wize-dev-kit 0.11.0 → 0.12.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (92) hide show
  1. package/AGENTS.md +3 -3
  2. package/CHANGELOG.md +37 -0
  3. package/README.es.md +3 -1
  4. package/README.md +3 -1
  5. package/README.pt-BR.md +3 -1
  6. package/package.json +1 -1
  7. package/src/app-overlay/wize-app-release-channels/workflow.md +2 -0
  8. package/src/app-overlay/wize-app-scaffold/workflow.md +2 -0
  9. package/src/app-overlay/wize-app-store-listing/workflow.md +2 -0
  10. package/src/builder-skills/wize-create-agent/workflow.md +2 -0
  11. package/src/builder-skills/wize-create-skill/workflow.md +2 -0
  12. package/src/builder-skills/wize-create-workflow/workflow.md +2 -0
  13. package/src/core-skills/module.yaml +3 -0
  14. package/src/core-skills/wize-advanced-elicitation/skill.md +2 -0
  15. package/src/core-skills/wize-brainstorming/skill.md +2 -0
  16. package/src/core-skills/wize-customize/skill.md +2 -0
  17. package/src/core-skills/wize-editorial-review-prose/skill.md +2 -0
  18. package/src/core-skills/wize-editorial-review-structure/skill.md +2 -0
  19. package/src/core-skills/wize-grill/skill.md +3 -1
  20. package/src/core-skills/wize-index-docs/skill.md +3 -1
  21. package/src/core-skills/wize-pre-pr-check/skill.md +134 -0
  22. package/src/core-skills/wize-review-adversarial/skill.md +2 -0
  23. package/src/core-skills/wize-review-edge-case-hunter/skill.md +2 -0
  24. package/src/core-skills/wize-shard-doc/skill.md +2 -0
  25. package/src/core-skills/wize-spec/skill.md +2 -0
  26. package/src/method-skills/1-analysis/wize-agent-analyst/agent.yaml +3 -0
  27. package/src/method-skills/1-analysis/wize-document-project/workflow.md +2 -0
  28. package/src/method-skills/1-analysis/wize-domain-research/workflow.md +7 -0
  29. package/src/method-skills/1-analysis/wize-market-research/workflow.md +7 -0
  30. package/src/method-skills/1-analysis/wize-prfaq/workflow.md +2 -0
  31. package/src/method-skills/1-analysis/wize-product-brief/workflow.md +2 -0
  32. package/src/method-skills/1-analysis/wize-refresh-knowledge/workflow.md +3 -1
  33. package/src/method-skills/1-analysis/wize-research/workflow.md +24 -89
  34. package/src/method-skills/1-analysis/wize-technical-research/workflow.md +7 -0
  35. package/src/method-skills/1-analysis/wize-trigger-map/workflow.md +2 -0
  36. package/src/method-skills/2-plan-workflows/wize-create-prd/workflow.md +2 -0
  37. package/src/method-skills/2-plan-workflows/wize-edit-prd/workflow.md +3 -1
  38. package/src/method-skills/2-plan-workflows/wize-ux-design/workflow.md +2 -0
  39. package/src/method-skills/2-plan-workflows/wize-ux-scenarios/workflow.md +2 -0
  40. package/src/method-skills/2-plan-workflows/wize-validate-prd/workflow.md +2 -0
  41. package/src/method-skills/3-solutioning/wize-check-implementation-readiness/workflow.md +2 -0
  42. package/src/method-skills/3-solutioning/wize-create-architecture/steps/step-08-complete.md +1 -1
  43. package/src/method-skills/3-solutioning/wize-create-architecture/workflow.md +2 -0
  44. package/src/method-skills/3-solutioning/wize-create-epics-and-stories/workflow.md +2 -0
  45. package/src/method-skills/3-solutioning/wize-design-system/workflow.md +2 -0
  46. package/src/method-skills/3-solutioning/wize-nfr-principles/workflow.md +3 -1
  47. package/src/method-skills/3-solutioning/wize-project-context/workflow.md +3 -1
  48. package/src/method-skills/3-solutioning/wize-tech-vision/workflow.md +3 -1
