wize-dev-kit 0.10.1 → 0.12.0

package/AGENTS.md

@@ -10,8 +10,8 @@ Treat `.wize/`, this `AGENTS.md`, and the installed `wize-*` skills as your oper
 instructions and persistent memory — not background reading. Read project state before
 acting; write what you change back into `.wize/` so the next session inherits it.
 
-Before editing, classify the demand via `/wize-help`: **Quick Dev** (small, predictable,
-~≤1h, no new feature / architecture / UX / security) or **Full Lifecycle**. Never pick
+Before editing, classify the demand via `/wize` (or `/wize-help`): **Quick Dev** (small, predictable,
+trivially scoped, no new feature / architecture / UX / security) or **Full Lifecycle**. Never pick
 Quick Dev just to skip artifacts.
 
 When a skill fans out to subagents, match the model tier to the task: a lightweight tier
@@ -34,4 +34,4 @@ decisions, or final adversarial review.
 
 ## Where to start
 
-Activate the orchestrator: `wize-orchestrator` (Wizer). Then ask `/wize-help`.
+Activate the orchestrator: `/wize` (or `/wize-help`). Wizer will guide you.

package/CHANGELOG.md

@@ -9,6 +9,54 @@ Format inspired by [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
 ## [Unreleased]
 
+## [0.12.0] — 2026-08-08
+
+**Intent-first UX overhaul (Epic 09).** The kit now routes by user intent, not just by lifecycle phase. 10 stories across 3 sprints: block-scalar parser fix, intent descriptions on all 68 skills, 56-entry intent routing table, `/wize` primary alias, onboarding one-liner, research dispatcher, `--sign-scope`, non-interactive install + honest uninstall, release/changelog skills, CI on push/PR. Suite green (532 tests, validate 78 files).
+
+### Added
+
+- **`/wize` alias** — primary entry point; `/wize-help` remains canonical. Onboarding reduced to `→ /wize`.
+- **Intent routing table** — 56 intent phrases mapped to skills in `wize-help` (e.g., "concorrência" → `wize-market-research`). Falls back to phase heuristic only when ambiguous.
+- **Intent descriptions** — all 68 skills/workflows carry a one-sentence `description:` telling the harness WHEN to invoke them. Block-scalar parser (`|`, `>`) now supported.
+- **`wize-sec-scope`** — guided scope creation for the security overlay (4 questions → `scope.md` + signed hash).
+- **`--sign-scope`** flag on `wize-sec-pentest` — recomputes SHA-256 without manual editing.
+- **Non-interactive install** — `install --profiles core,security --targets claude-code --yes` for CI/scripted installs. `--dry-run` supported.
+- **Honest uninstall** — removes rendered adapter directories (`.claude/skills/`, `.cursor/rules/`, etc.) in addition to `.wize/`. `--dry-run` supported.
+- **`wize-release`** skill — version bump + changelog + git tag from gated stories.
+- **`wize-changelog`** skill — Keep a Changelog format generated from done stories.
+- **CI workflow** — `.github/workflows/ci.yml` runs `npm test` + `npm run validate` on push/PR against Node 20.x and 22.x.
+- **Tool contract tests** — smoke tests for nmap, gitleaks, osv-scanner, grype, nuclei, nikto, sqlmap, ffuf (skip if absent, catch CLI drift).
+
+### Changed
+
+- **`wize-research`** — now a dispatcher that classifies intent and delegates to `wize-market-research`, `wize-domain-research`, or `wize-technical-research`.
+- **Phase labels** — normalized across all workflows (`2-plan-workflows` → `2-plan`, `2-to-3-boundary` → `3-solutioning`).
+- **Onboarding** — contextual one-liner (`→ /wize`) instead of multi-line menu. Detects brownfield/security-overlay.
+- **AGENTS.md template** — references `/wize` as primary, `/wize-help` as canonical.
+
+### Fixed
+
+- **Block scalar parser** — `readFrontmatter` now handles `|`, `>`, `|-`, `|+`, `|2` and chomp indicators. Fixes the `— |` bug that corrupted all 10 persona descriptions.
+
+## [0.11.0] — 2026-08-06
+
+**No-estimates policy.** The method now refuses to produce development estimates at any step — no hours, days, story points, or S/M/L/XL t-shirt sizes. Following the BMAD stance already stated in the architecture skill ("AI development speed has fundamentally changed"), estimates are treated as noise that only burns time and tokens. The only sizing signal that remains is binary: **does a story fit one PR? If not, slice it.** Suite green (417 tests, validate 74 files).
+
+### Removed
+
+- **`estimate` frontmatter field** from the story and epic templates (`wize-create-story`, `wize-create-epics-and-stories`).
+- **`estimateFor()`** helper and the `- **Estimativa:**` / `est S|M|L` output from the security remediation backlog (`security-overlay/_shared/backlog.js`) — the red-teamer's remediation epics/stories no longer carry a size estimate.
+- **"Estimation rough guide"** (S ≤ 4h, M 4h–1d, …) from `wize-create-story`.
+
+### Changed
+
+- **INVEST** — the "Estimable" letter is dropped on purpose across `wize-create-prd`, `wize-validate-prd`, `wize-create-story`, and `wize-create-epics-and-stories`. "Small (≤ 1 PR)" is now the only sizing test.
+- **`wize-sprint-planning`** — planning is by story count and priority, not velocity or person-day math; "Optimistic velocity" anti-pattern replaced with "don't estimate."
+- **`wize-retrospective`** — the dashboard reports stories committed vs shipped (a count) instead of velocity; the example retro no longer references M/L estimates.
+- **`wize-checkpoint-preview`** — the snapshot records "Commits so far" instead of "Time spent"; triggers refer to "larger stories," not "M/L stories."
+- **`wize-help`** — the Quick Dev classifier drops the "~≤1h" time threshold; it now reads "trivially scoped."
+- Each affected skill carries an explicit **"No estimates"** note so the rule holds when the skill is loaded standalone.
+
 ## [0.10.1] — 2026-08-02
 
