agentmods.dev

carousel-builder

carousel-builder is a skill for Claude Code from naveedharri/benai-skills. It costs 132 tokens per session (1,749 once invoked), scanned A, original, MIT.

A workflow that turns supplied source content into an image-first social media carousel and exports it as a PDF. It writes the slide text, renders the slides, adds the fixed brand elements, and produces the final document.

In plain words
What is it for?
Use it to create Ben AI authority carousels from a newsletter, video transcript, LinkedIn post, or brief.
Why use it?
It keeps the carousel focused on one clear point and separates content building from finding source material or publishing it. The exported PDF can be used as the finished deliverable.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the benai-marketing plugin — 13 skills shipped together

not rated 61repo +1 6d ago A scan SkillSpector: pass 132 tokens original MIT

Good fit Use it to create Ben AI authority carousels from a newsletter, video transcript, LinkedIn post, or brief.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/naveedharri/benai-skills/carousel-builder
View source ↗ naveedharri/benai-skills
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 naveedharri/benai-skills --skill carousel-builder
Clone the repo
git clone --depth 1 https://github.com/naveedharri/benai-skills

Made for: Claude Code.

Or install benai-marketing, the plugin that ships this one along with the rest of its 13 skills.

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 carousel-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/naveedharri/benai-skills/carousel-builder/github.svg)](https://agentmods.dev/skills/naveedharri/benai-skills/carousel-builder)
Your own site
<a href="https://agentmods.dev/skills/naveedharri/benai-skills/carousel-builder"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/carousel-builder/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 carousel-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/naveedharri/benai-skills/carousel-builder"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/carousel-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,749 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00132 $0.01749
Opus 5 $0.00066 $0.00874
Sonnet 5 $0.00026 $0.00350
Haiku 4.5 $0.00013 $0.00175

Measured 4d ago against content hash ead91eed3a5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

carousel-builder 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/footer.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/benai-marketing/skills/carousel-builder/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Turn one piece of source content that is handed to you into a finished Ben AI image-first authority carousel (Type B) and export a print-ready PDF. Slides render with Higgsfield GPT Image 2; the footer bar is composited by code so the logo, avatar, and page numbers are always correct.

Scope. This skill only builds the carousel from content it is given, and returns the PDF. It does not scan inboxes, choose which email to use, schedule anything, or post to Slack. An orchestrator (a person, or the daily routine) finds the source, invokes this skill, and handles delivery. Keep this skill focused on the build.

The carousel must make its point on its own (assume the social caption is one line).

Before you start (every run)

  1. Read references/brand-and-copy.md (palette, type, voice, copy architecture, hard rules).
  2. Read references/render-pipeline.md (exact render + footer + PDF commands, both the Higgsfield connector and the CLI paths).
  3. Scan assets/templates/type-b-image-first.png (the look) and assets/example/ (a finished reference carousel: 6 slides).

Step 1: Read the source, find the ONE point

Accept whatever content is provided: a newsletter body, a YouTube transcript, LinkedIn/post copy, or a brief. Identify the single argument the carousel makes: one point, backed up. If the source only teases (e.g. "watch my video"), reconstruct the real substance so the carousel stands alone. If the source has several disconnected ideas, pick the most useful one.

Step 2: Slide count and architecture (3-10)

Pick the count from the content (typical 5-8, lower lands harder). Build an arc:

  • Slides 1-3 = big-header, high-impact. Cover/hook (with Ben's portrait), problem, first turn to the solution. One large headline + one yellow highlight + short body.
  • Middle slides = text-heavier substance. Deliver the actual method: a smaller header plus 2-4 short bullets, numbered steps, or a simple labeled graphic. One idea per slide. This is what makes the carousel self-contained.
  • Final slide = a CTA that makes sense (follow / watch the full breakdown / grab the skill). Never a CTA that leans on context the slides never gave.

Read the full file on GitHub · 100 lines

Files

What ships with it

13 files 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. 4d ago First seen · 100 lines · 132 tokens per session scan A ead91eed3a5a

Subscribe to this mod's changes

carousel-builder is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 6d ago), licensed MIT. It adds 132 tokens to every session and 1,749 once invoked, about $0.0007 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 2026-09-05.

Claude CodeCreative and mediaDesign and UXagent-skillsaianthropicclaudeclaude-plugins
Related

Other skills, from other repositories

design-logo

A brand-aware logo design workflow that reads a project's visual rules, chooses a logo type, and prepares a vector or symbol-based logo request.

modu-ai/moai-cowork · 311 tokens

design-brand-visual

A brand-aware image prompt workflow that reads a project's colours, typography, spacing, shape rules, and brand voice before preparing a visual.

modu-ai/moai-cowork · 214 tokens

baoyu-infographic

An infographic generator that turns supplied content into a visual summary using different information layouts and visual styles. It supports standard and custom image proportions and multiple languages.

NousResearch/hermes-agent · 23 tokens

flier

Design a print-ready, single-page flier as one self-contained HTML file: exactly one fixed-size page.

asgeirtj/system_prompts_leaks · 7 tokens

visualize

Render a polished visual inline in the chat as part of your answer — a diagram, a chart, an interactive explainer, or a UI mockup. Load it proactively whenever an explanation would land better as a picture than as prose. Do not wait to be asked.

vellum-ai/vellum-assistant · 57 tokens

vellum-avatar

Customize the assistant's avatar - build a native character, upload an image, or generate one with AI.

vellum-ai/vellum-assistant · 24 tokens