P5-P8: TDD+SDD completion — 156 suites, 67 specs, 72.7% frontmatter

P5: 6 TDD+SDD for research skills (48/48 tests)
P6: 11 TDD+SDD for top-level skills (53/53 tests)
P7: 10 SDD specs for CORA-Eval suites
P8: 22 SKILL.md frontmatter YAML fixes (broomva + system)

TDD: 139 -> 156 suites (104% coverage)
SDD: 57 -> 67 specs (44.7% coverage)
Frontmatter YAML: 78 -> 109 (72.7%)

Author: marce

README.md

@@ -10,10 +10,11 @@
 
 [![Agentes](https://img.shields.io/badge/Agentes-125-6366f1?style=flat-square)](agents/)
 [![MCPs](https://img.shields.io/badge/MCP_Servers-46-0ea5e9?style=flat-square)](opencode.json)
-[![Skills](https://img.shields.io/badge/Skills-115-10b981?style=flat-square)](skills/)
-[![TDD](https://img.shields.io/badge/TDD-92.7%25-22c55e?style=flat-square)]()
-[![SDD](https://img.shields.io/badge/SDD-38%25-facc15?style=flat-square)](specs/)
+[![Skills](https://img.shields.io/badge/Skills-150-10b981?style=flat-square)](skills/)
+[![TDD](https://img.shields.io/badge/TDD-156_suites-22c55e?style=flat-square)]()
+[![SDD](https://img.shields.io/badge/SDD-67_specs-0ea5e9?style=flat-square)](specs/)
 [![Evolucoes](https://img.shields.io/badge/Evolucoes-14-c084fc?style=flat-square)](evolution/)
+[![GitHub](https://img.shields.io/badge/GitHub-v5.0.0-333?style=flat-square)](https://github.com/MarceloClaro/OpenCode_Ecosystem)
 [![Z3](https://img.shields.io/badge/Z3_Prover-4.16-8b5cf6?style=flat-square)]()
 [![Status](https://img.shields.io/badge/Status-Producao-22c55e?style=flat-square)]()
 

skills/agent-forum/specs/SPEC_TOP_forum.md

@@ -0,0 +1,64 @@
+# SPEC_TOP_forum — Agent Forum TDD Specification
+
+**Skill:** agent-forum  
+**Source:** scripts/moderator.py → Forum, AgentSpeech, ModeratorSpeech  
+**Framework:** pytest  
+**Status:** Spec-Driven
+
+---
+
+## CT-1: test_init — Inicializacao de Forum e componentes
+
+**Objetivo:** Verificar que `Forum` inicializa com agentes, perfil de
+debate, canal de memoria e estado `IDLE`.
+
+**Passos:**
+1. Instanciar `Forum(agents=["A","B"], debate_profile="LOGICO_RIGOROSO")`
+2. Verificar `len(forum.agents) == 2`
+3. Verificar `forum.debate_profile` e `forum.stage == IDLE`
+4. Verificar canal e `MemoryChannel`
+
+**Esperado:** Forum pronto para abrir sessao.
+
+---
+
+## CT-2: test_session_lifecycle — Ciclo open → publish → conclude
+
+**Objetivo:** Validar o ciclo completo de uma sessao de debate: abertura,
+publicacao de discursos por agentes, e conclusao.
+
+**Passos:**
+1. `open_session("Topico X")` → stage muda para OPEN
+2. `publish("AgenteA", "conteudo", confidence=0.85)` → AgentSpeech criado
+3. `conclude()` → stage muda para CLOSED
+4. `get_json_report()` → contem topic, stage, total_speeches
+
+**Esperado:** Fluxo completo sem erros.
+
+---
+
+## CT-3: test_game_theory — Analise de Teoria dos Jogos
+
+**Objetivo:** Confirmar que `run_game_theory_analysis()` retorna
+analise do Dilema do Prisioneiro e `describe_strategies()` retorna
+catalogo com 38 estrategias.
+
+**Passos:**
+1. `run_game_theory_analysis()` → contem "prisoners_dilemma"
+2. `describe_strategies()` → `total == 38`, contem "categorias"
+
+**Esperado:** Engine de game theory funcional.
+
+---
+
+## CT-4: test_available — Modo offline/demo sem LLM
+
+**Objetivo:** Garantir que Forum funciona sem API key (modo offline)
+gerando fallback synthesis e completando o ciclo de debate.
+
+**Passos:**
+1. Criar Forum sem api_key
+2. Abrir sessao, publicar discurso, concluir
+3. Verificar que transcript contem entradas e stage == CLOSED
+
+**Esperado:** Operacao normal mesmo sem LLM disponivel.