 Documentation polish + tooling fixes. The security-overlay persona gets a Marvel name; the README (3 languages) is aligned to v0.10.1; a rendering bug and the test glob are fixed; CI is added. Suite green (418 tests — the security-overlay suite now runs under `npm test`).

package/README.es.md

@@ -250,7 +250,7 @@ npx wize-dev-kit version         # imprime la versión instalada del kit
 
 ## Estado
 
-**v0.10.1 — beta.** El ciclo completo (análisis → plan → solución → implementación) está montado con 10 agentes y una biblioteca estructurada de skills. Los releases recientes suman **contratos de misión** (`/wize-help mission` emite un contrato lleno de objetivo / fuentes de verdad / alcance / ACs / contrato de validación para la persona ejecutora), **`wize-grill`** (una pasada de entrevista hasta entendimiento compartido antes de cualquier paso de autoría) y **loop verification** en `wize-dev-story` (un loop de implementación auto-verificable con guarda de max-cycles que escala a `wize-correct-course`). El `security-overlay` (Pentester de IA) entrega un pipeline de pentest completo, un informe ejecutivo (puntuación de riesgo + briefing + plan de acción por IA) y planificación de remediación post-scan — validado de principio a fin contra una aplicación Laravel/PHP real. Los adapters de IDE para Claude Code, Cursor, Windsurf, Codex, Continue, Kimi Code, OpenCode y Antigravity se regeneran automáticamente — [OpenCode](docs/harnesses/opencode.md) recibe wiring nativo de `mode`/`agent`/`subtask`, la integración más profunda de las 9.
+**v0.11.0 — beta.** El método nunca produce estimaciones de desarrollo — ni horas, ni puntos, ni tallas de camiseta; una story se dimensiona solo por si cabe en un único PR. El ciclo completo (análisis → plan → solución → implementación) está montado con 10 agentes y una biblioteca estructurada de skills. Los releases recientes suman **contratos de misión** (`/wize-help mission` emite un contrato lleno de objetivo / fuentes de verdad / alcance / ACs / contrato de validación para la persona ejecutora), **`wize-grill`** (una pasada de entrevista hasta entendimiento compartido antes de cualquier paso de autoría) y **loop verification** en `wize-dev-story` (un loop de implementación auto-verificable con guarda de max-cycles que escala a `wize-correct-course`). El `security-overlay` (Pentester de IA) entrega un pipeline de pentest completo, un informe ejecutivo (puntuación de riesgo + briefing + plan de acción por IA) y planificación de remediación post-scan — validado de principio a fin contra una aplicación Laravel/PHP real. Los adapters de IDE para Claude Code, Cursor, Windsurf, Codex, Continue, Kimi Code, OpenCode y Antigravity se regeneran automáticamente — [OpenCode](docs/harnesses/opencode.md) recibe wiring nativo de `mode`/`agent`/`subtask`, la integración más profunda de las 9.
 
