venturalabs-ai

Gera criativos e copies de anúncios para Meta (Facebook/Instagram) e Google Ads (Search, Display, YouTube) com validação automática de compliance.

Gera todos os assets de venda complementares — sequências de e-mail, scripts de WhatsApp, carta de vendas PDF, slides de oferta, roteiro de webinar e posts orgânicos.

Gera a estrutura completa e o HTML da página de vendas (VSL ou longa) com todos os blocos de alta conversão.

Biblioteca central de frameworks de copy e componentes reutilizáveis para vendas de infoprodutos.

Produz o conteúdo completo do infoproduto — roteiros de aulas, PDFs de apoio, exercícios, checklists, templates e bônus.

Cria a base estratégica do infoproduto a partir do briefing — nicho, avatar, promessa, mecanismo único, estrutura de módulos e oferta.

Produz README, guias e documentacao de modulos.

Le e descreve projetos Git, estrutura e qualidade de codigo.

Detect and remove AI-sounding patterns in Brazilian Portuguese text while preserving meaning tone and register. Use when finalizing or reviewing PT-BR copy drafts posts or chapters that must not read like generic AI output. Do not use when the text is already…

Verify foreign-language sentences in a text for correctness of spelling diacritics and register. Use when a text contains phrases that are not in the main language or when characters places titles or terms in another language must be written correctly. Do not…

Update Autor Ventura voice memory from approved author samples preferences rejections and revision history without inventing personal traits. Use when recurring writing should preserve a real author's established voice. Do not use when no approved samples or…

Build or review an Autor Ventura Claim Ledger for material verifiable assertions with source date and confidence traceability. Use when journalism academic edital or other evidence-sensitive content contains factual claims. Do not use when material is purely…

Check Autor Ventura academic or evidence-heavy content for alignment between question objective method evidence results discussion and conclusion. Use when finalizing work where conclusions must be bounded by a documented method or evidence chain. Do not use…

Add or run Autor Ventura structural editorial evals for routing publication packs voice and factual gates. Use when changing prompts router logic memory behavior or review constraints. Do not use when judging literary quality from one generated draft without…

Apply the correct Autor Ventura publication pack structure and review gates to a routed writing task. Use when the medium is known and the content must follow journal broadcast magazine book edital academic symposium or ceremonial conventions. Do not use when…

Route a writing request through Autor Ventura's speaker audience purpose medium evidence emotion and limits model before drafting. Use when the publication context is not yet converted into a publication pack decision. Do not use when a pack is already fixed…

Evolve Ventura Pro Agro FastAPI contracts without breaking existing routes schemas or documented behavior. Use when adding or changing API endpoints parameters or response models. Do not use when changing only internal data adapters with no API effect.

Add or refresh agricultural data sources with provenance freshness and failure behavior explicit. Use when integrating IBGE Open-Meteo ClimaTempo MAPA ZARC Embrapa or another approved source. Do not use when only presenting data already available through…

Implement or repair municipality and UF queries using the repository's IBGE-backed domain contracts. Use when changing municipality lookup filtering or identification. Do not use when calculating planting windows costs or climate signals.

Produce a producer-facing planning report from Ventura Pro Agro outputs with sources assumptions and uncertainty visible. Use when assembling municipality crop climate ZARC and cost results into one report. Do not use when changing the underlying calculations…

Combine repository-supported climate lunar and tidal signals while keeping each source and confidence separate. Use when building a composite planning view from these signals. Do not use when replacing official ZARC constraints or inventing missing…

Select the smallest trusted connector set from the repository agent manifest before a skill uses external tools. Use when a task may require APIs databases MCP servers models observability or runtime tools. Do not use when the task is fully local and needs no…

Calculate and present crop cost estimates from repository-supported inputs with explicit units and assumptions. Use when changing cost composition rural-unit conversion or estimate output. Do not use when the task is climate ZARC or municipality lookup.

Interpret and expose ZARC planting windows from repository-supported official references with traceable constraints. Use when changing ZARC lookup window selection or presentation. Do not use when producing unsupported agronomic recommendations beyond…

Triage suspicious Ventura.SEG events across audit gateway credential and sandbox evidence. Use when investigating anomalous agent behavior or security alerts. Do not use when authoring normal policies without an incident signal.