  49. package/src/method-skills/4-implementation/wize-changelog/workflow.md +184 -0
  50. package/src/method-skills/4-implementation/wize-checkpoint-preview/workflow.md +2 -0
  51. package/src/method-skills/4-implementation/wize-code-review/workflow.md +2 -0
  52. package/src/method-skills/4-implementation/wize-correct-course/workflow.md +2 -0
  53. package/src/method-skills/4-implementation/wize-create-story/workflow.md +2 -0
  54. package/src/method-skills/4-implementation/wize-dev-story/workflow.md +3 -1
  55. package/src/method-skills/4-implementation/wize-investigate/workflow.md +2 -0
  56. package/src/method-skills/4-implementation/wize-quick-dev/workflow.md +2 -0
  57. package/src/method-skills/4-implementation/wize-release/workflow.md +162 -0
  58. package/src/method-skills/4-implementation/wize-retrospective/workflow.md +2 -0
  59. package/src/method-skills/4-implementation/wize-sprint-planning/workflow.md +2 -0
  60. package/src/method-skills/4-implementation/wize-sprint-status/workflow.md +2 -0
  61. package/src/method-skills/module.yaml +12 -3
  62. package/src/orchestrator-skills/module.yaml +4 -1
  63. package/src/orchestrator-skills/wize/skill.md +164 -0
  64. package/src/orchestrator-skills/wize-help/skill.md +126 -5
  65. package/src/orchestrator-skills/wize-onboarding/workflow.md +3 -1
  66. package/src/orchestrator-skills/wize-orchestrator/agent.yaml +1 -0
  67. package/src/orchestrator-skills/wize-orchestrator/persona.md +29 -4
  68. package/src/orchestrator-skills/wize-party-mode/workflow.md +2 -0
  69. package/src/security-overlay/_shared/scope-parser.js +27 -0
  70. package/src/security-overlay/agents/red-teamer/agent.yaml +2 -0
  71. package/src/security-overlay/agents/red-teamer/persona.md +6 -0
  72. package/src/security-overlay/skills/wize-sec-enumerate/skill.md +2 -0
  73. package/src/security-overlay/skills/wize-sec-pentest/scripts/run-pipeline.js +18 -1
  74. package/src/security-overlay/skills/wize-sec-pentest/skill.md +2 -0
  75. package/src/security-overlay/skills/wize-sec-recon/skill.md +2 -0
  76. package/src/security-overlay/skills/wize-sec-scope/scripts/generate-scope.js +106 -0
  77. package/src/security-overlay/skills/wize-sec-scope/skill.md +52 -0
  78. package/src/tea-skills/wize-qa-generate-e2e-tests/workflow.md +2 -0
  79. package/src/tea-skills/wize-tea-design/workflow.md +3 -0
  80. package/src/tea-skills/wize-tea-gate/workflow.md +3 -0
  81. package/src/tea-skills/wize-tea-nfr/workflow.md +3 -0
  82. package/src/tea-skills/wize-tea-review/workflow.md +3 -0
  83. package/src/tea-skills/wize-tea-risk/workflow.md +3 -0
  84. package/src/tea-skills/wize-tea-trace/workflow.md +3 -0
  85. package/src/web-overlay/wize-web-deploy/workflow.md +2 -0
  86. package/src/web-overlay/wize-web-scaffold/workflow.md +2 -0
  87. package/src/web-overlay/wize-web-seo-audit/workflow.md +2 -0
  88. package/tools/installer/commands/doctor.js +2 -2
  89. package/tools/installer/onboarding.js +14 -21
  90. package/tools/installer/render-shared.js +50 -28
  91. package/tools/installer/validators/run-all.js +3 -2
  92. package/tools/installer/wize-cli.js +323 -77
package/AGENTS.md CHANGED
@@ -10,8 +10,8 @@ Treat `.wize/`, this `AGENTS.md`, and the installed `wize-*` skills as your oper
10
10
  instructions and persistent memory — not background reading. Read project state before
11
11
  acting; write what you change back into `.wize/` so the next session inherits it.
12
12
 
