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 victorperez22/marketing-claude-code --skill marketing-marcagit clone --depth 1 https://github.com/victorperez22/marketing-claude-codeWrote 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/victorperez22/marketing-claude-code/marketing-marca)<a href="https://agentmods.dev/skills/victorperez22/marketing-claude-code/marketing-marca"><img src="https://agentmods.dev/badge/skills/victorperez22/marketing-claude-code/marketing-marca/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/victorperez22/marketing-claude-code/marketing-marca"><img src="https://agentmods.dev/badge/skills/victorperez22/marketing-claude-code/marketing-marca.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.04321 |
| Opus 5 | $0.00000 | $0.02160 |
| Sonnet 5 | $0.00000 | $0.00864 |
| Haiku 4.5 | $0.00000 | $0.00432 |
Grade A, and why
marketing-marca 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 11d 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 — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analisis de Voz de Marca y Generacion de Guidelines
Proposito de la skill
Analizar la voz, tono y mensaje de una marca en todos los canales disponibles y generar una guia completa de voz de marca. Examina como comunica la marca, detecta patrones e inconsistencias y produce guidelines accionables para que cualquier redactor o marketer mantenga la consistencia.
Cuando usarla
- El usuario quiere entender o documentar la voz de una marca
- El usuario necesita guidelines de voz para un equipo, freelancers o agencia
- El usuario quiere asegurar consistencia entre canales
- El usuario esta rebrandeando o refinando su identidad
- El usuario quiere comparar su voz con competidores
- Se activa con
/marketing marca <url>o/marketing marca
Como ejecutarla
Paso 1: Recoger material fuente
Para analizar la voz, examina contenido de multiples fuentes. Prioriza en este orden:
Fuentes primarias (obligatorias):
- Home — la representacion mas curada de la marca
- About — como se describe a si misma
- Paginas de producto/servicio — como presentan la oferta
Fuentes secundarias (si estan disponibles): 4. Blog posts (al menos 3-5 recientes) 5. Perfiles en redes (bio, posts recientes, estilo de engagement) 6. Newsletters (welcome email, envios recientes) 7. Copy de cliente (mensajes de error, flujos de onboarding, help docs)
Fuentes terciarias: 8. Ofertas de empleo — revelan cultura y valores 9. Notas de prensa — estilo formal 10. Ad copy — enfoque en mensajes de pago 11. Scripts de video o transcripciones de podcast — voz hablada
Usa herramientas de navegador o scripts/analizar_pagina.py para el contenido web. Para redes, revisa enlaces sociales de la web y analiza los perfiles.
Paso 2: Analisis por dimensiones de voz
Mapea la voz en cuatro dimensiones principales. Cada una es un espectro, no un binario.
Dimension 1: Formal <-----> Casual
| Senal | Formal | Casual |
|---|---|---|
| Contracciones | Las evita | Las usa con libertad |
| Estructura de frases | Complejas, largas | Cortas, directas |
| Vocabulario | Profesional, estandar del sector | Conversacional |
| Saludos | "Estimado cliente" | "Hola!" |
| Pronombres | Tercera persona ("la empresa", "uno") | Primera/segunda ("nosotros", "tu") |
| Humor | Raro o ausente | Frecuente, natural |
| Jerga o coloquialismos | Nunca | A veces o con frecuencia |
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.
- 11d ago First seen · 501 lines · 0 tokens per session scan A 26605b9ea866
marketing-marca is a skill published in the GitHub repository victorperez22/marketing-claude-code (9 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,321 tokens. 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 2026-08-31.
Other skills, from other repositories
icp-research
Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation. Produces TAM analysis, firmographic segments, champion and economic buyer personas, use case mapping, customer proof points, and voice-of-customer synthesis with normalized attributes. Requires website…
cod-operations-analyst
COD (cash-on-delivery) e-commerce operations skill. Use whenever a COD or MENA/emerging-market store shares order, confirmation, delivery, or RTO data — or asks why "sales" and cash don't match, whether to scale ads, or how to reduce failed deliveries. Extends funnel analysis past checkout: computes real revenue…
launch-tier-framework
Classify product launches into defensible tiers and turn roadmap inputs into a season-of-launch plan that aligns Product, Campaigns, PR/AR, Sales, and customer-facing teams.
battlecards
Creates competitive battlecards for sales deal conversations. Produces win themes, landmines to plant, objection handlers, and competitive positioning per competitor. Outputs a structured markdown battlecard with quick-reference sections for live sales calls. Depends on competitor-research for competitive intelligence…
positioning-messaging-framework
Create sharp B2B positioning and messaging from customer truth, segmentation choices, real alternatives, differentiated value, and proof.
win-loss-analysis
Win/loss analysis for B2B SaaS. Analyzes sales call transcripts across 6 dimensions (product, messaging, GTM/sales, pricing, competition, customer context) to extract why deals are won, lost, retained, or churned. Produces aggregate patterns with verbatim-quote evidence, frequency counts, confidence levels, and…