Add or review Consul service-mesh intentions only when Consul is an explicit Ventura.SEG deployment dependency. Use when the task names an existing Consul deployment or integration. Do not use when Consul is absent from the target environment or repository…

Design DLP rules for Ventura.SEG with explicit detection tests and bounded false positives. Use when adding or tuning outbound sensitive-data detection. Do not use when changing command permissions or sandbox isolation.

Contain a suspected compromised agent by reducing privileges and isolating execution through existing Ventura.SEG controls. Use when active behavior may cause data loss credential abuse or destructive actions. Do not use when handling ordinary debugging or…

Author and validate Ventura.SEG permission policies against the repository policy engine. Use when changing allow block or ask decisions in policies. Do not use when the task is DLP content scanning or credential handling.

Add adversarial regression tests for Ventura.SEG security controls using safe synthetic fixtures. Use when a control changes or a security bypass is discovered. Do not use when writing unrelated feature tests or performing live offensive testing.

Integrate an external Ventura agent with existing Ventura.SEG permission DLP credential audit and sandbox controls. Use when another repository must adopt SEG protections. Do not use when changing SEG internals without an integration target.

Configure Ventura.SEG Vault-backed credential loading without embedding secrets in code. Use when enabling or changing Vault authentication and KV access. Do not use when credentials remain local handles without Vault.

Add a teaching module to AI Animation Academy with a clear learning objective reproducible exercise and documented limitation. Use when implementing new educational content inside the Next.js academy. Do not use when only changing site chrome or adding a raw…

Design or review an academy exercise for keeping one character consistent across generated scenes and shots. Use when a lesson or case study focuses on identity wardrobe proportions camera or scene continuity. Do not use when the request is unrelated…

Build a controlled academy comparison of animation or generation models using the same task inputs and evaluation dimensions. Use when teaching tradeoffs between supported multimodal workflows. Do not use when only one model is being documented or when…

Add a reusable animation prompt template to the academy only after its variables and platform assumptions are understood. Use when a validated prompt pattern should become teaching material. Do not use when the prompt is one-off untested or depends on…

Validate AI Animation Academy changes for typed Next.js code reproducible content current claims and documented limitations. Use when reviewing a lesson workflow case study or UI change before merge. Do not use when the task is only to evaluate external model…

Turn a tested multimodal animation workflow into an academy case study with inputs steps outputs costs and failure notes. Use when a real workflow has been executed and should become reusable learning material. Do not use when the workflow is speculative or…

Add a resource to a Ventura curation repository with provenance relevance and licensing context checked. Use when adding a new external reference to curated learning or resource lists. Do not use when copying upstream content into a Ventura project.

Update Ventura Studio repository indexes from verifiable repository metadata and declared maturity. Use when adding removing renaming or reclassifying ecosystem projects. Do not use when changing code inside a project rather than the ecosystem catalog.

Summarize verified ecosystem changes into Ventura Studio release notes without overstating maturity or metrics. Use when publishing a coordinated Ventura ecosystem update. Do not use when writing a single repository changelog entry with no hub impact.

Assign or update repository maturity badges from explicit engineering evidence. Use when a project changes incubation beta flagship or production-readiness status. Do not use when the requested label cannot be supported by repository tests CI security and…

Audit Agent Skills across Ventura repositories for overlap weak triggers unsupported references and format violations. Use when reviewing a repository skill catalog or preparing ecosystem-wide skill changes. Do not use when implementing the domain task…

Review the Ventura Pro agent prompt for conflicting autonomy safety tool and engineering instructions. Use when changing `.opencode/agent/ventura-pro.md` or adding a rule that affects agent behavior. Do not use when only applying the agent to a target coding…

Install Ventura Pro agent and rule files into a target OpenCode project using the repository layout and configuration contract. Use when a user wants Ventura Pro activated in another project. Do not use when editing Ventura Pro rules themselves or when the…

Add or revise Ventura Pro OpenCode engineering rules so they encode repository-specific decisions rather than generic coding advice. Use when a recurring engineering workflow needs a new or updated rule. Do not use when existing rules already cover the task…

Select the minimum Ventura Pro rule files relevant to a concrete engineering task. Use when deciding whether microservices mlops performance or pyspark guidance should be loaded. Do not use when the task is installing the agent or editing rule content.

Validate a Ventura Pro installation against the target project's actual stack commands tests and constraints. Use after installing or materially changing Ventura Pro in another repository. Do not use when no target OpenCode project is available for validation.