13
- Before editing, classify the demand via `/wize-help`: **Quick Dev** (small, predictable,
14
- ~≤1h, no new feature / architecture / UX / security) or **Full Lifecycle**. Never pick
13
+ Before editing, classify the demand via `/wize` (or `/wize-help`): **Quick Dev** (small, predictable,
14
+ trivially scoped, no new feature / architecture / UX / security) or **Full Lifecycle**. Never pick
15
15
  Quick Dev just to skip artifacts.
16
16
 
17
17
  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.
34
34
 
35
35
  ## Where to start
36
36
 
37
- Activate the orchestrator: `wize-orchestrator` (Wizer). Then ask `/wize-help`.
37
+ Activate the orchestrator: `/wize` (or `/wize-help`). Wizer will guide you.
package/CHANGELOG.md CHANGED
@@ -9,6 +9,43 @@ Format inspired by [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
9
9
 
10
10
  ## [Unreleased]
11
11
 
12
+ ## [0.12.1] — 2026-08-08
13
+
14
+ **Pre-PR Check — gate local antes de abrir PR.** Nova skill core para rodar lint, format, build e testes unitários localmente antes de submeter código, evitando ciclagem cara de CI no Actions. Agnóstica de tecnologia (detecta stack via `package.json`, `composer.json`, `Cargo.toml`, etc.). Registrada em todos os 9 harness adapters.
15
+
16
+ ### Added
17
+
18
+ - **`wize-pre-pr-check`** (core skill) — gate local que detecta a stack do projeto e roda checks rápidos (lint, format, type-check, build, unit tests) antes de `git push` ou abertura de PR. Pare no primeiro erro. Complementa o CI; não substitui testes de integração/E2E. Description: *"Quando for abrir um Pull Request ou PR leia."*
19
+
20
+ ## [0.12.0] — 2026-08-08
21
+
22
+ **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).
23
+
24
+ ### Added
25
+
26
+ - **`/wize` alias** — primary entry point; `/wize-help` remains canonical. Onboarding reduced to `→ /wize`.
27
+ - **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.
28
+ - **Intent descriptions** — all 68 skills/workflows carry a one-sentence `description:` telling the harness WHEN to invoke them. Block-scalar parser (`|`, `>`) now supported.
29
+ - **`wize-sec-scope`** — guided scope creation for the security overlay (4 questions → `scope.md` + signed hash).
30
+ - **`--sign-scope`** flag on `wize-sec-pentest` — recomputes SHA-256 without manual editing.
31
+ - **Non-interactive install** — `install --profiles core,security --targets claude-code --yes` for CI/scripted installs. `--dry-run` supported.
32
+ - **Honest uninstall** — removes rendered adapter directories (`.claude/skills/`, `.cursor/rules/`, etc.) in addition to `.wize/`. `--dry-run` supported.
33
+ - **`wize-release`** skill — version bump + changelog + git tag from gated stories.
34
+ - **`wize-changelog`** skill — Keep a Changelog format generated from done stories.
35
+ - **CI workflow** — `.github/workflows/ci.yml` runs `npm test` + `npm run validate` on push/PR against Node 20.x and 22.x.
36
+ - **Tool contract tests** — smoke tests for nmap, gitleaks, osv-scanner, grype, nuclei, nikto, sqlmap, ffuf (skip if absent, catch CLI drift).
37
+
38
+ ### Changed
39
+
40
+ - **`wize-research`** — now a dispatcher that classifies intent and delegates to `wize-market-research`, `wize-domain-research`, or `wize-technical-research`.
41
+ - **Phase labels** — normalized across all workflows (`2-plan-workflows` → `2-plan`, `2-to-3-boundary` → `3-solutioning`).
42
+ - **Onboarding** — contextual one-liner (`→ /wize`) instead of multi-line menu. Detects brownfield/security-overlay.
43
+ - **AGENTS.md template** — references `/wize` as primary, `/wize-help` as canonical.
44
+
45
+ ### Fixed
46
+
47
+ - **Block scalar parser** — `readFrontmatter` now handles `|`, `>`, `|-`, `|+`, `|2` and chomp indicators. Fixes the `— |` bug that corrupted all 10 persona descriptions.
48
+
12
49
  ## [0.11.0] — 2026-08-06
13
50
 
