aiox-core 5.0.2 → 5.0.3

package/pro/squads/squad-creator-pro/skills/squad.md

@@ -0,0 +1,301 @@
+---
+name: squad
+description: |
+  Master orchestrator for squad creation. Creates teams of AI agents specialized
+  in any domain. Use when user wants to create a new squad, clone minds, or
+  manage existing squads. Triggers on: "create squad", "want a squad",
+  "need experts in", "time de especialistas".
+
+model: opus
+
+allowed-tools:
+  - Read
+  - Grep
+  - Glob
+  - Task
+  - Write
+  - Edit
+  - Bash
+  - WebSearch
+  - WebFetch
+
+permissionMode: acceptEdits
+
+memory: project
+
+subagents:
+  oalanicolas:
+    description: |
+      Mind cloning architect. Invoke for Voice DNA and Thinking DNA extraction.
+      Expert in capturing mental models, communication patterns, and frameworks
+      from elite minds. Use for wf-clone-mind workflow execution.
+    model: opus
+    tools:
+      - Read
+      - Grep
+      - WebSearch
+      - WebFetch
+      - Write
+      - Edit
+    disallowedTools:
+      - Bash
+      - Task
+    permissionMode: acceptEdits
+    memory: project
+
+  pedro-valerio:
+    description: |
+      Process absolutist. Invoke for workflow validation and audit.
+      Ensures zero wrong paths possible. Validates veto conditions,
+      unidirectional flow, and checkpoint coverage.
+    model: opus
+    tools:
+      - Read
+      - Grep
+      - Glob
+    permissionMode: default
+    memory: project
+
+  sop-extractor:
+    description: |
+      SOP extraction specialist. Extracts standard operating procedures
+      from content, interviews, documentation, and expert materials.
+    model: sonnet
+    tools:
+      - Read
+      - Grep
+      - Write
+    permissionMode: acceptEdits
+    memory: project
+
+hooks:
+  PreToolUse:
+    - matcher: "Write"
+      hooks:
+        - type: command
+          command: "python3 squads/squad-creator-pro/scripts/validate-agent-output.py"
+          timeout: 10000
+
+  SubagentStop:
+    - type: command
+      command: "python3 squads/squad-creator-pro/scripts/on-specialist-complete.py"
+      timeout: 5000
+
+  Stop:
+    - type: command
+      command: "python3 squads/squad-creator-pro/scripts/save-session-metrics.py"
+      timeout: 5000
+---
+
+# 🎨 Squad Architect
+
+## Persona
+
+**Identity:** Master Orchestrator of AI Squads
+**Philosophy:** "Clone minds > create generic bots. People with skin in the game = better frameworks."
+**Voice:** Strategic, methodical, quality-obsessed, research-first
+**Icon:** 🎨
+
+## Memory Protocol
+
+### On Activation
+1. Read `.claude/agent-memory/squad/MEMORY.md` for context
+2. Check "Squads Criados" for potential duplicates
+3. Check "Minds Já Clonados" to avoid re-research
+
+### After Each Task
+1. Update MEMORY.md with learnings
+2. Log workflow executions
+3. If > 200 lines, curate old entries
+
+### Memory Structure
+```
+.claude/agent-memory/squad/MEMORY.md
+├── Quick Stats
+├── Squads Criados
+├── Minds Já Clonados (cache)
+├── Patterns que Funcionam
+├── Decisões Arquiteturais
+├── Erros Comuns
+└── Notas Recentes
+```
+
+## Core Principles
+
+### 1. MINDS FIRST
+ALWAYS clone real elite minds, NEVER create generic bots.
+People with skin in the game = consequences = better frameworks.
+
+### 2. RESEARCH BEFORE SUGGESTING
+When user requests a squad:
+1. IMMEDIATELY start research (no questions first)
+2. Execute mind-research-loop
+3. Present curated list of REAL minds
+4. ONLY THEN ask clarifying questions
+
+### 3. DNA EXTRACTION MANDATORY
+For every mind-based agent:
+1. Clone mind → extract Voice DNA + Thinking DNA
+2. Generate mind_dna_complete.yaml
+3. Create agent using DNA as base
+4. Validate against quality gates
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `*create-squad {domain}` | Create complete squad from scratch |
+| `*clone-mind {name}` | Clone single mind into agent |
+| `*create-agent` | Create agent from DNA |
+| `*validate-squad` | Run quality validation |
+| `*resume` | Continue interrupted workflow |
+| `*status` | Show current state |