Keep Ventura Art platform system and prompt templates consistent when supported capabilities change. Use when adding editing or deprecating entries in repository configs or model templates. Do not use when adapting one user prompt without changing repository…

Review Ventura Art publication material for repository-documented AI disclosure and platform compliance requirements. Use when generated media is about to be published or campaign guidance is being updated. Do not use when no publication or disclosure…

Adapt a Ventura Art master prompt to a supported generation platform using repository configs and templates. Use when a user needs the same creative intent translated to one target model or platform. Do not use when adding a new platform definition or…

Convert a proven Ventura Art prompt workflow into a reusable repository template with stable variables and replay instructions. Use when a prompt has succeeded repeatedly and should stop being rebuilt from scratch. Do not use when the workflow is in…

Build or review multi-scene Ventura Art prompts for character wardrobe camera light object and transition continuity. Use when a production spans multiple generated scenes that must match visually. Do not use when the request is a single independent shot or…

Customize one Ventura Agents prompt for a concrete organization while preserving its mission limits metrics and escalation boundaries. Use when adapting an existing agent to a real operating context. Do not use when the requested role is outside the existing…

Create repeatable cases that test one Ventura business agent's declared deliverables limits escalation and metric behavior. Use when changing an agent prompt or validating a customization. Do not use when only choosing an agent from the catalog.

Select the single Ventura Agents business agent whose declared mission best matches a requested outcome. Use when a user needs to choose among the ten agent prompts before execution. Do not use when modifying an agent prompt or coordinating several agents in…

Audit Ventura Agents prompt files and README catalog for role overlap missing files inconsistent anatomy and unsupported claims. Use when adding removing renaming or materially changing an agent. Do not use when executing an existing agent on a business task.

Define tool permissions confirmation points and least-privilege boundaries for a Ventura business agent connected to external systems. Use when an agent gains email CRM ERP database code or financial tools. Do not use when the agent is prompt-only with no…

Customize one Ventura Agents II prompt for a concrete organization while preserving mission limits metrics and escalation behavior. Use when adapting an existing specialist to real processes and tools. Do not use when the requested role is outside this…

Create repeatable cases that test one Ventura Agents II specialist's declared deliverables limits escalation and metric behavior. Use when changing a specialist prompt or validating an organizational customization. Do not use when only choosing an agent from…

Select the single Ventura Agents II specialist whose declared mission best matches a requested outcome. Use when choosing among product customer success operations supply security DevOps research pricing ecommerce or training agents. Do not use when modifying…

Audit Ventura Agents II prompt files and README catalog for role overlap missing artifacts inconsistent anatomy and unsupported reference claims. Use when adding removing renaming or materially changing a specialist. Do not use when executing an existing…

Define least-privilege tool access and confirmation boundaries for Ventura Agents II specialists connected to operational systems. Use when an agent gains infrastructure security supply pricing ecommerce or customer-system actions. Do not use when the agent…

Prepare a reproducible 60-second VenturaVoice demo that proves one implemented audio capability using authorized sample data. Use when an executable MVP slice needs a concise demonstration. Do not use when the capability is unimplemented or the sample lacks…

Create implementation-ready starter issues for VenturaVoice from the approved audio MVP and Beta gates. Use when maintainers need small independent tasks that move the scaffold toward a reproducible prototype. Do not use when requirements are undefined or the…

Define the next VenturaVoice MVP slice around transcription synthesis diarization or audio analysis with measurable acceptance criteria. Use when deciding what the incubation repository should implement next. Do not use when implementing an already-approved…

Bootstrap the smallest VenturaVoice Python structure for the approved speech or audio MVP using only declared stack needs. Use when the repository is ready to move from incubation docs to executable code. Do not use when a functional project structure already…

Prepare a reproducible 60-second VenturaVision demo that proves one implemented vision capability and its limitation. Use when an executable MVP slice needs a concise demonstration. Do not use when the feature is not implemented or the demo would rely on…

Create implementation-ready starter issues for VenturaVision from the approved MVP and Beta gates. Use when maintainers need small independent tasks that move the scaffold toward a reproducible prototype. Do not use when requirements are still undefined or…

Define the next VenturaVision MVP slice around detection OCR captioning or media analysis with measurable acceptance criteria. Use when deciding what the incubation repository should implement next. Do not use when implementing an already-approved feature or…

Bootstrap the smallest VenturaVision Python project structure for the approved MVP using only declared stack needs. Use when the repository is ready to move from incubation docs to executable code. Do not use when a functional project structure already exists…