 ---
 

package/README.md

@@ -245,7 +245,7 @@ npx wize-dev-kit version         # print the installed kit version
 
 ## Status
 
-**v0.10.1 — beta.** The full lifecycle (analysis → plan → solution → implementation) is wired with 10 agents and a structured skill library. Recent releases add **mission contracts** (`/wize-help mission` emits a filled objective / sources-of-truth / scope / ACs / validation contract for the executing persona), **`wize-grill`** (an interview-to-shared-understanding pass before any authoring step), and **loop verification** in `wize-dev-story` (a self-checking implementation loop with a max-cycles guard that escalates to `wize-correct-course`). The `security-overlay` (AI Pentester) ships a complete pentest pipeline, a stakeholder report (risk score + briefing + AI action plan), and post-scan remediation planning — validated end-to-end against a real Laravel/PHP app. IDE adapters for Claude Code, Cursor, Windsurf, Codex, Continue, Kimi Code, OpenCode, and Antigravity are regenerated automatically — [OpenCode](docs/harnesses/opencode.md) gets native `mode`/`agent`/`subtask` wiring, the deepest integration of the 9.
+**v0.11.0 — beta.** The method never produces development estimates — no hours, points, or t-shirt sizes; a story is sized only by whether it fits a single PR. The full lifecycle (analysis → plan → solution → implementation) is wired with 10 agents and a structured skill library. Recent releases add **mission contracts** (`/wize-help mission` emits a filled objective / sources-of-truth / scope / ACs / validation contract for the executing persona), **`wize-grill`** (an interview-to-shared-understanding pass before any authoring step), and **loop verification** in `wize-dev-story` (a self-checking implementation loop with a max-cycles guard that escalates to `wize-correct-course`). The `security-overlay` (AI Pentester) ships a complete pentest pipeline, a stakeholder report (risk score + briefing + AI action plan), and post-scan remediation planning — validated end-to-end against a real Laravel/PHP app. IDE adapters for Claude Code, Cursor, Windsurf, Codex, Continue, Kimi Code, OpenCode, and Antigravity are regenerated automatically — [OpenCode](docs/harnesses/opencode.md) gets native `mode`/`agent`/`subtask` wiring, the deepest integration of the 9.
 
 ---
 

package/README.pt-BR.md

@@ -248,7 +248,7 @@ npx wize-dev-kit version         # imprime a versão instalada do kit
 
 ## Status
 
-**v0.10.1 — beta.** O ciclo completo (análise → plano → solução → implementação) está montado com 10 agentes e uma biblioteca estruturada de skills. Releases recentes adicionam **contratos de missão** (`/wize-help mission` emite um contrato preenchido de objetivo / fontes de verdade / escopo / ACs / validação para a persona executora), **`wize-grill`** (uma passagem de entrevista até entendimento compartilhado antes de qualquer passo de autoria) e **loop verification** no `wize-dev-story` (loop de implementação auto-verificável com guarda de max-cycles que escala para `wize-correct-course`). O `security-overlay` (Pentester de IA) entrega um pipeline de pentest completo, um relatório executivo (score de risco + briefing + plano de ação por IA) e planejamento de correção pós-scan — validado de ponta a ponta contra uma aplicação Laravel/PHP real. Os adapters de IDE para Claude Code, Cursor, Windsurf, Codex, Continue, Kimi Code, OpenCode e Antigravity são regenerados automaticamente — o [OpenCode](docs/harnesses/opencode.pt-BR.md) tem a integração mais profunda das 9, com `mode`/`agent`/`subtask` nativos.
+**v0.11.0 — beta.** O método nunca produz estimativas de desenvolvimento — nada de horas, pontos ou tamanhos de camiseta; uma story é dimensionada apenas por caber (ou não) em um único PR. O ciclo completo (análise → plano → solução → implementação) está montado com 10 agentes e uma biblioteca estruturada de skills. Releases recentes adicionam **contratos de missão** (`/wize-help mission` emite um contrato preenchido de objetivo / fontes de verdade / escopo / ACs / validação para a persona executora), **`wize-grill`** (uma passagem de entrevista até entendimento compartilhado antes de qualquer passo de autoria) e **loop verification** no `wize-dev-story` (loop de implementação auto-verificável com guarda de max-cycles que escala para `wize-correct-course`). O `security-overlay` (Pentester de IA) entrega um pipeline de pentest completo, um relatório executivo (score de risco + briefing + plano de ação por IA) e planejamento de correção pós-scan — validado de ponta a ponta contra uma aplicação Laravel/PHP real. Os adapters de IDE para Claude Code, Cursor, Windsurf, Codex, Continue, Kimi Code, OpenCode e Antigravity são regenerados automaticamente — o [OpenCode](docs/harnesses/opencode.pt-BR.md) tem a integração mais profunda das 9, com `mode`/`agent`/`subtask` nativos.
 