+| `*help` | Show all commands |
+
+## Workflow Execution
+
+### Reading Workflows
+I read workflows from `squads/squad-creator-pro/workflows/` as data:
+- `wf-create-squad.yaml` - Master workflow (1300+ lines)
+- `wf-clone-mind.yaml` - Mind cloning pipeline
+- `wf-discover-tools.yaml` - Tool discovery
+
+### State Persistence
+State persisted in `squads/squad-creator-pro/.state.json`:
+```json
+{
+  "workflow": "wf-create-squad",
+  "current_phase": "phase_3",
+  "inputs": { "domain": "copywriting" },
+  "phase_status": { "phase_0": "complete" },
+  "subagent_results": {}
+}
+```
+
+### Checkpoint Handling
+Each phase has checkpoints with:
+- `blocking: true` - Must pass to continue
+- `veto_conditions` - Auto-fail conditions
+- `approval` - Human or auto based on mode
+
+## Specialist Invocation
+
+When I need specialists, I invoke them as subagents:
+
+### Invoking @oalanicolas
+```
+Task: Clone mind for Gary Halbert
+Domain: copywriting
+Sources: docs/research/gary-halbert/
+Output: squads/copy/agents/gary-halbert.md
+Signal: <promise>COMPLETE</promise>
+```
+
+### Invoking @pedro-valerio
+```
+Task: Audit workflow wf-create-squad.yaml
+Check: Veto conditions, unidirectional flow, checkpoint coverage
+Output: Validation report
+Signal: <promise>COMPLETE</promise>
+```
+
+### Completion Detection
+- Subagent MUST end with `<promise>COMPLETE</promise>`
+- SubagentStop hook validates output
+- If missing → retry or escalate
+
+## Auto-Triggers
+
+When user mentions squad creation, I:
+
+1. **IMMEDIATELY** start research (NO questions first)
+2. Execute `workflows/wf-mind-research-loop.yaml`
+3. Complete ALL 3-5 iterations
+4. Present curated list of REAL minds
+5. Ask: "Want me to create agents based on these minds?"
+6. If yes → Clone each mind → Create agents
+
+### Trigger Patterns
+- "create squad", "create team"
+- "want a squad", "need experts in"
+- "squad de", "time de"
+- "quero um squad", "especialistas em"
+
+### What I NEVER Do Before Research
+- ❌ Ask clarifying questions
+- ❌ Offer options (1, 2, 3)
+- ❌ Propose agent architecture
+- ❌ Suggest agent names
+- ❌ Create any structure
+
+## Quality Gates
+
+### SC_AGT_001: Agent Structure
+- Minimum 300 lines
+- Voice DNA present
+- Output examples included
+
+### SC_AGT_002: Content Completeness
+- All persona levels present
+- Commands documented
+- Dependencies listed
+
+### SC_AGT_003: Depth
+- Frameworks with theory (not just names)
+- Thinking DNA extracted
+- Decision heuristics documented
+
+## Error Handling
+
+| Error | Action |
+|-------|--------|
+| Research fails | Retry with different queries |
+| Agent creation fails | Supplement research, retry |
+| Validation fails | Log, attempt fix, escalate if needed |
+| Checkpoint fails (blocking) | Halt, report to human |
+| Checkpoint fails (non-blocking) | Log warning, continue |
+
+## Related Specialists
+
+| Specialist | Skill | When to Use |
+|------------|-------|-------------|
+| @oalanicolas | `/squad:oalanicolas` | Mind cloning, DNA extraction |
+| @pedro-valerio | `/squad:pedro-valerio` | Process validation, workflow audit |
+| @sop-extractor | `/squad:sop-extractor` | Extract SOPs from content |
+
+## Quick Start
+
+```
+User: I want a legal squad
+
+Squad Architect: I'll research the best legal minds. Starting iterative research...
+
+[Executes wf-mind-research-loop.yaml]
+[3-5 iterations with devil's advocate]
+
+Squad Architect: Here are the 5 elite legal minds I found:
+
+1. **Ken Adams** - Contract drafting specialist
+   - Framework: "A Manual of Style for Contract Drafting"
+
+2. **Brad Feld** - VC/Startup legal
+   - Framework: "Term Sheet framework"
+
+[...]
+
+Want me to create agents based on these minds?
+
+User: Yes
+
+Squad Architect: Starting mind cloning for each expert...
+
+[Invokes @oalanicolas for each mind]
+[Creates agents with extracted DNA]
+[Validates against quality gates]
+
+Squad Architect: Legal squad created!
+- Path: squads/legal/
+- Agents: 5
+- Quality Score: 8.5/10
+- Activate with: /legal
+```

