Skills replicate-video-ad

📦

replicate-video-ad

Name: replicate-video-ad
Author: jingyi-wu-richael

Content revision r1 Safe 🌐 Network access📁 Filesystem access⚡ Contains scripts⚙️ External commands

Turn Reference Videos Into Ecommerce Ad Prompts

Recreating a successful video ad from observation is slow and inconsistent. This skill converts reference footage into an evidence-based timeline and production-ready adaptation prompt.

Supports: Claude Codex Code(CC)

🥇 83 Gold

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "replicate-video-ad" from https://skillstore.io/skills/jingyi-wu-richael-replicate-video-ad.md and its manifest at https://skillstore.io/api/skills/jingyi-wu-richael-replicate-video-ad/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/jingyi-wu-richael-replicate-video-ad.md Signed manifest GET /api/skills/jingyi-wu-richael-replicate-video-ad/manifest Signed lockfile GET /api/skills/jingyi-wu-richael-replicate-video-ad/lockfile

Test it

Using "replicate-video-ad". Analyze a 30-second cleaning product video and adapt its structure for a cordless vacuum.

Expected outcome:

A timestamped shot timeline shows the mess, escalating time pressure, vacuum reveal, visible pickup path, clean-floor proof, payoff, and final offer.

Using "replicate-video-ad". Create a vertical skincare ad prompt from this reference without inventing product claims.

Expected outcome:

The production pack separates observed visuals from adaptation choices, keeps benefit claims as placeholders, and provides clean-footage and post-production text directions.

Using "replicate-video-ad". Prepare a generation plan for a reference video with difficult character continuity.

Expected outcome:

The plan divides the story into linked segments with stable wardrobe, room, product, lighting, start states, end states, and shared reference guidance.

Security Audit

Safe

v2 • 8/25/2026 Open versioned report

All 31 static alerts are false positives caused by installation examples, Markdown formatting, expected media-processing operations, and Simplified Chinese text. The extractor uses argument-list subprocess calls without a shell, limits URL inputs to HTTP(S), and writes only requested media artifacts.

Files scanned

886

Lines analyzed

Review items

False positives ignored

Risk Factors

🌐 Network access (2)

README.md:34 README.zh-CN.md:34

📁 Filesystem access (13)

README.md:33 README.md:35 README.md:33 README.md:35 README.zh-CN.md:33 README.zh-CN.md:35 README.zh-CN.md:33 README.zh-CN.md:35 scripts/extract_video.py:13 scripts/extract_video.py:175 scripts/extract_video.py:178 scripts/extract_video.py:14 scripts/extract_video.py:230

⚡ Contains scripts (1)

scripts/extract_video.py:220

⚙️ External commands (12)

scripts/extract_video.py:21 SKILL.md:29 SKILL.md:33 SKILL.md:37-41 SKILL.md:41-43 SKILL.md:43 SKILL.md:45 SKILL.md:57-63 SKILL.md:63-110 SKILL.md:110-111 SKILL.md:111-112 SKILL.md:112-113

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/jingyi-wu-richael-replicate-video-ad/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/jingyi-wu-richael-replicate-video-ad/security.svg)](https://skillstore.io/skills/jingyi-wu-richael-replicate-video-ad?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/jingyi-wu-richael-replicate-video-ad?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/jingyi-wu-richael-replicate-video-ad/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/jingyi-wu-richael-replicate-video-ad.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

jingyi-wu-richael. (2026). replicate-video-ad security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/jingyi-wu-richael-replicate-video-ad/audits/2

BibTeX citation

@techreport{jingyi-wu-richael-jingyi-wu-richael-replicate-video-ad-2026,
  author = {jingyi-wu-richael},
  title = {replicate-video-ad security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/jingyi-wu-richael-replicate-video-ad/audits/2},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "replicate-video-ad security audit report (audit version 2)"
version: "unspecified"
type: report
authors:
  - name: "jingyi-wu-richael"
date-released: "2026-08-25"
url: "https://skillstore.io/skills/jingyi-wu-richael-replicate-video-ad/audits/2"
identifiers:
  - type: other
    value: "skillstore:jingyi-wu-richael-replicate-video-ad:audit:2"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Adapt a Proven Ad Structure

Translate a reference ad's pacing and conversion sequence into a prompt for another product.

Build a Shot-Level Production Brief

Create a timestamped timeline, storyboard, and continuity notes before filming or generation.

Study Short-Form Ad Mechanics

Identify hooks, reversals, proof beats, and calls to action from visible evidence.

Try These Prompts

Analyze a Local Video

Analyze the attached video. Create a shot timeline and identify its hook, product bridge, proof, payoff, and CTA.

Adapt the Story for a Product

Analyze this reference video and adapt its structure for 【产品名】. Preserve pacing and framing. Mark every unverified claim as a placeholder.

Create a Platform Production Pack

Turn this reference into a 30-second vertical ad for 【平台】. Include a timeline, master prompt, dialogue direction, subtitle plan, and negative constraints.

Design a Segmented Generation Workflow

Analyze the source and create independently generatable segments. Define continuity anchors, start and end states, product proof, post-production text, and unresolved claims.

Best Practices

Provide a local source file when possible and confirm that you may analyze it.
Supply verified product facts, target platform, duration, language, and desired adaptation level.
Review sampled frames, transcript gaps, placeholders, and continuity anchors before generation.

Avoid

Do not request copied faces, voices, watermarks, account names, or platform interfaces.
Do not treat inferred dialogue or unverified product benefits as established facts.
Do not describe high-density sampling as analysis of every encoded frame.