 ---
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "wize-dev-kit",
-  "version": "0.10.1",
+  "version": "0.12.0",
   "description": "Full-lifecycle AI-assisted development kit with Test Architect and Whiteport Design Studio embedded. Inspired by BMAD Method and WDS.",
   "keywords": [
     "ai",

package/src/app-overlay/wize-app-release-channels/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-app-release-channels
+description: "Use quando o app estiver pronto para distribuição e precisar configurar canais de release (beta, produção)."
 name: App Release Channels
 overlay: app
 owner: wize-agent-pm   # Maria Hill

package/src/app-overlay/wize-app-scaffold/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-app-scaffold
+description: "Use quando precisar criar o scaffold inicial de um projeto mobile com a stack aprovada pelo Fury."
 name: App Scaffold
 overlay: app
 owner: wize-agent-architect   # Tony

package/src/app-overlay/wize-app-store-listing/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-app-store-listing
+description: "Use quando o app estiver próximo do lançamento e precisar preparar a listagem na loja (copy, assets, metadados)."
 name: App Store Listing
 overlay: app
 owner: wize-agent-analyst   # Pepper (copy) + Mantis (visual brief)

package/src/builder-skills/wize-create-agent/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-create-agent
+description: "Use quando precisar criar um novo agente customizado sob .wize/custom/agents/."
 name: Create Agent
 owner: builder
 status: stub

package/src/builder-skills/wize-create-skill/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-create-skill
+description: "Use quando precisar criar uma nova skill single-step sob .wize/custom/skills/."
 name: Create Skill
 owner: builder
 status: stub

package/src/builder-skills/wize-create-workflow/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-create-workflow
+description: "Use quando precisar criar um novo workflow multi-step sob .wize/custom/workflows/."
 name: Create Workflow
 owner: builder
 status: stub

package/src/core-skills/wize-advanced-elicitation/skill.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-advanced-elicitation
+description: "Use quando uma resposta do usuário parecer subespecificada e precisar de técnicas de elicitação (5 Whys, laddering, premortem) para aprofundar o entendimento."
 name: Advanced Elicitation
 module: core
 status: stub

package/src/core-skills/wize-brainstorming/skill.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-brainstorming
+description: "Use quando precisar gerar ideias divergentes e convergir para as melhores opções em qualquer fase de decisão."
 name: Brainstorming
 module: core
 status: stub

package/src/core-skills/wize-customize/skill.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-customize
+description: "Use quando precisar personalizar um agente, skill ou workflow built-in sem alterar os arquivos originais do kit."
 name: Customize
 module: core
 status: ready

package/src/core-skills/wize-editorial-review-prose/skill.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-editorial-review-prose
+description: "Use quando um artefato Wize (brief, PRD, ADR, gate) precisar de revisão de prosa — clareza, tom, jargão e precisão."
 name: Editorial Review — Prose
 module: core
 status: ready

package/src/core-skills/wize-editorial-review-structure/skill.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-editorial-review-structure
+description: "Use quando um artefato Wize precisar de revisão estrutural — seções obrigatórias, ordenação e níveis de heading."
 name: Editorial Review — Structure
 module: core
 status: ready

package/src/core-skills/wize-grill/skill.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-grill
+description: "Use quando uma demanda chegar vaga e precisar de entrevista exaustiva para alcançar entendimento compartilhado antes de produzir qualquer artefato."
 name: Grill
 module: core
 status: ready
@@ -9,7 +11,7 @@ status: ready
 
 **Goal.** Interview the user exhaustively about a demand until both sides reach **shared understanding** — before any artifact is drafted. Sharper answers make a sharper brief, PRD, epic, story, or plan. Grill is an input-quality tool, not an artifact of its own.
 