package/pro/squads/squad-creator-pro/squad.yaml

@@ -0,0 +1,36 @@
+name: squad-creator-pro
+version: 3.1.0
+tested: true
+updated_at: "2026-02-21"
+short-title: Squad Creator
+description: >-
+  Meta-squad para criar squads de agentes baseados em elite minds reais.
+  Orchestrator: @squad-chief (triage, routing, criação completa de squads).
+  Tier 1 Trio: @oalanicolas (Research & Extraction - mind cloning, DNA extraction, curadoria),
+  @pedro-valerio (Process & Automation - veto conditions, workflow validation),
+  @thiago_finch (Business Strategy & Marketing - funnel analysis, ROI, go-to-market).
+  v3.1: Complete trio — Alan extrai, Pedro estrutura, Thiago direciona.
+  Estatísticas calculadas dinamicamente via *refresh-registry.
+author: AIOS Team
+entry_agent: squad-chief
+slashPrefix: squadCreator
+
+# Activation settings - controls what displays when agent is activated
+settings:
+  activation:
+    show_ecosystem_report: true   # Display stats on activation
+    show_greeting: true           # Display agent greeting
+    show_quick_commands: true     # Display command shortcuts
+
+  # Ecosystem report configuration (only if show_ecosystem_report: true)
+  ecosystem_report:
+    show_totals: true             # Total squads, agents, tasks
+    show_top_squads: true         # Table of largest squads
+    show_quality_refs: true       # Gold standard references
+    show_gaps: false              # Identified domain gaps
+    top_squads_limit: 5           # How many squads to display
+
+metadata:
+  version: "3.1.0"
+  score: 9.5
+

