keep slide copy scannable and visually balanced.
  • Describe background scenes concretely when generation is requested.
  • Treat safe-area presets as metadata until rendered frames prove the placement.

Completion

Return the project ID, slide count, generation status, preview evidence, export status, and archive location. The task is incomplete if generated assets are still pending or the exported archive has not been verified.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 37 lines · 32 tokens per session scan A fe6a7d39a588

Subscribe to this mod's changes

blitzreels-carousels is a skill published in the GitHub repository blitzreels/agent-skills (3 stars, last pushed 11d ago), licensed MIT. It adds 32 tokens to every session and 368 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

authoring-video-templates

Use when creating or editing a video template JSON (the template descriptor), adding or changing sections/filters/maps/variables/transitions/looks/motion/audio/layers, or debugging template validation errors in ffmpeg-video-composer.

heristop/leclap · 51 tokens

core-architecture-patterns

Use when adding a segment type, platform adapter, editor manager, core service, or descriptor effect (look/grade/motion/section-audio field) in packages/ffmpeg-video-composer, or when wiring new dependencies into the tsyringe container.

heristop/leclap · 58 tokens

ondevice-ffmpeg-engine

Use when building, modifying, or consuming the on-device FFmpeg engine — the Rust crate packages/ffmpeg-engine, the leclap-ffmpeg Expo native module, the run/probe/version/cancel API, the uniffi bindings, build-engine.sh, or the FFmpeg-from-source toolchain in scripts/ffmpeg.

heristop/leclap · 75 tokens

cross-platform-ffmpeg

Use when working with FFmpeg across Node/Static/WASM, the PlatformBridge, the FFmpeg detection/fallback chain, or browser/React Native runtime constraints in ffmpeg-video-composer.

heristop/leclap · 45 tokens

kling-studio

Full-featured Kling 3.0 Omni video generation skill. Covers text-to-video, image-to-video, video editing (base mode), video reference (feature mode), multi-shot generation, and audio-synced video. Includes validated API constraint rules and prompt engineering guide.

wells1137/media-skills · 60 tokens

seedance-prompt

This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.

Emily2040/seedance-2.0 · 68 tokens