14
51
  **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).
package/README.es.md CHANGED
@@ -155,6 +155,8 @@ Transversales:
155
155
  /wize-grill Entrevista-hasta-entendimiento antes de cualquier
156
156
  paso de autoría.
157
157
  /wize-quick-dev Shuri toma un arreglo pequeño sin el ciclo completo.
158
+ /wize-pre-pr-check Corre lint/format/build/tests unitarios localmente
159
+ antes de abrir un PR — falla rápido, cero costo de runner.
158
160
  /wize-correct-course Re-planifica cuando un gate falla o el loop se
159
161
  estanca (auto-disparado por la guarda de max-cycles;
160
162
  también manual).
@@ -250,7 +252,7 @@ npx wize-dev-kit version # imprime la versión instalada del kit
250
252
 
251
253
  ## Estado
252
254
 
253
- **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.
255
+ **v0.12.1 — 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`), **`wize-grill`** (entrevista-hasta-entendimiento antes de cualquier paso de autoría), **`wize-pre-pr-check`** (gate local de lint/format/build/tests unitarios antes de abrir un PR — cero costo de runner de CI) 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.
254
256
 
255
257
  ---
256
258
 
package/README.md CHANGED
@@ -152,6 +152,8 @@ Cross-cutting:
152
152
  mission contract for the executing persona).
153
153
  /wize-grill Interview-to-understanding before any authoring step.
154
154
  /wize-quick-dev Shuri takes a small fix without the full ride.
155
+ /wize-pre-pr-check Run lint/format/build/unit tests locally before
156
+ opening a PR — fail fast, zero CI runner cost.
155
157
  /wize-correct-course Re-plan when a gate fails or a loop stalls (auto-
156
158
  triggered by the max-cycles guard; also manual).
157
159
  /wize-code-review Adversarial peer review before Hawkeye's TEA gate.
@@ -245,7 +247,7 @@ npx wize-dev-kit version # print the installed kit version
245
247
 
246
248
  ## Status
247
249
 
248
- **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.
250
+ **v0.12.1 — 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`), **`wize-grill`** (interview-to-shared-understanding before any authoring step), **`wize-pre-pr-check`** (local lint/format/build/unit-test gate before opening a PR — zero CI runner cost), 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.
249
251
 
250
252
  ---
251
253
 
package/README.pt-BR.md CHANGED
@@ -154,6 +154,8 @@ Transversais:
154
154
  /wize-grill Entrevista-até-entendimento antes de qualquer passo
155
155
  de autoria.
156
156
  /wize-quick-dev Shuri pega uma correção pequena sem o ciclo completo.
157
+ /wize-pre-pr-check Roda lint/format/build/testes unitários localmente
158
+ antes de abrir um PR — falha cedo, zero custo de runner.
157
159
  /wize-correct-course Re-planeja quando um gate falha ou o loop trava
158
160
  (auto-disparado pela guarda de max-cycles; também
159
161
  manual).
@@ -248,7 +250,7 @@ npx wize-dev-kit version # imprime a versão instalada do kit
248
250
 
249
251
  ## Status
250
252
 
251
- **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.
253
+ **v0.12.1 — 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`), **`wize-grill`** (entrevista-até-entendimento antes de qualquer passo de autoria), **`wize-pre-pr-check`** (gate local de lint/format/build/testes unitários antes de abrir um PR — zero custo de runner de CI) 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.
252
254
 