skills/agent-forum/tests/test_forum.py

@@ -0,0 +1,98 @@
+"""
+TDD tests for Agent Forum — Debate multiagente com moderador LLM.
+CT-1: test_init — inicializacao de Forum, AgentSpeech, ModeratorSpeech
+CT-2: test_session_lifecycle — open_session → publish → conclude
+CT-3: test_game_theory — run_game_theory_analysis e describe_strategies
+CT-4: test_available — Forum sem LLM (modo offline/demo)
+"""
+
+import os
+import sys
+import pytest
+
+SCRIPT_DIR = os.path.join(os.path.dirname(__file__), "..", "scripts")
+sys.path.insert(0, SCRIPT_DIR)
+
+from moderator import (
+    Forum, AgentSpeech, ModeratorSpeech,
+    ForumModerator, ForumMonitor, SessionConfig,
+    MemoryChannel, DebateStage, ModeratorMode,
+)
+
+
+class TestAgentForum:
+
+    def test_init(self):
+        forum = Forum(
+            agents=["QueryEngine", "MediaEngine"],
+            debate_profile="LOGICO_RIGOROSO",
+            language="pt-BR",
+        )
+        assert len(forum.agents) == 2
+        assert forum.debate_profile == "LOGICO_RIGOROSO"
+        assert forum.stage == DebateStage.IDLE
+        assert forum.is_active is False
+        assert isinstance(forum._channel, MemoryChannel)
+
+    def test_session_lifecycle(self):
+        forum = Forum(
+            agents=["AgenteA", "AgenteB"],
+            debate_profile="ESTRATEGISTA",
+            language="pt-BR",
+        )
+
+        opening = forum.open_session("Teste de debate")
+        assert forum.stage == DebateStage.OPEN
+        assert forum.is_active is True
+        assert isinstance(opening, ModeratorSpeech)
+        assert "Teste de debate" in opening.content
+
+        speech = forum.publish(
+            "AgenteA",
+            "Dados mostram tendencia de alta no setor.",
+            confidence=0.85,
+            stance="Apoio",
+        )
+        assert isinstance(speech, AgentSpeech)
+        assert speech.source == "AgenteA"
+        assert speech.confidence == 0.85
+
+        conclusion = forum.conclude()
+        assert forum.stage == DebateStage.CLOSED
+        assert isinstance(conclusion, ModeratorSpeech)
+
+        report = forum.get_json_report()
+        assert report["topic"] == "Teste de debate"
+        assert report["stage"] == "closed"
+        assert report["total_speeches"] >= 1
+
+    def test_game_theory(self):
+        forum = Forum(
+            agents=["P1", "P2"],
+            debate_profile="ESTRATEGISTA",
+            language="pt-BR",
+        )
+        forum.open_session("Analisar cooperacao")
+
+        analysis = forum.run_game_theory_analysis()
+        assert "prisoners_dilemma" in analysis
+        pd = analysis["prisoners_dilemma"]
+        assert "nash_equilibria" in pd or "insight" in pd
+
+        strategies = forum.describe_strategies()
+        assert strategies["total"] == 38
+        assert "categorias" in strategies
+        assert "perfis_predefinidos" in strategies
+
+    def test_available(self):
+        forum = Forum(agents=["Solo"], language="pt-BR")
+        forum.open_session("Sessao offline")
+
+        speech = forum.publish("Solo", "Analise sem LLM disponivel.")
+        assert speech.source == "Solo"
+
+        transcript = forum.transcript
+        assert len(transcript) >= 2
+
+        forum.conclude()
+        assert forum.stage == DebateStage.CLOSED

skills/broomva/content-engine/SKILL.md

@@ -1,5 +1,8 @@
 ---
 name: content-engine
+category: broomva
+version: "1.0.0"
+kind: python
 description: "Full-stack AI content studio — orchestrates visual DNA compilation, cinematic generation (via Higgsfield CLI or MCP), browser-automated tool execution, and multi-platform distribution into a unified content pipeline. Compiles brand identity, character sheets, and style guides into persistent knowledge (Karpathy compile-then-query pattern), then generates premium cinematic content using Higgsfield (30+ models including Soul V2, Nano Banana 2, Veo 3.1, Kling 3.0, Seedance 2.0, Flux 2), Soul Cinema, Weavy, and ComfyUI with consistent character identity and intentional visual direction. Triggers on: 'content engine', 'generate campaign', 'compile brand', 'cinematic content', 'AI content studio', 'batch generate', 'content pipeline', 'visual DNA', 'character consistency', 'higgsfield', 'marketing studio', 'product photoshoot', 'soul character'."
 ---
 

