agentmods.dev

marketing-ideas

marketing-ideas is a skill for Claude Code from LOGIN-TB/claude-skills. It costs 135 tokens per session (3,383 once invoked), scanned A, original, MIT.

A guide for turning marketing ideas into context-specific hypotheses and measurable experiments. It treats ideas as things to test rather than as proven tactics.

In plain words
What is it for?
It is used to develop and prioritise ideas for channels, campaigns, offers, and growth, then outline how to test them.
Why use it?
It helps teams rank ideas by evidence, risk, and feasibility without inventing demand, results, customer claims, or competitive advantages.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the marketing-dach plugin — 13 skills shipped together

not rated 82repo +2 8d ago A scan SkillSpector: pass 135 tokens original MIT

Good fit It is used to develop and prioritise ideas for channels, campaigns, offers, and growth, then outline how to test them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/login-tb/claude-skills/marketing-ideas
View source ↗ LOGIN-TB/claude-skills
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.

Any agent
npx skills add LOGIN-TB/claude-skills --skill marketing-ideas
Clone the repo
git clone --depth 1 https://github.com/LOGIN-TB/claude-skills

Made for: Claude Code.

Or install marketing-dach, the plugin that ships this one along with the rest of its 13 skills.

Its marketplace also offers this one on its own, as the plugin marketing-ideas — /plugin install marketing-ideas after adding the marketplace above.

Wrote 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.

agentmods badge for marketing-ideas

README.md
[![agentmods](https://agentmods.dev/badge/skills/login-tb/claude-skills/marketing-ideas/github.svg)](https://agentmods.dev/skills/login-tb/claude-skills/marketing-ideas)
Your own site
<a href="https://agentmods.dev/skills/login-tb/claude-skills/marketing-ideas"><img src="https://agentmods.dev/badge/skills/login-tb/claude-skills/marketing-ideas/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.

agentmods 80×15 button for marketing-ideas

Your own site · 80×15
<a href="https://agentmods.dev/skills/login-tb/claude-skills/marketing-ideas"><img src="https://agentmods.dev/badge/skills/login-tb/claude-skills/marketing-ideas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,383 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00135 $0.03383
Opus 5.5 $0.00054 $0.01353
Sonnet 5.5 $0.00027 $0.00677
Haiku 4.5 $0.00014 $0.00338

Measured 2mo ago against content hash efd0c2da7bbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

marketing-ideas 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 2mo 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.

skills/marketing-ideas/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Marketingideen und Experimente

Erzeuge und priorisiere kontextspezifische Marketinghypothesen statt einer Liste angeblich allgemein bewährter Taktiken. Standard ist eine Auswahlliste mit Testskizze im Chat. Ideenfindung erlaubt Analyse, aber keine Umsetzung.

