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.
/plugin marketplace add schwepps/skillsnpx agentmods add plugins/schwepps/skills/marketplacegit clone --depth 1 https://github.com/schwepps/skillsGrade 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 2d 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
{
"owner": {
"name": "schwepps",
"url": "https://github.com/schwepps"
},
"name": "skills",
"version": "1.0.0",
"description": "Claude Code skills: SEO audits, AI search optimization, music creation, smart contract security, LinkedIn personal branding, developer tools.",
"license": "MIT",
"repository": {
"type": "git",
"url": "https://github.com/schwepps/skills.git"
},
"plugins": [
{
"name": "seo-technical-audit",
"source": "./seo-technical-audit",
"description": "Technical SEO: crawlability, Core Web Vitals, AI crawlers"
},
{
"name": "seo-content-audit",
"source": "./seo-content-audit",
"description": "On-page SEO and content quality scoring"
},
{
"name": "geo-aeo-optimization",
"source": "./geo-aeo-optimization",
"description": "AI search optimization for ChatGPT, Perplexity, Google AI"
},
{
"name": "suno-music-creator",
"source": "./suno-music-creator",
"description": "Music creation with Suno AI V5"
},
{
"name": "solidity-auditor",
"source": "./solidity-auditor",
"description": "Professional smart contract security audits with OWASP Top 10 coverage"
},
{
"name": "install-skill",
"source": "./install-skill",
"description": "Automate skill package installation and marketplace registration"
},
{
"name": "linkedin-personal-branding",
"source": "./linkedin-personal-branding",
"description": "LinkedIn profile analysis, personal branding audit, and visibility optimization"
},
{
"name": "linkedin-roast",
"source": "./linkedin-roast",
"description": "LinkedIn profile roasting with savage but friendly comedy burns"
}
]
}
What ships with it
5 files beside marketplace.json 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.
- 2d ago First seen · 57 lines scan A af64f6e183a4
skills is a plugin published in the GitHub repository schwepps/skills (16 stars, last pushed 7mo ago), 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
banner-creator
Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio for GitHub, Twitter, LinkedIn, etc.
interaction-design
Design meaningful interactions with micro-animations, state machines, gestures, error handling, and feedback patterns.
agents-inc
Skills, stacks, and agents for Agents Inc.
maciejdzierzek-kling
Plugin marketplace listing 1 plugin: kling-ai-prompt-generator.
kling-ai-prompt-generator
Write and improve prompts for Kling AI video generation and pick the right Kling model. Covers VIDEO 3.0, VIDEO 3.0 Turbo, VIDEO 3.0 Omni (including video editing), Motion Control, Avatar 2.0 talking avatars, multi-shot storyboards, Element Reference, Voice Control, native audio, first/last frame control, credit and…
frontend-design
Production-grade frontend design skill that avoids AI slop — specific rules for typography, color (OKLCH), layout, motion, interaction, and UX writing.