claude

base-segura

Base segura (L1): skills transversales (incluye humanizalo: que tus textos no suenen a IA, y modo-directo: respuestas del largo que corresponde) + auditor de skills externas + academy-guide (te sugiere cursos oficiales cuando aprendés a usar Claude) + agentes básicos + plantillas de CLAUDE.md. Día 1 para cualquier empresa.

0 on GitHubby Fernando Raimondiv0.14.6MITupdated todayproductivity
/

Plugin base-segura from marketplace claude-catalogo in raimondifernando-web/claude-catalogo. Commands read from the repo's manifest — today.

What it installs

Skills (18)

  • academy-guide

    Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "

  • copy-editing

    When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean u

  • council

    Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.

  • decisiones-tecnicas

    Antes de contratar, instalar o armar cualquier servicio técnico (poner una web o herramienta en internet, automatizar un proceso, guardar datos en una base, manejar claves, vigilar gastos, usar una IA externa con datos del cliente), aplicá los criterios de stack que ya se decidieron y se pagaron car

  • doc-coauthoring

    Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc

  • excel-analysis

    Analyze Excel spreadsheets, create pivot tables, generate charts, and perform data analysis. Use when analyzing Excel files, spreadsheets, tabular data, or .xlsx files.

  • humanizalo

    Hace que un texto escrito por IA suene a persona: detecta y elimina 40 señas de IA (vocabulario, estructura, formato, relleno y tics de chatbot), le inyecta voz, se califica en 6 dimensiones y no entrega hasta pasar 42/60 o agotar 3 pasadas. Usala cuando el usuario diga "esto suena a IA", "se nota q

  • i-have-adhd

    Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

  • markitdown

    Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.

  • meeting-insights-analyzer

    Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication

  • mermaid-diagrams

    Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowch

  • metodologias-agiles

    Metodologías ágiles y de gestión de objetivos para cualquier PM, en castellano: elegir y aplicar OKR, Scrum, Kanban, Scrumban, Shape Up, Lean Startup, Design Sprint, teoría del cambio y marco lógico, y armar retrospectivas. USAR SIEMPRE que pidan o mencionen: «metodología ágil», «OKR / objetivos y r

  • modo-directo

    Entrega la respuesta con el mínimo de palabras que sigue siendo correcto: el largo lo fija el tipo de pregunta, no la costumbre. Analiza completo y recorta al final; nunca recorta un matiz que cambia la decisión. Funciona en dos direcciones: como modo que se queda puesto toda la sesión, y como pasad

  • planning-with-files

    Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring more than 5 tool calls.

  • professional-communication

    Guide technical communication for software developers. Covers email structure, team messaging etiquette, meeting agendas, and adapting messages for technical vs non-technical audiences. Use when drafting professional messages, preparing meeting communications, or improving written communication.

  • session-handoff

    Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need t

  • skill-security-auditor

    Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4)

  • writing-clearly-and-concisely

    Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

Subagents (3)

  • critic

    Work plan and code review expert — thorough, structured, multi-perspective

  • planner

    Strategic planning consultant with interview workflow

  • research-analyst

    Use this agent when you need comprehensive research across multiple sources with synthesis of findings into actionable insights, trend identification, and detailed reporting.

View source on GitHub

More from raimondifernando-web/claude-catalogo

All 24 plugins →

Copia fijada de oh-my-claudecode (39.3K★, MIT, commit 9fd35ec, 2026-09-23) con dos arreglos de seguridad sobre el original auditado: (1) se saca el hook PermissionRequest que auto-aprobaba heredocs 'git commit'/'git tag' sin revisar el contenido (riesgo de inyección por sustitución de comandos); (2) hardMaxIterations tiene un tope real (500 normal / 200 estricto) que ninguna configuración puede subir ni apagar. Todo lo demás del original entra sin tocar.

44 skills · 20 commands · 19 agents · 1 MCP server · hooks

0

Pack de rubro (L2): marketing y ventas — copy, emails, anuncios, SEO, CRO, lanzamientos, referidos, pricing, revops y análisis de campañas (40 skills) + 23 agentes: jefe general de pyme (pm-empresa), jefes de marketing y de ventas, estrategia de negocio y de contenido, SEO, anuncios pagos, conversión, redes, marca, prensa, tienda online argentina, prospección, discovery, propuestas, pipeline, cuentas, WhatsApp B2B, soporte y customer success. Requiere base-segura.

40 skills · 23 agents

0

agent-skills

claudecodex

Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship. (Original de Addy Osmani, 98.7K★, MIT, fijado al commit auditado 1401c8b — PASS con condiciones, 2026-09-23 y re-auditado 2026-10-10: preguntar antes de reset --hard, push, deploy, npm/brew/pip install o agregar MCP.)

25 skills · 4 agents

0

Pack de rubro (L2): propuestas y honorarios, pliegos, informes de visita, adicionales, punch list, revisión de presupuestos, normativa argentina (sobre PDFs oficiales), plan semanal + ficha A3, identidad visual del estudio (tu marca en cada pieza), investigación de mercado, contenido y diseño para estudios de arquitectura y profesiones similares. Requiere base-segura.

23 skills · 4 agents

0

Capa L4 para desarrollar tus propias herramientas con Claude (vibe coding): 1 skill (research-deep-dive) y 17 agentes. Revisores de solo lectura (code-reviewer, security-reviewer) explican en castellano qué arreglar primero. Construir: python-pro, javascript-pro, sql-pro, data-analyst, prompt-engineer, documentation-engineer. Decidir y gestionar: product-manager, technology-scout, jefe-de-ingenieria, jefe-de-proyectos, analista-de-bi. Investigación: research-analyst y afines.

8 skills · 17 agents

0

Pack de rubro (L2): finanzas, legal y administración de una pyme argentina — CFO, finanzas personales, trámites del auto, M&A (4 skills) + 18 agentes: impuestos, legal comercial, revisión de contratos, datos personales (Ley 25.326), flujo de caja, cobranzas, conciliación, cierre contable, compras, logística, reclamos, inventario, operaciones, SOP, RR.HH. y reclutamiento. Orientativo: no reemplaza a un contador ni a un abogado. Requiere base-segura.

4 skills · 18 agents

0

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain base-segura?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins24 plugins