skills/broomva/content-engine/extensions/opencaptions/SKILL.md

@@ -1,8 +1,10 @@
 ---
 name: content-engine-opencaptions
+category: broomva
+version: "1.0.0"
+kind: python
 slug: opencaptions
 hook: post-production
-version: "0.1.0"
 description: "OpenCaptions extension for Content Engine — adds intent-driven CWI (Caption With Intent) captions to the post-production pipeline. Hooks into the grade → caption → final stage. Generates captions that understand video intent (pitch, volume, emotion, emphasis) and style themselves accordingly with variable font weight, size, and color. Uses the OpenCaptions CLI or MCP server. Triggers on: 'add captions', 'opencaptions', 'CWI captions', 'intent captions'."
 inputs:
   - "graded video asset from post-production pipeline"

skills/broomva/content-engine/skills/content-engine-autopilot/SKILL.md

@@ -1,5 +1,8 @@
 ---
 name: content-engine-autopilot
+category: broomva
+version: "1.0.0"
+kind: python
 description: "Browser Orchestration — Playwright-driven generation at scale. Claude Code runs your entire content pipeline in the browser. Saves authentication sessions per tool, executes batch generation using compiled identity, and organizes output automatically. Supports Higgsfield, Weavy, Artlist, and extensible to any web-based generation tool. Triggers on: 'autopilot', 'browser automation', 'batch generate', 'setup tool', 'automated generation'."
 ---
 

skills/broomva/content-engine/skills/content-engine-cinema/SKILL.md

@@ -1,5 +1,8 @@
 ---
 name: content-engine-cinema
+category: broomva
+version: "1.0.0"
+kind: python
 description: "Cinematic Generation Layer — the taste and technique library for premium AI content. Codifies start-frame doctrine, camera style vocabulary (Anderson/Fincher/Nolan/Villeneuve/Kubrick), node pipeline architecture, scene generation formulas, and 25+ design styles with exact prompts. Tier-1 generation via Higgsfield CLI (30+ models — Soul V2, Nano Banana 2, Veo 3.1, Kling 3.0, Seedance 2.0, Flux 2, Marketing Studio). Triggers on: 'generate content', 'cinematic', 'create scene', 'start frame', 'style library', 'generate campaign', 'AI filmmaking', 'higgsfield generate', 'soul cinema', 'marketing studio'."
 ---
 

skills/broomva/content-engine/skills/content-engine-dna/SKILL.md

@@ -1,7 +1,9 @@
 ---
 name: content-engine-dna
+category: broomva
+version: "1.0.0"
+kind: python
 description: "Visual DNA Compiler -- compiles raw brand assets, character references, and style inspiration into persistent, structured identity files. Uses Gemini multimodal analysis to extract color palettes, composition rules, lighting patterns, and texture preferences. Generates tool-specific prompt fragments for Nano Banana Pro, Soul Cinema, Weavy, and ComfyUI. Inspired by Karpathy's LLM Wiki (compile-then-query) and MemPalace spatial hierarchy. Triggers on: 'compile brand', 'extract DNA', 'character sheet', 'style guide', 'compile identity', 'brand analysis'."
-version: 1.0.0
 author: broomva
 tags:
   - visual-identity

skills/broomva/content-engine/skills/content-engine-loop/SKILL.md

@@ -1,5 +1,8 @@
 ---
 name: content-engine-loop
+category: broomva
+version: "1.0.0"
+kind: python
 description: "Content Loop + Distribution — compounds existing broomva skills into a unified content lifecycle. Orchestrates /blog-post, /content-creation, /social-intelligence, /brainrot-for-good, and /brand-icons for multi-platform distribution. Adds performance tracking, feedback-driven identity refinement, content calendar, and campaign management. Triggers on: 'distribute content', 'content loop', 'publish campaign', 'content calendar', 'track performance'."
 ---
 

skills/broomva/decision-log/SKILL.md

@@ -1,5 +1,8 @@
 ---
 name: decision-log
+category: broomva
+version: "1.0.0"
+kind: python
 description: >
   Captures a decision with context, alternatives considered, and rationale, then links
   it to the relevant project doc in the vault. Creates a searchable decision record.