script-writing

Gere o roteiro do programa AI Talk Radio a partir da pesquisa usando a API Interactions.

npx skills add https://github.com/google-gemini/gemini-managed-agents-templates --skill script-writing

Script Writing

Generate a naturalistic, multi-character radio show script directly via the LLM. The script features host Paul taking calls from people around the world, with advanced audio tags.

Embedded Script

python3 skills/script-writing/scripts/generate_script.py --workspace ./workspace --style debate

Arguments

ArgumentDefaultDescription
--workspaceworkspaceRoot workspace directory
--styledefaultShow format (see styles below)
--context""Additional tone/style notes inferred from user prompts (e.g., "emphasize the technical details", "make it sound like a late night show"). Applies to ALL styles. Keep brief. Do NOT use to specify stories/topics.

Styles

StyleCallersFormatUse when user says...
debate2 per topic, opposing viewsStructured back-and-forth, Paul moderates"opposing views", "debate", "both sides"
roundtable3-4, different anglesCollaborative discussion, callers build on each other"roundtable", "panel", "discussion"
interview1-2 with direct experienceQ&A format, Paul asks probing questions"interview", "deep dive", "expert"
explainer2-3, each explains an aspectTeach the audience, Paul asks clarifying questions"explain", "break it down", "what is"
defaultSame as debateDefault when no style specified(anything else)

Examples

# HN discussion with opposing views, applying context
python3 skills/script-writing/scripts/generate_script.py \
  --workspace ./workspace --style debate --context "make it sound like a late night show"

# Panel discussion about a GitHub repo with context notes
python3 skills/script-writing/scripts/generate_script.py \
  --workspace ./workspace --style roundtable --context "emphasize the performance improvements"

# Interview with an expert about a paper
python3 skills/script-writing/scripts/generate_script.py \
  --workspace ./workspace --style interview

# Explain a new technology
python3 skills/script-writing/scripts/generate_script.py \
  --workspace ./workspace --style explainer

What it does

  1. Reads all research from {workspace}/data/research/*.md.
  2. Builds a system prompt with the base format rules + style-specific caller/structure instructions.
  3. Calls Gemini via the Interactions API (client.interactions.create()).
  4. Saves the script to {workspace}/data/script.md.

Dependencies

  • google-genai (>= 2.0.0)

Output

  • Script File: {workspace}/data/script.md
  • Format: Plain text, each line starting with Speaker: dialogue

Cast

SpeakerRolePersonality
PaulHostProfessional but relatable British moderator
CallersCall-insAmateur, rough, natural — from various cities around the world

Script Format Rules

  • Every line: SpeakerName: [audio tag] Dialogue text
  • Must include audio tags in square brackets (e.g., [sighs], [excitedly]).
  • Callers should sound amateurish (include "uh", "like", natural pauses).
  • Short punchy sentences — spoken word, not prose.
  • ~450-500 words total (~3 minutes when spoken).

Mais skills de google-gemini

agent-tui
google-gemini
Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications…
gemini-api-cli
google-gemini
Guia para usar a ferramenta de linha de comando da API Gemini. Use quando precisar interagir com a API Gemini via linha de comando, gerenciar agentes ou gerar mídia (imagens,…
behavioral-evals
google-gemini
Orientação para criar, executar, corrigir e promover avaliações comportamentais. Use ao verificar a lógica de decisão do agente, depurar falhas, depurar prompt…
gemini-live-api-dev
google-gemini
We need to translate the given text from English to Brazilian Portuguese. The text describes a real-time bidirectional streaming capability with Gemini over WebSockets. It mentions audio, video, text, audio input/output specs, video frames, automatic transcriptions, voice activity detection, interruption handling, native audio features (affective dialog, proactive audio, thinking mode), function calling, Google Search grounding, session management with context compression, resumption, etc. We must preserve product names, protocol names, URLs, numbers, technical terms. The name "gemini-live-api-dev" is not in the text, so we don't include it. We only translate the text inside <text>. No extra commentary, no labels. The text ends with "and..." so we keep that as is. Translation: "Streaming bidirecional em tempo real com Gemini via WebSockets para conversas de áudio, vídeo e texto. Suporta entrada/saída de áudio (PCM 16 kHz), quadros de vídeo, texto e transcrições automáticas com detecção
gemini-omni-flash-api
google-gemini
Use esta habilidade para edição generativa de vídeo, texto para vídeo, geração de vídeo com referência de imagem e animações de transição de primeiro quadro para vídeo usando o…
gemini-api-dev
google-gemini
We need to translate the given text from English to Brazilian Portuguese. The text describes building applications with Google's Gemini models. We must preserve product names, protocol names, URLs, numbers, technical terms. The name "gemini-api-dev" is not in the text, so we don't include it. We translate only the text inside <text>. No extra commentary, no labels. The text: "Build applications with Google's Gemini models, supporting multimodal content, function calling, and structured outputs across Python, JavaScript, Go, and Java. Access current Gemini 3 models (Pro, Flash, Pro Image) with 1M token context; legacy Gemini 2.x and 1.5 models are deprecated Supports text generation, image/audio/video understanding, function calling, structured JSON output, code execution, context caching, and embeddings Official SDKs available: google-genai (Python),..." We need to translate fluently but preserve terms like "Gemini models", "multimodal content", "function calling", "structured outputs", "Python", "JavaScript", "Go",
gemini-interactions-api
google-gemini
Interface unificado para modelos e agentes Gemini com estado no servidor, streaming e orquestração de ferramentas. Suporta vários modelos atuais (gemini-3-flash-preview, gemini-3-pro-preview, gemini-2.5-flash/pro) e o agente Deep Research; substitui automaticamente IDs de modelos obsoletos por alternativas atuais. Descarrega o histórico de conversas para o servidor via previous_interaction_id para interações multi-turno com estado, sem gerenciamento manual de histórico. Orquestração de ferramentas integrada, incluindo...
deliver
google-gemini
Publica uma versão condensada do briefing em um webhook de entrada do Google Chat ou Slack, para que a execução diária se entregue sozinha — pula silenciosamente quando não há webhook…