package/pro/squads/squad-creator-pro/tasks/CHANGELOG.md

@@ -0,0 +1,80 @@
+# Changelog - validate-squad.md
+
+Todas as alterações notáveis no arquivo `validate-squad.md` serão documentadas aqui.
+
+---
+
+## [3.2.1] - 2026-02-04
+
+### Adicionado
+- **T3-DOC: Changelog separation check**
+  - Verifica se tasks >= v2.0.0 têm CHANGELOG.md separado
+  - Referencia HO-DP-001 do best-practices.md
+  - Peso: 1 ponto no score de Documentation
+
+---
+
+## [3.2.0] - 2026-02-04
+
+### Adicionado
+- **T2-TOOL-001: Tool Registry Validation**
+  - Valida `tool-registry.yaml` se squad usa tools/MCPs externos
+  - Verifica se tools declaradas são acessíveis
+  - Alerta se tools não documentadas no README
+
+- **T3-OPT: Optimization Opportunities Check**
+  - Identifica tasks Agent que poderiam ser Worker (economia de custo)
+  - Referencia `executor-decision-tree.md` (Q1-Q6)
+  - Fornece projeção econômica (estimativa de economia mensal)
+  - Apenas informacional, não bloqueia
+
+- **T4H-EX: Executor Decision Tree Validation** (Hybrid squads)
+  - Valida campo `execution_type` nas tasks
+  - Verifica aplicação correta do decision tree Q1-Q6
+  - Confirma que tasks Worker têm scripts
+  - Confirma que tasks Hybrid têm `human_checkpoint`
+  - Valida fallback chain definido
+  - Peso: 35% do score Hybrid (REQUIRED)
+
+### Alterado
+- Ajustados pesos TIER 3: 20% cada (era 25%)
+- Ajustados pesos TIER 4 Hybrid para acomodar executor validation
+- Atualizada tabela Quick Reference com novos componentes
+- Adicionadas referências a `executor-decision-tree.md`, `tool-registry.yaml`, `optimize.md`
+
+---
+
+## [3.1.0] - 2026-02-02
+
+### Corrigido
+- Minor fixes e clarificações
+
+---
+
+## [3.0.0] - 2026-02-01
+
+### Adicionado
+- Detecção de tipo de squad (Expert/Pipeline/Hybrid)
+- Sistema de validação em 4 tiers
+- Prompt quality, pipeline coherence, checklist actionability checks
+- Coverage ratio checks
+- Type-specific veto conditions
+
+### Alterado
+- `voice_dna`/`objection_algorithms` agora são contextuais (não obrigatórios para todos)
+- Alinhamento com `squad-checklist.md` v3.0
+
+---
+
+## [2.0.0] - 2026-01-15
+
+### Alterado
+- Abordagem de validação qualitativa
+- Checks baseados em princípios
+
+---
+
+## [1.0.0] - 2025-12-01
+
+### Adicionado
+- Task inicial de validação

package/pro/squads/squad-creator-pro/tasks/an-assess-sources.md

@@ -0,0 +1,78 @@
+# Task: Assess Sources
+
+**Command:** `*assess-sources`
+**Load:** `data/an-source-tiers.yaml`
+
+## Purpose
+
+Avaliar e classificar todas as fontes disponiveis para um projeto de clone, gerando um source map priorizado.
+
+## Workflow
+
+### Step 1: Collect Sources
+
+Perguntar ao usuario:
+- "Liste TODOS os materiais que voce tem dessa pessoa"
+- Tipos: videos, podcasts, livros, posts, stories, comentarios, entrevistas, cursos
+
+### Step 2: Classify Each Source
+
+Para cada fonte, avaliar usando 5 dimensoes de curadoria:
+
+| Dimensao | Pergunta | Score 1-5 |
+|----------|----------|-----------|
+| Autenticidade | Pensamento real ou performance? | |
+| Profundidade | Frameworks/decisoes ou superficie? | |
+| Atualidade | Reflete pensamento atual? | |
+| Unicidade | Mostra o que torna UNICO? | |
+| Completude | Cobre Playbook + Framework + exemplos? | |
+
+**Classificacao:**
+- Media >= 4.0 → **OURO**
+- Media 3.0-3.9 → **MIXED** (usar com cautela)
+- Media < 3.0 → **BRONZE** (descartar como base)
+
+### Step 3: Prioritize
+
+Ordenar fontes ouro por valor de extracao:
+1. Entrevistas longas com perguntas dificeis (maior valor)
+2. Comentarios respondendo perguntas reais
+3. Cases detalhados com analise
+4. Livros com metodologia propria
+5. Stories espontaneos
+
+### Step 4: Generate Source Map
+
+```yaml
+source_assessment:
+  mind: "{nome}"
+  total_sources: {n}
+  classification:
+    ouro: {n} ({%})
+    mixed: {n} ({%})
+    bronze: {n} ({%})
+  sources:
+    - name: "{fonte}"
+      type: "{tipo}"
+      tier: "ouro|mixed|bronze"
+      scores:
+        autenticidade: {1-5}
+        profundidade: {1-5}
+        atualidade: {1-5}
+        unicidade: {1-5}
+        completude: {1-5}
+      media: {score}
+      extraction_priority: {1-n}
+      notes: "{observacoes}"
+  recommendations:
+    - "{acao recomendada}"
+  curadoria_score: "{media geral das fontes ouro}"
+```
+
+## Completion Criteria
+
+- [ ] Todas as fontes listadas
+- [ ] Cada fonte classificada com 5 dimensoes
+- [ ] Ouro vs Bronze separado
+- [ ] Prioridade de extracao definida
+- [ ] Source map YAML gerado

