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.
git clone --depth 1 https://github.com/novoads/agent-skillsWrote 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/plugins/novoads/agent-skills/skills)<a href="https://agentmods.dev/plugins/novoads/agent-skills/skills"><img src="https://agentmods.dev/badge/plugins/novoads/agent-skills/skills/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/plugins/novoads/agent-skills/skills"><img src="https://agentmods.dev/badge/plugins/novoads/agent-skills/skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
skills 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 today.
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.
This is a copy
86% identical to skills — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"name": "skills",
"source": "./",
"description": "AI video and image ads for marketers, built in Claude Code or Cursor and priced by a live estimate first. Skills clone a competitor's ad, build Pixar and claymation spots, turn a product photo into motion, generate thumbnails and Meta ad frames, swap a voice, and sweep the Meta Ad Library. Every skill runs on the Novoads REST API and quotes a live estimate before anything is charged.",
"author": {
"name": "Novoads",
"url": "https://novoads.ai"
},
"homepage": "https://github.com/novoads/agent-skills",
"repository": "https://github.com/novoads/agent-skills",
"license": "MIT",
"keywords": [
"ads",
"advertising",
"marketing",
"video",
"image-generation",
"ugc",
"creative"
],
"skills": [
"./skills",
"./shared/skills"
]
}What it installs
The manifest is a name and a version. 17 skills travel with it, and installing the plugin installs all of them — 3,129 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill novoads-api A 189 tokens
- Skill clone-video-ad A 233 tokens
- Skill clone-image-ad A 246 tokens
- Skill spy-competitor-ads A 209 tokens
- Skill analyze-video A 138 tokens
- Skill change-voice A 217 tokens
- Skill chatgpt-image-ad A 159 tokens
- Skill claymation-ad A 230 tokens
- Skill image-to-motion A 236 tokens
- Skill nano-banana-image-ad A 140 tokens
- Skill generate-youtube-thumbnail A 80 tokens
- Skill meta-ad-builder A 157 tokens
- Skill music-mix A 127 tokens
- Skill broll-overlay A 128 tokens
- Skill caption-video A 226 tokens
- Skill novoads-update B 186 tokens
- Skill pixar-ad C 228 tokens
What ships with it
2 files beside marketplace.json#skills in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 25 lines scan A c6c6c7fb1f8e
skills is a plugin published in the GitHub repository novoads/agent-skills (14 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. It is 86% identical to skills, differing in 2 lines, and is treated as a copy.
Other plugins, from other repositories
video-shotcraft
Craft cinematic product videos with Remotion using shot recipes, motion previews, reusable components, SFX, and a production-ready template.
meshy-3d-agent
Generate 3D models, textures, and images, rig and animate characters, and prepare models for 3D printing with the Meshy AI API.
ui-clone-skills
Motion forensics for the animated web. Four jobs against a live URL: decode (analyse motion + build, no code), clone (URL → React + Tailwind), verify (AE/SSIM + motion-parity score vs. an existing impl), extract (raw JSON dump). Extracts real CSS and animation params (GSAP / Framer Motion / Lenis / anime.js) directly…
webnovel
A toolkit for writing Chinese online novels from early ideas through revision and publication checks. It covers story planning, drafting, character and world design, continuity checks, pacing review, and text editing.
video-subtitle
A video subtitle toolkit that extracts audio, transcribes speech, translates it, and can burn subtitles into the video. Whisper is the speech-recognition system used for transcription, and FFmpeg is the media-processing tool used in the workflow.
slides-ai-plugin
Professional presentation generator for HTML (with GSAP animations) and PPTX formats. Creates conference talks, pitch decks and tech presentations with curated style presets and validation.