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 carousel-generatorgit 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/carousel-generator)<a href="https://agentmods.dev/skills/crealwork/ai-marketing-kit/carousel-generator"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/carousel-generator.svg" alt="Measured on agentmods" 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 | $0.00154 | $0.10030 |
| Opus 5 | $0.00077 | $0.05015 |
| Sonnet 5 | $0.00031 | $0.02006 |
| Haiku 4.5 | $0.00015 | $0.01003 |
Grade A, and why
carousel-generator 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 1,003 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Card News Generator (카드뉴스 자동 생성기)
This skill creates professional Instagram/Threads card news (4:5 ratio, 1080x1350px) through a complete pipeline: brand selection, topic confirmation, deep research, card flow planning, HTML generation with neumorphism design, and PNG download capability.
The goal is not just pretty cards -- it's a full content pipeline where research quality and message flow matter more than decoration.
Brand Templates
This generator supports multiple brand presets. If the user doesn't specify a brand, ask which one to use via AskUserQuestion. If context makes the brand obvious (e.g., the user mentions a specific brand name or account), use that preset directly.
The presets below are worked examples (real brands run with this skill in production). Treat them as the template for defining YOUR brand's preset: copy one, swap the account/palette/tone/footer, and add it as a new preset section. If a brand has its own dedicated card-news skill installed, that skill wins over these presets.
Preset: CREAL (댄정 @crealwork)
Account: @crealwork
Brand name: 댄정
Footer text: 댄정 @crealwork
Content domain: AI + Marketing (AI 활용법, 마케팅 자동화, 생산성, 트렌드 등)
Language: Korean
CTA button text: Follow Dan
Tone: 쉽고 실용적인 정보형 -- 전문 용어를 쓰더라도 한 번은 쉽게 풀어서 설명하고, 독자가 "이거 저장해야지"라고 느낄 수 있게 구체적이고 실행 가능한 내용 위주로 쓴다. 가볍지만 근거 있는 톤. 과장하지 않되, 임팩트는 살린다.
Color Palette (CREAL B.I. Guideline):
- Navy (Primary):
#1A2A4F-- headings, key text, dark backgrounds - Yellow (Accent):
#FFCC4E-- highlights, CTAs, emphasis, badges - Black:
#000000-- body text on light backgrounds - White:
#FFFFFF-- text on dark backgrounds - Warm Gray:
#A39F94-- secondary text, dividers, subtle elements - Coral:
#D77A61-- charts, secondary accents - Background:
#F8F5F0(ivory cream) for light mode,#1A2A4Ffor dark mode
Default style: Style A (Light Neumorphism) for general audiences. Logo: CREAL Text logo in footer. White/Yellow on dark, Black/Blue on light.
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.
- 8d ago First seen · 1,003 lines · 154 tokens per session scan A dd0f14b7029a
carousel-generator is a skill published in the GitHub repository crealwork/ai-marketing-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 10,030 once invoked, about $0.0008 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.