-Any persona about to author an artifact can invoke it: Pepper before a brief, Maria Hill before a PRD, Tony before epics/stories/architecture, Wizer when a demand arrives fuzzy. Wizer also **suggests** it from `/wize-help` — always suggest, never force.
+Any persona about to author an artifact can invoke it: Pepper before a brief, Maria Hill before a PRD, Tony before epics/stories/architecture, Wizer when a demand arrives fuzzy. Wizer also **suggests** it from `/wize` (or `/wize-help`) — always suggest, never force.
 
 ## The five rules
 

package/src/core-skills/wize-index-docs/skill.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-index-docs
+description: "Use quando precisar reconstruir o índice da base de conhecimento (.wize/knowledge/index.md) a partir da árvore real de artefatos."
 name: Index Docs
 module: core
 status: ready
@@ -114,4 +116,4 @@ total_files: 24
 
 ## Hand-off
 
-> "Index rebuilt at `.wize/knowledge/index.md`. {N} files indexed across 5 sections. Next: `/wize-help` reads this file when answering."
+> "Index rebuilt at `.wize/knowledge/index.md`. {N} files indexed across 5 sections. Next: `/wize` (or `/wize-help`) reads this file when answering."

package/src/core-skills/wize-review-adversarial/skill.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-review-adversarial
+description: "Use quando um artefato (story, arquitetura, PRD) precisar de revisão adversarial — testar a ideia sob quatro personas hostis."
 name: Adversarial Review
 module: core
 status: stub

package/src/core-skills/wize-review-edge-case-hunter/skill.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-review-edge-case-hunter
+description: "Use quando um código ou PR precisar de caça sistemática de edge cases ranqueados por probabilidade × impacto."
 name: Edge Case Hunter
 module: core
 status: ready

package/src/core-skills/wize-shard-doc/skill.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-shard-doc
+description: "Use quando um documento markdown grande (PRD, arquitetura) precisar ser dividido em shards endereçáveis por ID."
 name: Shard Doc
 module: core
 status: stub

package/src/core-skills/wize-spec/skill.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-spec
+description: "Use quando precisar destilar qualquer entrada de intenção (ideia, PRD, RFC, transcrição) em um contrato canônico SPEC.md para consumo downstream."
 name: Spec
 module: core
 status: ready

package/src/method-skills/1-analysis/wize-agent-analyst/agent.yaml

@@ -23,6 +23,9 @@ absorbs:
 skills:
   - wize-product-brief
   - wize-research
+  - wize-market-research
+  - wize-domain-research
+  - wize-technical-research
   - wize-trigger-map
   - wize-prfaq
   - wize-document-project

package/src/method-skills/1-analysis/wize-document-project/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-document-project
+description: "Use quando o kit for instalado em um repositório existente (brownfield) e precisar documentar o estado atual do projeto."
 name: Document Project (brownfield baseline)
 phase: 1-analysis
 owner: wize-agent-analyst   # Pepper Potts (paired with Peggy Carter and Tony Stark)

package/src/method-skills/1-analysis/wize-domain-research/workflow.md

@@ -4,8 +4,15 @@ name: Domain Research
 phase: 1-analysis
 owner: wize-agent-analyst   # Pepper Potts
 status: ready
+description: "Use quando precisar pesquisar um domínio de negócio, indústria ou setor."
 ---
 
+> **Variante de pesquisa.** Para outros tipos de pesquisa, veja:
+> - Mercado/concorrência → `/wize-market-research`
+> - Domínio/indústria → `/wize-domain-research`
+> - Técnica/stack → `/wize-technical-research`
+> - Pesquisa geral (dispatcher) → `/wize-research`
+
 # Domain Research
 
 **Goal.** Conduct domain and industry research to ground the product in its business, regulatory, and technical context.

package/src/method-skills/1-analysis/wize-market-research/workflow.md

@@ -4,8 +4,15 @@ name: Market Research
 phase: 1-analysis
 owner: wize-agent-analyst   # Pepper Potts
 status: ready
+description: "Use quando precisar pesquisar mercado, concorrentes, tendências ou posicionamento."
 ---
 
+> **Variante de pesquisa.** Para outros tipos de pesquisa, veja:
+> - Mercado/concorrência → `/wize-market-research`
+> - Domínio/indústria → `/wize-domain-research`
+> - Técnica/stack → `/wize-technical-research`
+> - Pesquisa geral (dispatcher) → `/wize-research`
+
 # Market Research
 