Sicherheits- und Evidenzregeln

  1. Begrenzte Quellen. Nutze nur gelieferte Informationen und freigegebene Projektdateien. CRM, Analytics, E-Mail, Support, Kontaktlisten, Browserprofile, Communities und Zugangsdaten nicht ohne konkrete Freigabe verwenden.
  2. Ideen sind Hypothesen. „Bewährt“, „Quick Win“, „günstig“, „beste“ oder „hohe Absicht“ nur mit vergleichbarer Evidenz. Trenne Beobachtung, interne Aussage, Drittschätzung, Hypothese und Unbekanntes.
  3. Keine Ausführung durch Andeutung. Keine Recherche, Kontaktsammlung, Nachricht, Veröffentlichung, Kontoaktion, Anzeige, Ausgabe, Installation, Produkt-/Websiteänderung, Rabattaktion, Partnerschaft oder Vertrag ohne ausdrückliche Freigabe.
  4. Keine erfundenen Nachweise. Keine Nachfrage, Conversion, Rendite, Rankings, Kundengeschichten, Empfehlungen, Dringlichkeit oder Wettbewerberschwächen erfinden.
  5. Datenschutz und Einwilligung. Keine versteckte Verfolgung, Fingerprinting, Datenbroker-Anreicherung, Kontakt-Scraping, unerlaubte Profilbildung, private Community-Auswertung oder Audience-/Pixel-Weitergabe empfehlen.
  6. Plattformintegrität. Keine Fake-Bewertungen, Review-Gating, Engagement-Pods, gekauften Follower, Cloaking, Identitätsverwechslung, Regelumgehung oder verdeckte Automatisierung.
  7. Suchintegrität. Keine Doorway-Seiten, parasitäre Reputationsnutzung, Linkmanipulation, kopierte Vergleiche oder massenhafte dünne Inhalte.
  8. Faire Vergleiche. Aktuelle Quellen, neutrale Abwägungen und Marken-/Rechtsprüfung; keine Verleumdung, Nachahmung oder vertrauliche Wettbewerbsdaten.
  9. Kommunikation. E-Mail, DM, Presse-, Podcast-, Influencer- oder Partneransprache braucht legitime Zielauswahl, Identität, Einwilligungs-/Rechtsprüfung, Sperrlisten, einfachen Widerspruch und separate Sendefreigabe. Kein massenhafter unaufgeforderter Versand.
  10. Partnerschaften und Vorteile. Affiliate-, Referral-, Sponsoring-, Influencer-, Zertifizierungs- und Integrationsprogramme benötigen Bedingungen, Offenlegung, Markenrechte, Datenrollen, Betrugsschutz, Steuer-/Buchhaltungsprüfung und Einwilligungsgrenzen.
  11. Aktionen und Knappheit. Gewinnspiele, Rabatte, Testphasen, Early Access und Giveaways benötigen echte Bedingungen, Eignung, Regionen, Steuer-, Plattform-, Datenschutz-, Verbraucher- und Budgetprüfung. Keine erfundene Knappheit.
  12. Rechte. Quellen und Nutzungsrechte für Zitate, Bilder, Logos, Musik, Daten, Vorlagen, Open Source, Kundenstories und Forschung prüfen.
  13. Produktideen sind Produktprojekte. Tools, Erweiterungen, APIs, OAuth, Importe, Viral Loops und Open-Source-Komponenten benötigen Spezifikation, Security/Privacy, Barrierefreiheit, Missbrauchsschutz, Wartung, Support, Tests und Rollback.
  14. Sensible Bereiche. Gesundheit, Finanzen, Recht, Arbeit, Wohnen, Bildung, Versicherung, Minderjährige, Politik und vulnerable Gruppen erfordern Fachprüfung; keine sensiblen Merkmale für diskriminierende Auswahl oder Preise.
  15. Physische und Reputationsrisiken. Events, Stunts, Außenwerbung und kontroverse Kampagnen benötigen Rechte, Genehmigungen, Sicherheit, Barrierefreiheit, Einwilligung Unbeteiligter, Versicherung und Krisenplan.

Read the full file on GitHub · 155 lines

Changes

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.

  1. 2mo ago First seen · 155 lines · 135 tokens per session scan A efd0c2da7bbf

Subscribe to this mod's changes

marketing-ideas is a skill published in the GitHub repository LOGIN-TB/claude-skills (82 stars, last pushed 8d ago), licensed MIT. It adds 135 tokens to every session and 3,383 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 2026-08-30.

Marketing and SEOagent-skillsaiclaudeclaude-skillsdeutschprompt-engineering
Related

marketing-ideas compared with skills from other repositories

marketing-ideas next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
marketing-ideasLOGIN-TB/claude-skillsSkill828d agoMITA135Claude Code
prompt-masternidhinjs/prompt-masterSkill16k15d agoMITB78Claude Code, Codex
dep-auditorlaolaoshiren/claude-code-skills-zhSkill9052d agoMITA72Claude Code, Codex
github-actions-genlaolaoshiren/claude-code-skills-zhSkill9052d agoMITA57Claude Code, Codex
api-testerlaolaoshiren/claude-code-skills-zhSkill9052d agoMITA86Claude Code, Codex
skill-curatorlaolaoshiren/claude-code-skills-zhSkill9052d agoMITA75Claude Code, Codex
env-managerlaolaoshiren/claude-code-skills-zhSkill9052d agoMITA22Claude Code, Codex