Files

Emanuel Almeida 9404af7ac9 feat: sync all plugins, skills, agents updates

New plugins: core-tools
New skills: auto-expense, ticket-triage, design, security-check,
  aiktop-tasks, daily-digest, imap-triage, index-update, mindmap,
  notebooklm, proc-creator, tasks-overview, validate-component,
  perfex-module, report, calendar-manager
New agents: design-critic, design-generator, design-lead,
  design-prompt-architect, design-researcher, compliance-auditor,
  metabase-analyst, gitea-integration-specialist
Updated: all plugin configs, knowledge datasets, existing skills

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-05 17:16:32 +00:00

3.0 KiB

Raw Permalink Blame History

Protocolo de Knowledge Sources v2.0

Data: 2026-02-12 Propósito: Consulta inteligente de conhecimento com dual-source (NotebookLM + Dify KB)

Visão Geral

Skills e agents consultam conhecimento via dual-source:

NotebookLM (primario) - Gemini 2.5 RAG com conhecimento curado
Dify KB (fallback) - Datasets tematicos quando NotebookLM insuficiente

Fluxo de Consulta

1. Skill/Agent precisa conhecimento
2. Consultar NotebookLM (primario)
   → mcp__notebooklm__notebook_query notebook_id:"<id>" query:"<tema>"
3. Se resultado suficiente → usar
4. Se insuficiente → consultar Dify KB (fallback)
   → mcp__dify-kb__dify_kb_retrieve_segments dataset:"<nome>" query:"<tema>"
5. Agregar resultados

Como Consultar NotebookLM (Primario)

1. Identificar Notebook (via notebooklm-mapping.json)

// Ler mapeamento
const mapping = require('./notebooklm-mapping.json').mapping;
const notebook = mapping['WordPress'];
// → {notebook_id: "5be0d1a6-...", notebook_title: "WordPress e Elementor"}

2. Consultar Notebook

mcp__notebooklm__notebook_query notebook_id:"5be0d1a6-00f2-4cd9-b835-978cb7721601" query:"elementor custom widgets"

3. Múltiplos Notebooks

Quando o tema cobre vários notebooks, consultar em paralelo:

# Paralelo: WordPress + Dev
mcp__notebooklm__notebook_query notebook_id:"5be0d1a6-..." query:"tema"
mcp__notebooklm__notebook_query notebook_id:"24947ffa-..." query:"tema"

Como Consultar Dify KB (Fallback)

1. Identificar Dataset

mcp__dify-kb__dify_kb_retrieve_segments({
  dataset: "WordPress",
  query: "elementor custom widgets",
  top_k: 5
});

2. Consulta Paralela (Múltiplos Datasets)

// Lançar consultas em paralelo para datasets prioritarios
const results = await Promise.all([
  dify_kb_retrieve(dataset1, query),
  dify_kb_retrieve(dataset2, query)
]);

Mapeamento Notebooks

Ficheiro central: notebooklm-mapping.json (mesmo directorio)

51 notebooks disponiveis cobrindo:

Marketing (5 notebooks)
Desenvolvimento (8 notebooks)
Infraestrutura (3 notebooks)
Gestao (3 notebooks)
Negocio (4 notebooks)
Automacao (3 notebooks)
Design (2 notebooks)

Template para Agents

Secção standard nos agents:

## Knowledge Sources (Consultar SEMPRE)

### NotebookLM (Primario - usar PRIMEIRO)

mcp__notebooklm__notebook_query notebook_id:"" query:""


### Dify KB (Secundario - se NotebookLM insuficiente)

mcp__dify-kb__dify_kb_retrieve_segments dataset:"" query:""

Template para Skills

Adicionar no SKILL.md:

# PRIMARIO: NotebookLM (Gemini 2.5 RAG)
# mcp__notebooklm__notebook_query notebook_id:"<uuid>"
# FALLBACK: Dify KB
mcp__dify-kb__dify_kb_retrieve_segments dataset:"<nome>" query:"<tema>"

Metricas

Rastrear na instrumentacao:

kb_source: "notebooklm" ou "dify"
kb_consulted: 1 se consultou KB
kb_fallback: 1 se precisou de Dify apos NotebookLM

Protocolo v2.0 | 2026-02-12 | Dual-source (NotebookLM + Dify KB)

3.0 KiB Raw Permalink Blame History