Marketing Skills is an open-source library of reusable workflows that helps AI coding agents perform marketing and SEO tasks. It serves people working on search optimization, content, advertising, launches, analytics, and related marketing activities, and its catalogue entries are the individual skills agents can install.
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 kostja94/marketing-skills --skill metadatagit clone --depth 1 https://github.com/kostja94/marketing-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/skills/kostja94/marketing-skills/metadata)<a href="https://agentmods.dev/skills/kostja94/marketing-skills/metadata"><img src="https://agentmods.dev/badge/skills/kostja94/marketing-skills/metadata/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/kostja94/marketing-skills/metadata"><img src="https://agentmods.dev/badge/skills/kostja94/marketing-skills/metadata.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00116 | $0.01556 |
| Opus 5.5 | $0.00046 | $0.00622 |
| Sonnet 5.5 | $0.00023 | $0.00311 |
| Haiku 4.5 | $0.00012 | $0.00156 |
Grade A, and why
page-metadata 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 20d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- page-metadata — 100% identical, 160 lines differ
- page-metadata — 100% identical, 160 lines differ
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO On-Page: Page Metadata
Orchestrates the complete metadata lifecycle. It owns scope, routing, implementation, validation, and delivery; specialist skills own their individual writing and tag rules.
When invoking: On first use, briefly state the scope and which specialist skills are needed. Then work from current production evidence and the real source of truth rather than producing a detached copy sheet.
Ownership and boundaries
| Concern | Owner |
|---|---|
| Lifecycle, page inventory, implementation, validation, delivery | page-metadata |
<title> writing and review |
title-tag |
| Meta description writing and review | meta-description |
| H1-H6 writing and hierarchy | heading-structure |
| Open Graph | open-graph |
| X/Twitter Cards | twitter-cards |
| Canonical URL | canonical-tag |
| Localization | localization-strategy, translation |
| Post-release query and CTR observation | google-search-console |
This skill may check H1 and body coverage to confirm that metadata promises are fulfilled. It must not rewrite H1-H6; route that work to heading-structure. It may report keyword cannibalization, but must not merge pages, change page roles, delete URLs, or redistribute target keywords.
Required inputs and evidence
Read root contextus.md when present and load only relevant modules. Otherwise use project documentation and verified product facts. Establish:
- Target site, locales, environment, and release scope.
- Page inventory from production navigation, footer, contextual links, index or hub pages, robots.txt, sitemap, production URLs, and application routes. A sitemap is evidence, not a complete inventory guarantee. For very large generated page families, inspect the template and representative examples instead of enumerating every URL.
- Page type, unique job, primary search intent, target query evidence, audience, and page-specific facts.
- Current production output: title, description, H1, canonical, robots, hreflang, OG, Twitter Cards, HTTP status, and server-returned HTML.
- Actual maintenance source: framework metadata API, layout template, route module, static HTML, JSON/YAML, CMS fields, server injection, or proxy layer.
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.
- 20d ago Changed · -3 tokens per session 14e82760d9c0
- 1mo ago Changed a4afe31694f7
- 1mo ago First seen · 121 lines · 119 tokens per session scan A 223f61ff9d3e
page-metadata is a skill published in the GitHub repository kostja94/marketing-skills (1,062 stars, last pushed 5d ago), licensed MIT. It adds 116 tokens to every session and 1,556 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
seo-hreflang
International SEO, multi-regional architecture, and hreflang tag validation. Enforces bidirectional return tags and cultural localization profiles.
SEO Content Optimizer
Analyzes and rewrites content to maximize search engine visibility without sounding robotic.
cold-outbound-sequencer
Use when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in compliant"; produces a multi-step outbound sequence with reply-triage branches (positive / objection / referral / not-now / opt-out), a…
newsletter-monetization-planner
Use when the user asks to "monetize my newsletter", "build a sponsorship rate card", or "model paid-subscription revenue"; produces a revenue model (paid tiers, ad/sponsorship inventory + CPM/flat rate card, referral/boost loops), a list-growth ↔ revenue projection, and honest-offer / disclosure checks for the SEND-D…
contract-helper
Use when the user asks to "draft an influencer contract", "review these agreement terms", or "build a partnership template"; produces a full influencer agreement framework (scope, compensation, usage rights, exclusivity, FTC disclosure), a clause-by-clause review with red flags, and a negotiation cheat sheet. Not for…
sales-enablement-kit
Use when the user asks to "build battle cards", "prep the sales team for launch", or "write the internal launch FAQ"; produces the internal enablement kit for a sales-led launch — battle cards vs each named alternative (where we win / where they win / trap questions, every fact traceable), a sales talk track derived…