generate-youtube-thumbnail-arcads-mcp

generate-youtube-thumbnail-arcads-mcp is a skill for Claude Code, Codex from krusemediallc/cursor-ad-agent. It costs 103 tokens per session (2,135 once invoked), scanned A, original, MIT.

A workflow for creating 16:9 YouTube thumbnails with Nano Banana 2 through the Arcads MCP server, a tool connection that handles authentication and image-generation requests.

In plain words
What is it for?
Use it to make thumbnail concepts for videos, including versions that use a person's face, a product, or brand imagery as references.
Why use it?
It provides the MCP-based version of the thumbnail process and supports reference images plus several concepts in one request.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to make thumbnail concepts for videos, including versions that use a person's face, a product, or brand imagery as references.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/krusemediallc/cursor-ad-agent/generate-youtube-thumbnail-arcads-mcp
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 krusemediallc/cursor-ad-agent --skill generate-youtube-thumbnail-arcads-mcp
Clone the repo
git clone --depth 1 https://github.com/krusemediallc/cursor-ad-agent

Made for: Claude Code, Codex.

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 generate-youtube-thumbnail-arcads-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/krusemediallc/cursor-ad-agent/generate-youtube-thumbnail-arcads-mcp/github.svg)](https://agentmods.dev/skills/krusemediallc/cursor-ad-agent/generate-youtube-thumbnail-arcads-mcp)
Your own site
<a href="https://agentmods.dev/skills/krusemediallc/cursor-ad-agent/generate-youtube-thumbnail-arcads-mcp"><img src="https://agentmods.dev/badge/skills/krusemediallc/cursor-ad-agent/generate-youtube-thumbnail-arcads-mcp/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 generate-youtube-thumbnail-arcads-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/krusemediallc/cursor-ad-agent/generate-youtube-thumbnail-arcads-mcp"><img src="https://agentmods.dev/badge/skills/krusemediallc/cursor-ad-agent/generate-youtube-thumbnail-arcads-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,135 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00103 $0.02135
Opus 5 $0.00051 $0.01068
Sonnet 5 $0.00021 $0.00427
Haiku 4.5 $0.00010 $0.00214

Measured 12d ago against content hash 180095403e73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

generate-youtube-thumbnail-arcads-mcp scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `generate-batch.sh` + curl auth / `.env` | `arcads_generate_image_nano_banana` (MCP handles auth) |
skills/generate-youtube-thumbnail-arcads-mcp/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate YouTube Thumbnail (Arcads MCP)

Create high-CTR YouTube thumbnails with Nano Banana 2 at 16:9 through the Arcads MCP server, with proper character likeness and proven CTR formulas.

This is the MCP-native version of generate-youtube-thumbnail. No .env, no HTTP Basic auth, no generate-batch.sh, no manual presigned-upload pipeline.

REST generate-youtube-thumbnail step MCP replacement
generate-batch.sh + curl auth / .env arcads_generate_image_nano_banana (MCP handles auth)
POST /v2/images/generate nano-banana-2 arcads_generate_image_nano_banana(model="nano-banana-2")
presigned upload + S3 PUT (in-script) arcads_get_upload_url + PUT (explicit — see Uploading)
GET /v1/assets/{id} polling loop arcads_watch_asset (status and URL in one call)
N parallel POSTs for N concepts nbGenerations (1–10) in a single call
productId from MASTER_CONTEXT auto-selects (one product)

Tools used (Arcads MCP)

Tool Role
arcads_generate_image_nano_banana Generate thumbnails. model:"nano-banana-2", aspectRatio:"16:9", referenceImages (face/brand/product), nbGenerations.
arcads_get_upload_url Presigned S3 URL per local reference (face photos, logo, product). Required in remote agent clients such as Cursor.
arcads_watch_asset Poll status and fetch the signed downloadUrl. Primary poll tool.
arcads_list_products Resolve productId (optional — auto-selects).

Key parameters

Param Value Notes
model "nano-banana-2" Up to 14 reference images — pass several face angles for likeness.
aspectRatio "16:9" Always 16:9 for YouTube (renders 2752×1536).
referenceImages array, ≤14 Face headshot + 3/4 angles + expressions; brand/logo; product. S3 filePaths.
nbGenerations 110 A/B variations in one call.

Read order

  1. This file — the MCP workflow, batch generation.
  2. ../../shared/skills/generate-youtube-thumbnail/prompting/guide.md — likeness alignment, expressions cheat sheet, prompt structure.
  3. ../../shared/skills/generate-youtube-thumbnail/prompting/formulas.md — 5 proven CTR formulas with templates. Read before composing.

Read the full file on GitHub · 133 lines

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. 12d ago First seen · 133 lines · 103 tokens per session scan A 180095403e73

Subscribe to this mod's changes

generate-youtube-thumbnail-arcads-mcp is a skill published in the GitHub repository krusemediallc/cursor-ad-agent (10 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 2,135 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

RunAPI Media Generator

A workflow for creating images, videos, music, and audio through RunAPI, a service that provides access to media-generation models. It checks the chosen model and request before submitting the job.

runapi-ai/mcp · 90 tokens

RunAPI Model Explorer

A RunAPI catalogue assistant that lists available AI models, explains their required inputs, and provides current pricing information.

runapi-ai/mcp · 71 tokens

imaginode

Generate AI images and videos through the Imaginode MCP server (imaginode.ai). Use when the user asks to create, generate or illustrate an image, picture, visual, thumbnail, or a short video clip, and the Imaginode MCP tools (generateimage, generatevideo, listmodels, getgenerationstatus) are available.

Frankhoubre/imaginode-mcp · 72 tokens

uni1-image-ad

Use when the user wants to generate a Meta/Facebook image ad with Luma uni-1 and attach it to an existing Meta ad set. Triggers on phrases like "uni-1 ad", "make a Luma ad creative", "new image ad in ", "uni-1 image ad for Meta", "generate uni-1 ad creative", "upload uni-1 image as Meta ad". Anchors on uni-1 + Meta…

krusemediallc/uni1-image-ad · 138 tokens

image-ad-clone

Use when the user wants to reverse-engineer an existing image ad into a reusable, parameterizable prompt template that can be reused with any brand and any product. Triggers on phrases like "clone this ad as a template", "reverse engineer this ad", "turn this ad into a prompt", "extract a template from this image"…

krusemediallc/uni1-image-ad · 126 tokens

distribea-media

Generate or place on-brand media (images, video, music, voice) with Distribea. Use whenever a project needs imagery or audio — a hero/illustration/avatar, a page full of placeholders, a video clip, background music, or a voice-over — instead of shipping stock photos, placeholders, CSS-gradient-only sections, or raw…

Distribea/distribea-mcp · 113 tokens