clone-video-ad

clone-video-ad is a skill for Claude Code from novoads/agent-skills. It costs 233 tokens per session (13,603 once invoked), scanned A, original, MIT.

A workflow for recreating an existing video advertisement for a different product or offer through the Novoads API, ending with a rendered MP4 video.

In plain words
What is it for?
Use it to analyze a source ad, adapt its structure and tone to another product, and render the complete replacement advertisement.
Why use it?
It converts the source ad’s dialogue, pacing, camera work, visual style, and beat structure into a new production instead of providing only a reusable formula.

Skill for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/check-novoads-env.sh.

Part of the skills plugin — 17 skills, 1 hook shipped together

Good fit Use it to analyze a source ad, adapt its structure and tone to another product, and render the complete replacement advertisement.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/novoads/agent-skills
agentmods
npx agentmods add skills/novoads/agent-skills/clone-video-ad

Made for: Claude Code.

Or install skills, the plugin that ships this one along with the rest of its 17 skills, 1 hook.

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 clone-video-ad

README.md
[![agentmods](https://agentmods.dev/badge/skills/novoads/agent-skills/clone-video-ad/github.svg)](https://agentmods.dev/skills/novoads/agent-skills/clone-video-ad)
Your own site
<a href="https://agentmods.dev/skills/novoads/agent-skills/clone-video-ad"><img src="https://agentmods.dev/badge/skills/novoads/agent-skills/clone-video-ad/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 clone-video-ad

Your own site · 80×15
<a href="https://agentmods.dev/skills/novoads/agent-skills/clone-video-ad"><img src="https://agentmods.dev/badge/skills/novoads/agent-skills/clone-video-ad.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 233 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,603 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 11 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 93
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Data Exfiltration · line 201
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 201
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 206
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 571
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 621
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 678
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 718
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 734
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Agent Snooping · line 238
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Data Exfiltration · line 571
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00233 $0.13603
Opus 5 $0.00117 $0.06802
Sonnet 5 $0.00047 $0.02721
Haiku 4.5 $0.00023 $0.01360

Measured 8d ago against content hash 4b246590500a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

clone-video-ad 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 8d 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.

curl -sS -X POST https://api.novoads.ai/v1/uploads \
skills/clone-video-ad/SKILL.md · 840 lines

How it starts

The opening of the file, as written. The whole thing — 840 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clone ad — Seedance 2.0

Clone an existing video ad for a different product. You analyze the source frame by frame, transcribe the dialogue, extract the visual style and beat structure, then generate a new seedance-2.0 video adapted for the user's product.

How this differs from analyze-video:

  • analyze-video → the output is a reusable markdown formula saved to prompt-library/.
  • clone-video-ad → the output is a rendered video delivered to the user.

Steps 1 to 3 are the same analysis in both. The only charge in that half is the transcript in step 2 — a fraction of a credit, and free on a re-read of the same source. Everything from step 9 on is the real spend.

If shared/ is missing from disk

references/solo-install.md — what a solo install lacks (craft.md, caption-video, the b-roll scripts, check-novoads-env.sh, MASTER_CONTEXT.md) and how to fetch each. Skip it inside the full pack.

Read order

This skill links outward more than any other here, and its two biggest targets fan out again (22 and 10 further links). A file reached through another file gets skimmed, not read, so open these four directly, in order. Everything else is lookup.

  1. This file — workflow, gates, the constraints that bite.
  2. ../novoads-api/prompting/prompt-library/seedance-2.md — fields, grid, prompt craft, what the estimate flags. Before composing a prompt, not when one fails.
  3. One formula matched to the source, not all: seedance-2-ugc.md talking-head, -feature-walkthrough demo, -premium-reveal / -product-hero product-only, -studio-lookbook polished. Same directory as (2).
  4. ../../shared/references/craft.md § 1 — the transcribe-verify doctrine step 12 rests on.

../novoads-api/SKILL.md is the contract, not a step: open it when a response shape or an error code needs settling.

What this API changes about cloning

The analysis half is nearly untouched: frames and the beat structure are local work on the user's file, and the transcript is one cheap API call instead of a local install (step 2). The generation half has three differences worth knowing before you promise anything. All three were established with free 400 probes that reject before any charge, and re-verified field-for-field against the deployed spec 2.12.0 (2026-08-06):

Read the full file on GitHub · 840 lines

Files

What ships with it

3 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. 8d ago First seen · 840 lines · 233 tokens per session scan A 4b246590500a

Subscribe to this mod's changes

clone-video-ad is a skill published in the GitHub repository novoads/agent-skills (14 stars, last pushed 13d ago), licensed MIT. It adds 233 tokens to every session and 13,603 once invoked, about $0.0012 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

xiaohongshu-auto-posting

Automates the complete Xiaohongshu (XHS / Little Red Book) content operation workflow: pain-point topic collection → style case collection → topic selection → content writing → publishing → performance tracking. Use when user mentions xiaohongshu auto posting, xhs auto post, little red book posting, xiaohongshu post…

browser-act/skills · 182 tokens

muapi-seedance-2

Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal.

SamurAIGPT/Generative-Media-Skills · 67 tokens

muapi-social-media-video

Brand-aware social media video creator. Reads brand-identity.md, ICP.md, and messaging.md to write a post/storyboard, craft an optimized Seedance 2.0 Director prompt, generate reference frames with the best available image model, and produce platform-ready video.

SamurAIGPT/Generative-Media-Skills · 60 tokens

muapi-ai-clipping

Turn a long video into N viral-ready short clips with a single managed API call. Wraps muapi.ai's /ai-clipping endpoint, which handles transcription, highlight ranking through a virality framework (hook / emotional peak / opinion bomb / revelation / conflict / quotable / story peak / practical value), overlap dedupe…

SamurAIGPT/Generative-Media-Skills · 96 tokens

muapi-youtube-shorts

Auto-generate viral 9:16 YouTube Shorts (or TikTok / Reels clips) from a long-form video. Thin platform-aware wrapper around the AI Clipping skill — picks sensible defaults for short-form social platforms (9:16, 30–60s sweet spot) and delegates the actual highlight extraction + crop to muapi.ai's /ai-clipping endpoint.

SamurAIGPT/Generative-Media-Skills · 85 tokens

muapi-workflow

Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.

SamurAIGPT/Generative-Media-Skills · 44 tokens