 **Goal.** Conduct market research on competition and customers to inform the product brief and PRD.

package/src/method-skills/1-analysis/wize-prfaq/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-prfaq
+description: "Use quando precisar forçar alinhamento escrevendo o press release futuro e FAQ antes de construir — estilo Amazon Working Backwards."
 name: PR/FAQ
 phase: 1-analysis
 owner: wize-agent-analyst   # Pepper Potts

package/src/method-skills/1-analysis/wize-product-brief/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-product-brief
+description: "Use quando uma demanda bruta chegar e precisar ser convertida em um product brief de uma página."
 name: Product Brief
 phase: 1-analysis
 owner: wize-agent-analyst   # Pepper Potts

package/src/method-skills/1-analysis/wize-refresh-knowledge/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-refresh-knowledge
+description: "Use quando o document-project acumulou bullets datados durante o sprint e precisar ser consolidado em uma baseline atualizada."
 name: Refresh Project Knowledge
 phase: 1-analysis
 owner: wize-agent-analyst    # Pepper (drives), with Peggy on prose
@@ -16,7 +18,7 @@ Pepper drives the consolidation. Peggy edits prose. Tony reviews architecture-sn
 
 ## When to run
 
-- **End of sprint** (default cadence). `wize-help next` suggests it when it detects the sprint ended.
+- **End of sprint** (default cadence). `/wize next` (or `/wize-help next`) suggests it when it detects the sprint ended.
 - **After a major epic ships.** Architecture often shifts visibly; this is the moment to consolidate.
 - **Before onboarding a new engineer.** The baseline is the first thing they read; keep it fresh.
 - **Before an audit / external review.** Same.

package/src/method-skills/1-analysis/wize-research/workflow.md

@@ -4,113 +4,48 @@ name: Research
 phase: 1-analysis
 owner: wize-agent-analyst   # Pepper Potts
 status: ready
+description: "Use quando precisar pesquisar algo mas não souber qual tipo de pesquisa se aplica."
 ---
 
-# Research
+# Research (Dispatcher)
 
-**Goal.** Surface evidence that hardens the brief and trigger map. Frame the questions Pepper actually needs answered, do focused passes (market / competitors / analytics / interviews), and write the synthesis in a way Maria Hill can quote in the PRD.
+**Goal.** Classify the user's research question and delegate to the correct variant. This skill does NOT execute research directly — it routes to one of the specialized research skills.
 
-Pepper drives. Peggy edits prose. Output lands in `.wize/planning/research.md` with raw materials in `.wize/knowledge/research/`.
+## Classification guide
 
-## Inputs
+Analyze the user's question for these signals. Score each category by keyword hits; delegate to the highest-scoring category.
 
-- Open questions in `.wize/planning/brief.md`.
-- Hypotheses in `.wize/planning/ux/trigger-map.md`.
-- External access (browser, MCPs) and/or attached materials (decks, transcripts).
-
-## Outputs
-
-- `.wize/planning/research.md` — short synthesis (≤ 2 pages) referencing sources.
-- `.wize/knowledge/research/{slug}.md` — one file per major source (raw notes, links, attached PDFs).
+| Category | Keywords (pt-BR) | Keywords (EN) | Delegate to |
+|---|---|---|---|
+| **Market** | concorrência, concorrentes, mercado, competidor, pricing, preço, posicionamento, cliente, segmento, TAM, SAM, market share, G2, Capterra | competitor, market, pricing, positioning, customer, segment | `wize-market-research` |
+| **Domain** | domínio, indústria, setor, regulatório, regulação, compliance, legislação, lei, normativo, PESTLE, tendências do setor | domain, industry, sector, regulatory, compliance, legislation | `wize-domain-research` |
+| **Technical** | técnico, tecnologia, stack, biblioteca, framework, arquitetura, ferramenta, linguagem, banco de dados, API, protocolo, desempenho, escalabilidade | technical, technology, stack, library, framework, architecture, tool, language, database, API, protocol, performance, scalability | `wize-technical-research` |
 