253
255
  ---
254
256
 
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "$schema": "https://json.schemastore.org/package.json",
3
3
  "name": "wize-dev-kit",
4
- "version": "0.11.0",
4
+ "version": "0.12.1",
5
5
  "description": "Full-lifecycle AI-assisted development kit with Test Architect and Whiteport Design Studio embedded. Inspired by BMAD Method and WDS.",
6
6
  "keywords": [
7
7
  "ai",
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-app-release-channels
4
+ description: "Use quando o app estiver pronto para distribuição e precisar configurar canais de release (beta, produção)."
3
5
  name: App Release Channels
4
6
  overlay: app
5
7
  owner: wize-agent-pm # Maria Hill
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-app-scaffold
4
+ description: "Use quando precisar criar o scaffold inicial de um projeto mobile com a stack aprovada pelo Fury."
3
5
  name: App Scaffold
4
6
  overlay: app
5
7
  owner: wize-agent-architect # Tony
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-app-store-listing
4
+ description: "Use quando o app estiver próximo do lançamento e precisar preparar a listagem na loja (copy, assets, metadados)."
3
5
  name: App Store Listing
4
6
  overlay: app
5
7
  owner: wize-agent-analyst # Pepper (copy) + Mantis (visual brief)
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-create-agent
4
+ description: "Use quando precisar criar um novo agente customizado sob .wize/custom/agents/."
3
5
  name: Create Agent
4
6
  owner: builder
5
7
  status: stub
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-create-skill
4
+ description: "Use quando precisar criar uma nova skill single-step sob .wize/custom/skills/."
3
5
  name: Create Skill
4
6
  owner: builder
5
7
  status: stub
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-create-workflow
4
+ description: "Use quando precisar criar um novo workflow multi-step sob .wize/custom/workflows/."
3
5
  name: Create Workflow
4
6
  owner: builder
5
7
  status: stub
@@ -28,4 +28,7 @@ skills:
28
28
  - code: wize-spec
29
29
  name: "Spec"
30
30
  description: "Distills any intent input into a canonical five-field spec kernel + companions."
31
+ - code: wize-pre-pr-check
32
+ name: "Pre-PR Check"
33
+ description: "Quando for abrir um Pull Request ou PR leia — gate local para lint, format, build e testes rápidos antes de submeter código."
31
34
 
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-advanced-elicitation
4
+ description: "Use quando uma resposta do usuário parecer subespecificada e precisar de técnicas de elicitação (5 Whys, laddering, premortem) para aprofundar o entendimento."
3
5
  name: Advanced Elicitation
4
6
  module: core
5
7
  status: stub
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-brainstorming
4
+ description: "Use quando precisar gerar ideias divergentes e convergir para as melhores opções em qualquer fase de decisão."
3
5
  name: Brainstorming
4
6
  module: core
5
7
  status: stub
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-customize
4
+ description: "Use quando precisar personalizar um agente, skill ou workflow built-in sem alterar os arquivos originais do kit."
3
5
  name: Customize
4
6
  module: core
5
7
  status: ready
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-editorial-review-prose
4
+ description: "Use quando um artefato Wize (brief, PRD, ADR, gate) precisar de revisão de prosa — clareza, tom, jargão e precisão."
3
5
  name: Editorial Review — Prose
4
6
  module: core
5
7
  status: ready
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-editorial-review-structure
4
+ description: "Use quando um artefato Wize precisar de revisão estrutural — seções obrigatórias, ordenação e níveis de heading."
3
5
  name: Editorial Review — Structure
4
6
  module: core
5
7
  status: ready
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-grill
4
+ description: "Use quando uma demanda chegar vaga e precisar de entrevista exaustiva para alcançar entendimento compartilhado antes de produzir qualquer artefato."
3
5
  name: Grill
4
6
  module: core
5
7
  status: ready
@@ -9,7 +11,7 @@ status: ready
9
11
 
10
12
  **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.
11
13
 
12
- 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.
14
+ 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.
13
15
 
14
16
  ## The five rules
15
17
 
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-index-docs
4
+ description: "Use quando precisar reconstruir o índice da base de conhecimento (.wize/knowledge/index.md) a partir da árvore real de artefatos."
3
5
  name: Index Docs
4
6
  module: core
5
7
  status: ready
@@ -114,4 +116,4 @@ total_files: 24
114
116
 