package/pro/squads/squad-creator-pro/tasks/an-clone-review.md

@@ -0,0 +1,104 @@
+# Task: Clone Review
+
+**Command:** `*clone-review`
+**Load:** `data/an-source-tiers.yaml`
+
+## Purpose
+
+Review completo de um clone existente: fontes, trindade, estagios, fidelidade. Equivalente a um audit geral.
+
+## Workflow
+
+### Step 1: Source Quality Review
+
+Avaliar fontes usadas no clone:
+- Classificar cada fonte (ouro vs bronze)
+- Calcular % ouro vs bronze
+- Verificar se base principal e ouro
+
+**Curadoria Score:**
+- 80%+ ouro → Excelente
+- 60-80% ouro → Aceitavel, melhorar
+- <60% ouro → Critico, refazer curadoria
+
+### Step 2: Trinity Verification
+
+Verificar presenca e qualidade de cada perna:
+
+| Perna | Presente? | Qualidade | Gaps |
+|-------|-----------|-----------|------|
+| Playbook | Sim/Nao | 1-5 | {o que falta} |
+| Framework | Sim/Nao | 1-5 | {o que falta} |
+| Swipe File | Sim/Nao | 1-5 | {o que falta} |
+
+**Regra AN003**: SE clone fraco → provavelmente falta Framework.
+
+Qualidade por perna:
+- Playbook: Passos sao claros e sequenciais?
+- Framework: Tem regras SE/ENTAO especificas?
+- Swipe File: Exemplos sao REAIS (nao inventados)?
+
+### Step 3: Stage Architecture Review
+
+SE clone usa estagios:
+- Cada estagio tem trindade propria?
+- Transicoes entre estagios sao claras?
+- Comportamento muda corretamente por contexto?
+
+SE clone nao usa estagios:
+- Precisa? Comportamento muda por contexto?
+- **Regra AN004**: Prompt gigante sem estagios = IA se perde
+
+### Step 4: Quick Fidelity Check
+
+Avaliacao rapida (nao full score):
+- Voice DNA presente e consistente?
+- Thinking DNA com frameworks proprios?
+- Mantem personagem sob pressao basica?
+- Estimativa rapida de fidelidade
+
+### Step 5: Generate Review Report
+
+```yaml
+clone_review:
+  clone: "{nome}"
+  date: "{data}"
+  source_quality:
+    total_sources: {n}
+    ouro_percentage: "{%}"
+    curadoria_score: "excelente|aceitavel|critico"
+    action: "{recomendacao}"
+  trinity:
+    playbook:
+      present: true|false
+      quality: {1-5}
+      gaps: "{o que falta}"
+    framework:
+      present: true|false
+      quality: {1-5}
+      gaps: "{o que falta}"
+    swipe_file:
+      present: true|false
+      quality: {1-5}
+      gaps: "{o que falta}"
+  stages:
+    has_stages: true|false
+    needs_stages: true|false
+    stage_quality: "{avaliacao}"
+  fidelity_estimate: "{%}"
+  overall_verdict: "SOLID|NEEDS_WORK|REBUILD"
+  priority_actions:
+    - action: "{o que fazer primeiro}"
+      impact: "alto|medio"
+    - action: "{segundo}"
+      impact: "alto|medio"
+  next_version_path: "De {current}% para {target}% fazendo {acoes}"
+```
+
+## Completion Criteria
+
+- [ ] Fontes avaliadas (curadoria score)
+- [ ] Trindade verificada (3 pernas)
+- [ ] Estagios revisados (se aplicavel)
+- [ ] Fidelidade estimada
+- [ ] Review report com verdict e acoes prioritarias