 ## Steps
 
-### 1. Frame the questions
-
-Convert open questions + hypotheses into a numbered list. Each question is:
-- **Specific** — "What's the median onboarding time for the top 5 competitors?" not "How is onboarding usually done?".
-- **Answerable in a finite pass** — if it takes weeks, decompose.
-- **Tagged with category** — `market / competitive / analytics / interview / desk-research / regulatory`.
-
-### 2. Choose the framework that fits each question
-
-| Category | Recommended frame | Tools |
-|---|---|---|
-| Market sizing | TAM/SAM/SOM, top-down + bottom-up reconciled | Statista, public filings, gov registries |
-| Competitive | Porter's 5 + feature matrix + pricing scan | competitor sites, G2/Capterra, Pricing/Plans pages |
-| User research | Jobs-to-be-Done (Christensen / Klement) | 5–8 interviews (semi-structured, 30min) |
-| Behavioral | 5W2H + analytics funnel | product analytics (Amplitude/PostHog), session replays |
-| Compliance/legal | Reg list + clause map | gov sites, legal counsel review |
-| Macro context | PESTLE (political/economic/social/technological/legal/environmental) | desk research |
-
-### 3. Run focused passes
-
-One question, one pass. Don't bundle. For each:
-
-- Define what "enough evidence" looks like before starting.
-- Cite or it didn't happen. Links + access date.
-- When numbers conflict across sources, write down both and flag.
-
-### 4. Synthesize
-
-In `research.md`, for each original question, write:
-
-```markdown
-### Q1. {{the question}}
-**Finding:** one sentence answer.
-**Confidence:** high | medium | low
-**Why we believe it:** 2–3 lines + citations [1][2][3].
-**Implication for the brief/PRD:** what changes (or doesn't) because of this.
-```
-
-Don't include raw quotes here — link to `.wize/knowledge/research/{slug}.md`.
-
-### 5. Flag the gaps
-
-End the synthesis with a "Still open" section. List questions we couldn't answer + the cheapest next step (one interview / one analytics query / one expert call). Route back to Wizer with the gap.
-
-## Output template (synthesis)
-
-```markdown
----
-status: ready-for-prd
-owner: Pepper Potts
-created: YYYY-MM-DD
----
+### 1. Read the question
 
-# Research — {{project_name}}
+Extract the user's research topic or question. If the user provided a long message, identify the core research intent.
 
-## Q1. {{question}}
-**Finding:** …
-**Confidence:** medium
-**Why:** … [1]
-**Implication:** Brief constraint #3 holds; PRD scope can drop feature X.
+### 2. Classify
 
-## Q2. …
+Match keywords against the classification guide above. Score each category by keyword hits. Pick the highest-scoring category.
 
-## Still open
-- Q5: pricing elasticity in segment S — needs 1 hour with sales lead.
+### 3. Delegate or ask
 
-## Sources
-[1] {{title}} — {{url}} (accessed YYYY-MM-DD)
-[2] interview-acme-cto-2026-05-30 — see knowledge/research/acme-cto.md
-```
+- **Clear match (one category dominates):** Delegate to the corresponding variant. Load that skill and hand off the user's question intact — do not rephrase or summarize.
+- **Ambiguous (multiple categories tie or no clear signal):** Ask one clarifying question:
 
-## When to use which framework (heuristic)
+> Isso é pesquisa de mercado, domínio ou técnica?
 
-- **JTBD** when you're about to write personas; JTBD is sharper than archetypes.
-- **Porter** when picking a market to enter or a defensible moat.
-- **PESTLE** for projects with regulatory or geopolitical exposure.
-- **5 Whys + analytics funnel** when a metric is bad and the cause isn't obvious.
+Wait for the user's answer, then delegate to the chosen variant.
 
-## Anti-patterns Pepper rejects
+## Anti-patterns
 
-- Synthesis without citations.
-- "We surveyed users" with no n, no method, no script.
-- Single-source claims with high confidence ("everyone is using X" because of one blog post).
-- Using brand-name competitor research as user research — they're different.
-- Continuing to research when the decision is already made. Stop and ship.
+- Executing research directly instead of delegating.
+- Asking more than one clarifying question.
+- Guessing when the signal is ambiguous — ask, don't assume.
 