115
117
  ## Hand-off
116
118
 
117
- > "Index rebuilt at `.wize/knowledge/index.md`. {N} files indexed across 5 sections. Next: `/wize-help` reads this file when answering."
119
+ > "Index rebuilt at `.wize/knowledge/index.md`. {N} files indexed across 5 sections. Next: `/wize` (or `/wize-help`) reads this file when answering."
@@ -0,0 +1,134 @@
1
+ ---
2
+ code: wize-pre-pr-check
3
+ name: wize-pre-pr-check
4
+ module: core
5
+ description: "Quando for abrir um Pull Request ou PR leia"
6
+ ---
7
+
8
+ # Pre-PR Check
9
+
10
+ **Goal.** Rodar os checks obrigatórios localmente antes de abrir um PR, falhando cedo e rápido. Evita ciclagem cara de CI no Actions — principalmente lint, format, build e testes rápidos. O objetivo é ser um portão (gate) antes de submeter código.
11
+
12
+ **Agnóstica de tecnologia.** Não prescreve ferramentas específicas; lê os comandos disponíveis no repositório e executa o que for aplicável.
13
+
14
+ ## When to run
15
+
16
+ - Imediatamente antes de `git push` para uma branch de PR.
17
+ - Antes de abrir o PR no GitHub/GitLab.
18
+ - Após `git commit` na branch de feature, como sanity check.
19
+ - A qualquer momento durante o desenvolvimento — fail fast.
20
+
21
+ ## When NOT to run
22
+
23
+ - Quando o CI já está verde e o PR está em revisão (o gate já passou).
24
+ - Quando o repositório não tem scripts/ferramentas de lint/test configurados.
25
+
26
+ ## Operating contract
27
+
28
+ - **Leia o projeto antes de rodar.** Procura por `package.json`, `composer.json`, `Makefile`, `justfile`, `pyproject.toml`, `Cargo.toml`, etc. para descobrir os comandos de check existentes.
29
+ - **Só execute o que existir.** Se não houver `eslint`, pule o passo de lint. Se não houver `phpstan`, pule o passo de análise estática. Nunca exija uma ferramenta que não esteja configurada no repo.
30
+ - **Pare no primeiro erro.** A menos que o usuário peça `--continue`, um check que falha interrompe a cadeia — corrija antes de continuar.
31
+ - **Não seja um substituto completo do CI.** O CI continua sendo a fonte da verdade para testes de integração, e2e, banco de dados, Docker, etc. Este gate é para checks rápidos e baratos.
32
+ - **Custo zero no Actions.** Tudo roda localmente.
33
+
34
+ ## Inputs
35
+
36
+ - Estado atual do working tree (staged + unstaged).
37
+ - Arquivos de config do projeto para descobrir comandos.
38
+
39
+ ## Outputs
40
+
41
+ - Relatório compacto de quais checks passaram/falharam.
42
+ - Se falhou: mensagem de erro + arquivo(s) sugerido(s) para corrigir.
43
+ - Se passou: confirmação pronta para PR.
44
+
45
+ ## Steps
46
+
47
+ ### 1. Detectar stack
48
+
49
+ Procurar nos arquivos de config do projeto quais ferramentas estão disponíveis:
50
+
51
+ | Fonte | O que extrair |
52
+ |-------|---------------|
53
+ | `package.json` → `scripts` | `lint`, `format`, `format:check`, `type-check`, `build`, `test`, `test:unit` |
54
+ | `composer.json` → `scripts` | `test`, `phpstan`, `pint`, `phpcs` |
55
+ | `Makefile` / `justfile` | targets `lint`, `format`, `check`, `test` |
56
+ | `pyproject.toml` / `setup.cfg` | `flake8`, `black`, `mypy`, `pytest` |
57
+ | `Cargo.toml` | `cargo check`, `cargo test`, `cargo clippy`, `cargo fmt` |
58
+ | `.github/workflows/*.yml` | steps de `lint`, `format`, `build`, `test` (como referência, não para rodar) |
59
+
60
+ Heurística de prioridade: scripts do gerenciador de pacote local (`npm run`, `composer run`) > binários diretos (`vendor/bin/pint`) > comandos genéricos (`cargo clippy`).
61
+
62
+ ### 2. Selecionar checks por velocidade
63
+
64
+ Separar em **rápido** (executa em segundos) e **lento** (minutos):
65
+
66
+ **Rápido (executar sempre):**
67
+ - Lint (ESLint, PHPStan, Clippy, Ruff, etc.)
68
+ - Format check (Prettier, Pint, Black, rustfmt)
69
+ - Type check (tsc, mypy)
70
+ - Análise estática (PHPStan, Psalm)
71
+
72
+ **Lento (executar quando houver mudanças relevantes):**
73
+ - Build (Vite, Webpack, Cargo build)
74
+ - Testes unitários (Vitest, Jest, Pest, pytest, `cargo test`)
75
+ - Guard-rails custom (scripts próprios do projeto, ex: `check:orphans`)
76
+
77
+ **Muito lento (opcional / em dia de merge):**
