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 indranilbanerjee/digital-marketing-pro --skill ad-creativegit clone --depth 1 https://github.com/indranilbanerjee/digital-marketing-proWrote 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/indranilbanerjee/digital-marketing-pro/ad-creative)<a href="https://agentmods.dev/skills/indranilbanerjee/digital-marketing-pro/ad-creative"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/digital-marketing-pro/ad-creative/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/indranilbanerjee/digital-marketing-pro/ad-creative"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/digital-marketing-pro/ad-creative.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00162 | $0.01497 |
| Opus 5 | $0.00081 | $0.00749 |
| Sonnet 5 | $0.00032 | $0.00299 |
| Haiku 4.5 | $0.00016 | $0.00150 |
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 12d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/digital-marketing-pro:ad-creative
Purpose
Generate high-performing ad copy variations tailored to specific platforms and formats. Each variation is scored for quality and compliance, with recommendations for testing strategy.
Input Required
The user must provide (or will be prompted for):
- Product/service: What is being advertised
- Platform(s): Google Ads, Meta (Facebook/Instagram), LinkedIn, TikTok, X, Pinterest
- Ad format: RSA, single image, carousel, video script, story, etc. For video ad scripts (6s bumper, 15s skippable, 30s spot, UGC-style), route to /digital-marketing-pro:video-script — its step 2.4 carries the per-format structural rules (the 5-second skip deadline, one-message bumpers, native-style disclosure) and its output passes the /check gate. This skill owns the copy layer around the video: headlines, descriptions, and CTAs.
- Campaign objective: Awareness, traffic, leads, conversions, app installs
- Target audience: Who the ads are for
- Key offer/CTA: Promotion, value prop, or desired action
- Landing page URL: Where the ad will drive traffic (optional)
Process
- Load brand context: Read
~/.claude-marketing/brands/_active-brand.jsonfor the active slug, then load~/.claude-marketing/brands/{slug}/profile.json. Apply brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. Also check for guidelines at~/.claude-marketing/brands/{slug}/guidelines/_manifest.json— if present, load restrictions and relevant category files. Check for custom templates at~/.claude-marketing/brands/{slug}/templates/. Check for agency SOPs at~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults. - Identify platform-specific constraints: character limits, format requirements, policy restrictions
- Generate 3-5 ad copy variations per platform, each with a distinct angle (benefit, urgency, social proof, curiosity, direct)
- Score each variation on: brand alignment, clarity, emotional impact, CTA strength, policy compliance
- Flag any potential policy violations (restricted claims, prohibited language)
- Recommend A/B testing groupings and priority order
- If landing page URL is provided, check message match between ad and page
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.
- 12d ago First seen · 68 lines · 162 tokens per session scan A f06399f15c26
ad-creative is a skill published in the GitHub repository indranilbanerjee/digital-marketing-pro (806 stars, last pushed 4d ago), licensed MIT. It adds 162 tokens to every session and 1,497 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
cf-video-script
Produce a production-ready video script for YouTube, YouTube Shorts, TikTok, Instagram Reels, or explainers — timestamps, scene dialogue, B-roll shot list, on-screen text, and music notes. Every script passes the Phase 3.5 claim-verification gate (contentforge:fact-checker checks each statistic in narration and…
seo-image-gen
AI image generation for SEO assets: OG/social preview images, blog hero images, schema images, product photography, infographics. Powered by Gemini via nanobanana-mcp. Requires banana extension installed. Use when user says "generate image", "OG image", "social preview", "hero image", "blog image", "product photo"…
phase-publish
Run Phase Publish — image generation sub-pipeline (provider-pluggable: relay primary + official OpenAI fallback, realtime-forced) + WordPress publish with RankMath meta + IndexNow ping. Use when draft has passed all quality gates and is ready for live publication. Triggered by /seo-blog publish, /publish, "post this…
openai-image-generator
Generate the article's images (count from image-prompts.json — brief.imagecount via scripts/core/imagepolicy.py, default 6, max 8) via the unified openaiimagepipeline (provider-aware: Vertex Gemini 3 Pro Image 4K primary + official OpenAI fallback, realtime-forced). Single-call pipeline replaces the prior…
image-prompt-designer
Build shared Art Direction Prefix + per-slot 9-field prompts for the article's image slots (brief.imagecount, default 6, max 8 — scripts/core/imagepolicy.py). Uses Strategy A (shared prefix; per-slot variation). Reads brand-identity, brand-config, formatid. Produces image-prompts.json for openai-image-generator. Stage…
image-slot-allocator
Decide the article's image slots (brief.imagecount, default 6 = 1 cover + 5 section images, max 8). Reads outline.json + formatid. Picks H2s to image based on per-format mapping in references/image/format-style-mapping.md. Triggered as Stage 27a of phase-publish image sub-pipeline.