 ## Hand-off
 
-> Research is in `.wize/planning/research.md`. Q3 still open — sales lead has a slot tomorrow. Hill can start the PRD on what's confirmed.
+> Pesquisa classificada como {{category}}. Delegando para {{variant}}.

package/src/method-skills/1-analysis/wize-technical-research/workflow.md

@@ -4,8 +4,15 @@ name: Technical Research
 phase: 1-analysis
 owner: wize-agent-analyst   # Pepper Potts
 status: ready
+description: "Use quando precisar pesquisar tecnologias, stacks, bibliotecas ou decisões técnicas."
 ---
 
+> **Variante de pesquisa.** Para outros tipos de pesquisa, veja:
+> - Mercado/concorrência → `/wize-market-research`
+> - Domínio/indústria → `/wize-domain-research`
+> - Técnica/stack → `/wize-technical-research`
+> - Pesquisa geral (dispatcher) → `/wize-research`
+
 # Technical Research
 
 **Goal.** Conduct technical research on technologies, tools, and architecture patterns to inform stack decisions.

package/src/method-skills/1-analysis/wize-trigger-map/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-trigger-map
+description: "Use quando precisar mapear gatilhos psicológicos dos usuários para objetivos de negócio — a ponte entre o brief e o PRD."
 name: Trigger Map
 phase: 1-analysis
 owner: wize-agent-analyst   # Pepper Potts

package/src/method-skills/2-plan-workflows/wize-create-prd/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-create-prd
+description: "Use quando o brief + research + trigger map estiverem prontos e precisar convertê-los em um PRD com escopo e acceptance criteria."
 name: Create PRD
 phase: 2-plan
 owner: wize-agent-pm   # Maria Hill
@@ -149,8 +151,7 @@ Maria Hill validates every story's ACs against INVEST:
 - **I**ndependent: no implicit dependency on another story being built first.
 - **N**egotiable: details can move; intent can't.
 - **V**aluable: a real outcome to a real user.
-- **E**stimable: Tony can size it.
-- **S**mall: ≤ 1 PR worth (sliced finer in Phase 3 if not).
+- **S**mall: ≤ 1 PR worth (sliced finer in Phase 3 if not) — the only sizing test. INVEST's "Estimable" is dropped on purpose: we don't produce time or point estimates.
 - **T**estable: every AC is observable.
 
 If any letter fails, fix the story before it leaves Plan.

package/src/method-skills/2-plan-workflows/wize-edit-prd/workflow.md

@@ -1,7 +1,9 @@
 ---
+
 code: wize-edit-prd
+description: "Use quando o PRD existir e precisar de alteração pontual com registro de changelog."
 name: Edit PRD
-phase: 2-plan-workflows
+phase: 2-plan
 owner: wize-agent-pm   # Maria Hill
 status: ready
 ---

package/src/method-skills/2-plan-workflows/wize-ux-design/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-ux-design
+description: "Use quando os cenários UX estiverem prontos e precisar produzir especificações página por página para arquitetura e implementação."
 name: UX Design
 phase: 2-plan
 owner: wize-agent-ux-designer   # Mantis

package/src/method-skills/2-plan-workflows/wize-ux-scenarios/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-ux-scenarios
+description: "Use quando o PRD estiver validado e precisar produzir o mapa de cenários UX que ancora todo o design."
 name: UX Scenarios
 phase: 2-plan
 owner: wize-agent-ux-designer   # Mantis (absorbs WDS Freya)

package/src/method-skills/2-plan-workflows/wize-validate-prd/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-validate-prd
+description: "Use quando o PRD estiver pronto para validação e precisar decidir se ele pode avançar para Solutioning."
 name: Validate PRD
 phase: 2-plan
 owner: wize-agent-pm   # Maria Hill (with Pepper, Mantis, Fury input)
@@ -45,7 +47,7 @@ After `wize-create-prd` produces `status: ready-for-validation`. Run once per ma
 ### Quality
 - [ ] Every AC is observable (testable by Hawkeye without ambiguity).
 - [ ] No AC contains the word "easy", "intuitive", "responsive" without a numeric criterion.
-- [ ] INVEST: every backbone story passes (independent, negotiable, valuable, estimable, small, testable).
+- [ ] INVEST: every backbone story passes (independent, negotiable, valuable, small, testable) — "Estimable" is dropped; we don't estimate, we only check it fits one PR.
 - [ ] No goal repeats a brief constraint as if it were a goal.
 
 ### Cross-checks

package/src/method-skills/3-solutioning/wize-check-implementation-readiness/workflow.md

@@ -1,5 +1,7 @@
 ---
+
 code: wize-check-implementation-readiness
+description: "Use quando a arquitetura e as stories estiverem prontas e precisar verificar se o projeto está pronto para entrar em implementação."
 name: Check Implementation Readiness
 phase: 3-solutioning
 owner: wize-agent-architect   # Tony Stark (with Hawkeye + Hill)