78
+ - Testes de integração
79
+ - E2E (Playwright, Cypress)
80
+ - Build de Docker
81
+
82
+ ### 3. Rodar o gate
83
+
84
+ Na ordem: format → lint → type-check → build → testes unitários → guard-rails.
85
+
86
+ Comandos típicos por stack (detectados em tempo real, não hardcoded):
87
+
88
+ | Stack | Comandos comuns |
89
+ |-------|-----------------|
90
+ | Node/JS/TS | `npm run format:check`, `npm run lint`, `npm run check:type` (ou `tsc --noEmit`), `npm run build`, `npm run test` |
91
+ | PHP/Laravel | `vendor/bin/pint --test`, `vendor/bin/phpstan analyse`, `php artisan test` |
92
+ | Python | `black --check`, `ruff check`, `mypy`, `pytest` |
93
+ | Rust | `cargo fmt -- --check`, `cargo clippy`, `cargo check`, `cargo test` |
94
+ | Go | `gofmt -l`, `golangci-lint run`, `go test ./...` |
95
+
96
+ Se um check falhar, pare e reporte. Não prossiga para o próximo.
97
+
98
+ ### 4. Reportar
99
+
100
+ Formato compacto, uma linha por check:
101
+
102
+ ```
103
+ ✓ format:check (npm run format:check) — 0.8s
104
+ ✓ lint (vendor/bin/pint --test) — 2.1s
105
+ ✗ phpstan (vendor/bin/phpstan) — 4.5s → FAIL
106
+ app/Http/Controllers/LegalController.php:11 — FQCN não importado
107
+ → Corrija antes de abrir o PR.
108
+ ```
109
+
110
+ Se tudo passar:
111
+
112
+ ```
113
+ ✓ format:check — PASS (0.8s)
114
+ ✓ lint — PASS (2.1s)
115
+ ✓ phpstan — PASS (4.5s)
116
+ ✓ build — PASS (32s)
117
+ ✓ test:unit — PASS (30s)
118
+ ─────────────────────────────
119
+ Gate limpo. Pode abrir o PR.
120
+ ```
121
+
122
+ ## Anti-patterns
123
+
124
+ - **Rodar checks que não existem no repo.** Se não há `composer.json`, não tente `vendor/bin/pint`.
125
+ - **Ignorar falhas de lint.** Lint fail = PR fail. Corrija antes.
126
+ - **Executar E2E localmente toda vez.** E2E é caro; deixe para o CI ou rode antes de merge.
127
+ - **Substituir o CI.** Este gate é complementar, não substituto.
128
+
129
+ ## Hand-off
130
+
131
+ > Gate `wize-pre-pr-check` concluído. `{passados}/{total}` checks passaram. `{tempo_total}s`. Pronto para PR.
132
+
133
+ Se houve falha:
134
+ > Gate `wize-pre-pr-check` interrompido em `{check_falho}`. Corrija e re-execute antes de abrir o PR.
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-review-adversarial
4
+ description: "Use quando um artefato (story, arquitetura, PRD) precisar de revisão adversarial — testar a ideia sob quatro personas hostis."
3
5
  name: Adversarial Review
4
6
  module: core
5
7
  status: stub
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-review-edge-case-hunter
4
+ description: "Use quando um código ou PR precisar de caça sistemática de edge cases ranqueados por probabilidade × impacto."
3
5
  name: Edge Case Hunter
4
6
  module: core
5
7
  status: ready
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-shard-doc
4
+ description: "Use quando um documento markdown grande (PRD, arquitetura) precisar ser dividido em shards endereçáveis por ID."
3
5
  name: Shard Doc
4
6
  module: core
5
7
  status: stub
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-spec
4
+ description: "Use quando precisar destilar qualquer entrada de intenção (ideia, PRD, RFC, transcrição) em um contrato canônico SPEC.md para consumo downstream."
3
5
  name: Spec
4
6
  module: core
5
7
  status: ready
@@ -23,6 +23,9 @@ absorbs:
23
23
  skills:
24
24
  - wize-product-brief
25
25
  - wize-research
26
+ - wize-market-research
27
+ - wize-domain-research
28
+ - wize-technical-research
26
29
  - wize-trigger-map
27
30
  - wize-prfaq
28
31
  - wize-document-project
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-document-project
4
+ description: "Use quando o kit for instalado em um repositório existente (brownfield) e precisar documentar o estado atual do projeto."
3
5
  name: Document Project (brownfield baseline)
4
6
  phase: 1-analysis
5
7
  owner: wize-agent-analyst # Pepper Potts (paired with Peggy Carter and Tony Stark)
@@ -4,8 +4,15 @@ name: Domain Research
4
4
  phase: 1-analysis
5
5
  owner: wize-agent-analyst # Pepper Potts
6
6
  status: ready
7
+ description: "Use quando precisar pesquisar um domínio de negócio, indústria ou setor."
7
8
  ---
8
9
 
