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.
npx skills add crealwork/ai-marketing-kit --skill ad-videogit clone --depth 1 https://github.com/crealwork/ai-marketing-kitWrote 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.
[](https://agentmods.dev/skills/crealwork/ai-marketing-kit/ad-video)<a href="https://agentmods.dev/skills/crealwork/ai-marketing-kit/ad-video"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/ad-video/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.
<a href="https://agentmods.dev/skills/crealwork/ai-marketing-kit/ad-video"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/ad-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00115 | $0.01010 |
| Opus 5 | $0.00057 | $0.00505 |
| Sonnet 5 | $0.00023 | $0.00202 |
| Haiku 4.5 | $0.00012 | $0.00101 |
Grade A, and why
ad-video 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 10d 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.
What it actually says
Ad Video
모션그래픽 + AI 생성 비주얼로 광고 영상을 만든다. 렌더 엔진은 HyperFrames (HTML→video), 비주얼 소스는 image-gen 정책(Higgsfield CLI), 성과 원칙은 A/B 변형 — 영상도 1개만 뽑으면 학습 없는 지출이다.
전제: hyperframes 스킬 설치 필수 (없으면 npx skills add heygen-com/hyperframes --all).
이 스킬은 워크플로우 오케스트레이터 — 렌더 규칙은 hyperframes가 소유한다.
Workflow
1. 브리프 (한 번에). 무엇을 파는가(제품/URL), 타깃 플레이스먼트(Reels/TikTok 9:16, 피드 1:1, YouTube 16:9), 길이(기본 30s, 범위 15–60s), 훅 후보, 브랜드 토큰 (DESIGN.md — 없으면 brand-guide 먼저), CTA. 광고 집행까지 갈 거면 예산/기간은 paid-ads 게이트에서 — 이 스킬은 제작만.
2. 라우팅 (hyperframes 규칙 준수).
- 제품/사이트가 있으면 →
/product-launch-video(사이트 캡처 + 브랜드 토큰) - 모션이 곧 메시지인 ≤10s 컷 →
/motion-graphics - 소재만 있는 자유 구성 →
/general-video라우팅 후npx hyperframes skills update <workflow>— 라우터 지시대로.
3. AI 비주얼 (image-gen 정책 그대로).
- 장면용 이미지가 필요하면 image-gen 스킬로: Higgsfield CLI 경유, 기본 gpt_image_2, 폴백 금지, 생성물 READ 검증. 텍스트는 이미지에 굽지 않는다 — 카피는 전부 HyperFrames 타이포 레이어로.
- 제품 누끼:
rembg+birefnet-portrait(인물) — 로컬, 무료. - BGM/SFX/아이콘은 media-use 스킬로 해결 (로열티프리만).
4. A/B 변형 (MANDATORY). 캠페인당 최소 2개, 권장 3개 — 축을 다르게:
- 훅 축: 첫 3초를 다르게 (숫자 훅 / 문제 제기 / 결과 먼저)
- 비주얼 축: 제품 중심 vs 상황 중심 vs 타이포 중심
공유 씬은 서브컴포지션으로 재사용해 변형 비용을 낮춘다. 네이밍
{campaign}_{hook축}_{visual축}.mp4.
5. 광고 규격 체크 (배포 전 blocking).
- 첫 3초에 훅 + 브랜드 노출 (사운드 오프 시청 전제 — 핵심 카피는 화면 텍스트로)
- 세이프존: 9:16은 상단 ~140px/하단 ~350px에 로드베어링 요소 금지
- 한국어 카피 줄나눔: keep-all, 조사에서 끊지 않기 (humanizer 룰)
- CTA는 마지막 3초 고정 + 로고 엔드카드
- 파일: H.264, 플랫폼 규격 (Meta ≤4GB/240min이지만 실무는 <100MB, 릴스 9:16 ≤90s)
- 렌더 후 프레임 추출 READ: 첫 프레임/훅 카피/CTA/엔드카드 4장 육안 검증
6. 핸드오프. 변형 세트 + 각 변형의 축 설명 한 줄 → 유저 승인 → 집행은 paid-ads(예산 게이트), 오가닉 게시는 organic-social. 24–48h 후 성과로 진 변형 끄고 이긴 축으로 다음 세트.
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.
- 10d ago First seen · 52 lines · 115 tokens per session scan A ae094767730a
ad-video is a skill published in the GitHub repository crealwork/ai-marketing-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 1,010 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.