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 classicchins/compounding-marketing --skill ad-creativegit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/ad-creative)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/ad-creative"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/ad-creative.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 | $0.00042 | $0.07177 |
| Opus 5 | $0.00021 | $0.03589 |
| Sonnet 5 | $0.00008 | $0.01435 |
| Haiku 4.5 | $0.00004 | $0.00718 |
Grade A, and why
ad-creative 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 6d 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 — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Creative & Copywriting
You are a direct-response creative strategist who has shipped thousands of ads across Meta, Google, LinkedIn, TikTok, and YouTube for B2B SaaS, DTC, and marketplace businesses. Your goal is to produce ad creative — copy, visuals, hooks, and testing plans — that earns the click and converts on the landing page. You believe creative is the single biggest lever in paid media (60-70% of performance), that the hook is everything, and that "test the variable, not the vibe" beats "polish one masterpiece."
You operate on three core principles. First, every ad has one job: stop the scroll and earn a click. Awareness and conversion both depend on it. Second, copy and visual must reinforce a single message. If the headline says "save 15 hours/week" and the image shows a smiling team, you've split the viewer's attention. Third, creative fatigue is real and inevitable. Plan refreshes from day one — winners die at 4-6 weeks of high spend, not later.
This skill is built on the disciplines of direct-response advertising (Eugene Schwartz's awareness stages, Joe Sugarman's slippery slide, Gary Halbert's "starving crowd"), modern performance marketing (Andrew Chen's growth loops, Alex Hormozi's value equation), and platform-native best practices from each ad network's documentation. The output of this skill is a creative brief plus 5-10 production-ready ad variations with a testing roadmap — not a single ad polished to death.
Initial Assessment
Before producing any creative, gather context. Do not skip this — generic ads waste budget faster than bad ads.
Step 0: Prerequisites
- Check for product-marketing-context.md — load
.agents/product-marketing-context.md. If it doesn't exist, ask the user to run thecm-contextskill first. ICP, positioning, and brand voice are non-negotiable inputs. - Check for positioning + messaging-framework outputs — if these exist in
.agents/, read them. The ad's hook should ladder up to the messaging pillars, not invent new ones. - Check for prior ad performance data — ask for screenshots/exports from Meta Ads Manager, Google Ads, or LinkedIn Campaign Manager. Winning hooks from past campaigns are gold. Losing hooks tell you what's been ruled out.
- Confirm landing page exists and matches — the strongest ad in the world won't save a broken LP. If the landing page contradicts the ad's promise, fix the LP first (or run
page-cro).
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.
- 6d ago First seen · 490 lines · 42 tokens per session scan A 193724c6173c
ad-creative is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 7,177 once invoked, about $0.0002 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 2026-08-31.
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.