10
+ > **Variante de pesquisa.** Para outros tipos de pesquisa, veja:
11
+ > - Mercado/concorrência → `/wize-market-research`
12
+ > - Domínio/indústria → `/wize-domain-research`
13
+ > - Técnica/stack → `/wize-technical-research`
14
+ > - Pesquisa geral (dispatcher) → `/wize-research`
15
+
9
16
  # Domain Research
10
17
 
11
18
  **Goal.** Conduct domain and industry research to ground the product in its business, regulatory, and technical context.
@@ -4,8 +4,15 @@ name: Market Research
4
4
  phase: 1-analysis
5
5
  owner: wize-agent-analyst # Pepper Potts
6
6
  status: ready
7
+ description: "Use quando precisar pesquisar mercado, concorrentes, tendências ou posicionamento."
7
8
  ---
8
9
 
10
+ > **Variante de pesquisa.** Para outros tipos de pesquisa, veja:
11
+ > - Mercado/concorrência → `/wize-market-research`
12
+ > - Domínio/indústria → `/wize-domain-research`
13
+ > - Técnica/stack → `/wize-technical-research`
14
+ > - Pesquisa geral (dispatcher) → `/wize-research`
15
+
9
16
  # Market Research
10
17
 
11
18
  **Goal.** Conduct market research on competition and customers to inform the product brief and PRD.
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-prfaq
4
+ description: "Use quando precisar forçar alinhamento escrevendo o press release futuro e FAQ antes de construir — estilo Amazon Working Backwards."
3
5
  name: PR/FAQ
4
6
  phase: 1-analysis
5
7
  owner: wize-agent-analyst # Pepper Potts
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-product-brief
4
+ description: "Use quando uma demanda bruta chegar e precisar ser convertida em um product brief de uma página."
3
5
  name: Product Brief
4
6
  phase: 1-analysis
5
7
  owner: wize-agent-analyst # Pepper Potts
@@ -1,5 +1,7 @@
1
1
  ---
2
+
2
3
  code: wize-refresh-knowledge
4
+ description: "Use quando o document-project acumulou bullets datados durante o sprint e precisar ser consolidado em uma baseline atualizada."
3
5
  name: Refresh Project Knowledge
4
6
  phase: 1-analysis
5
7
  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
16
18
 
17
19
  ## When to run
18
20
 
19
- - **End of sprint** (default cadence). `wize-help next` suggests it when it detects the sprint ended.
21
+ - **End of sprint** (default cadence). `/wize next` (or `/wize-help next`) suggests it when it detects the sprint ended.
20
22
  - **After a major epic ships.** Architecture often shifts visibly; this is the moment to consolidate.
21
23
  - **Before onboarding a new engineer.** The baseline is the first thing they read; keep it fresh.
22
24
  - **Before an audit / external review.** Same.