adi_dev_workflow 1.1.1 → 1.3.0

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 (98) hide show
  1. package/bin/index.js +8 -8
  2. package/frameworks/agents/qa-staff-engineer.md +311 -311
  3. package/frameworks/agents/qa-validation-expert.md +458 -458
  4. package/frameworks/agents/tech-review-conformance.md +200 -200
  5. package/frameworks/commands/ministack/README.md +2 -0
  6. package/frameworks/commands/ministack/code-review.md +2 -0
  7. package/frameworks/commands/ministack/generate-intent.md +2 -0
  8. package/frameworks/commands/ministack/generate-scope.md +2 -0
  9. package/frameworks/commands/ministack/generate-tasks.md +2 -0
  10. package/frameworks/commands/ministack/generate-tech-direction.md +2 -0
  11. package/frameworks/commands/ministack/run-ministack-tasks.md +3 -0
  12. package/frameworks/commands/ministack/run-ministack-withlinear.md +2 -0
  13. package/frameworks/commands/ministack/status.md +2 -0
  14. package/frameworks/commands/sdd/code-review.md +2 -0
  15. package/frameworks/commands/sdd/generate-prd.md +2 -0
  16. package/frameworks/commands/sdd/generate-task-plan.md +2 -0
  17. package/frameworks/commands/sdd/generate-tech-direction.md +2 -0
  18. package/frameworks/commands/sdd/generate-tech-spec.md +2 -0
  19. package/frameworks/commands/sdd/generate-tests.md +2 -0
  20. package/frameworks/commands/sdd/run_tasks.md +3 -0
  21. package/frameworks/commands/sdd/run_tasks_withlinear.md +2 -0
  22. package/frameworks/commands/sdd/status.md +2 -0
  23. package/frameworks/commands/sdd/validate-sdd.md +2 -0
  24. package/frameworks/commands/sync-tasks-to-linear.md +2 -0
  25. package/frameworks/commands/taskcard/generate-taskcard.md +2 -0
  26. package/frameworks/commands/taskcard/run-taskcard.md +2 -0
  27. package/frameworks/config/ai-framework-config.yaml +112 -0
  28. package/frameworks/skills/ministack-tasks-expert/SKILL.md +204 -204
  29. package/frameworks/skills/ministack-tasks-expert/templates/task_plan_template.md +78 -78
  30. package/frameworks/skills/ministack-tasks-expert/templates/task_template.md +103 -103
  31. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/benchmark.json +99 -99
  32. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/benchmark.md +64 -64
  33. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-1-happy-path/eval_metadata.json +12 -12
  34. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-1-happy-path/with_skill/grading.json +32 -32
  35. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-1-happy-path/with_skill/outputs/response.md +134 -134
  36. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-1-happy-path/with_skill/outputs/transcript.md +68 -68
  37. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-1-happy-path/with_skill/timing.json +5 -5
  38. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-1-happy-path/without_skill/grading.json +32 -32
  39. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-1-happy-path/without_skill/outputs/response.md +525 -525
  40. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-1-happy-path/without_skill/outputs/transcript.md +30 -30
  41. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-1-happy-path/without_skill/timing.json +5 -5
  42. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-2-spec-simples/eval_metadata.json +12 -12
  43. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-2-spec-simples/with_skill/grading.json +32 -32
  44. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-2-spec-simples/with_skill/outputs/response.md +1126 -1126
  45. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-2-spec-simples/with_skill/outputs/transcript.md +131 -131
  46. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-2-spec-simples/with_skill/timing.json +5 -5
  47. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-2-spec-simples/without_skill/grading.json +32 -32
  48. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-2-spec-simples/without_skill/outputs/response.md +452 -452
  49. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-2-spec-simples/without_skill/outputs/transcript.md +78 -78
  50. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-2-spec-simples/without_skill/timing.json +5 -5
  51. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-3-sem-user-stories/eval_metadata.json +12 -12
  52. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-3-sem-user-stories/with_skill/grading.json +32 -32
  53. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-3-sem-user-stories/with_skill/outputs/response.md +101 -101
  54. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-3-sem-user-stories/with_skill/outputs/transcript.md +133 -133
  55. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-3-sem-user-stories/with_skill/timing.json +5 -5
  56. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-3-sem-user-stories/without_skill/grading.json +32 -32
  57. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-3-sem-user-stories/without_skill/outputs/response.md +248 -248
  58. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-3-sem-user-stories/without_skill/outputs/transcript.md +49 -49
  59. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/eval-3-sem-user-stories/without_skill/timing.json +5 -5
  60. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-1/review.html +1325 -1325
  61. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/benchmark.json +94 -94
  62. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/benchmark.md +67 -67
  63. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-1-happy-path/eval_metadata.json +12 -12
  64. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-1-happy-path/with_skill/grading.json +32 -32
  65. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-1-happy-path/with_skill/outputs/response.md +117 -117
  66. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-1-happy-path/with_skill/outputs/transcript.md +91 -91
  67. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-1-happy-path/with_skill/timing.json +1 -1
  68. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-1-happy-path/without_skill/grading.json +32 -32
  69. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-1-happy-path/without_skill/outputs/response.md +694 -694
  70. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-1-happy-path/without_skill/outputs/transcript.md +45 -45
  71. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-1-happy-path/without_skill/timing.json +1 -1
  72. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-2-spec-simples/eval_metadata.json +12 -12
  73. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-2-spec-simples/with_skill/grading.json +32 -32
  74. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-2-spec-simples/with_skill/outputs/response.md +1087 -1087
  75. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-2-spec-simples/with_skill/outputs/transcript.md +124 -124
  76. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-2-spec-simples/with_skill/timing.json +1 -1
  77. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-2-spec-simples/without_skill/grading.json +32 -32
  78. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-2-spec-simples/without_skill/outputs/response.md +458 -458
  79. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-2-spec-simples/without_skill/outputs/transcript.md +84 -84
  80. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-2-spec-simples/without_skill/timing.json +1 -1
  81. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-3-sem-user-stories/eval_metadata.json +12 -12
  82. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-3-sem-user-stories/with_skill/grading.json +32 -32
  83. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-3-sem-user-stories/with_skill/outputs/response.md +70 -70
  84. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-3-sem-user-stories/with_skill/outputs/transcript.md +148 -148
  85. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-3-sem-user-stories/with_skill/timing.json +1 -1
  86. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-3-sem-user-stories/without_skill/grading.json +32 -32
  87. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-3-sem-user-stories/without_skill/outputs/response.md +249 -249
  88. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-3-sem-user-stories/without_skill/outputs/transcript.md +80 -80
  89. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/eval-3-sem-user-stories/without_skill/timing.json +1 -1
  90. package/frameworks/skills/sdd-task-plan-expert-workspace/iteration-2/review.html +1325 -1325
  91. package/frameworks/skills/sdd-tech-spec-expert/SKILL.md +317 -317
  92. package/frameworks/skills/sdd-tech-spec-expert/evals/evals.json +199 -199
  93. package/frameworks/skills/sdd-tech-spec-expert/templates/spec_tech_template.md +290 -290
  94. package/frameworks/skills/sdd-tech-spec-expert/templates/tech_direction-template.md +23 -23
  95. package/package.json +28 -28
  96. package/src/cli.js +121 -121
  97. package/src/installer.js +155 -136
  98. package/src/transformer.js +86 -86
@@ -1,78 +1,78 @@
1
- # TASK PLAN – MiniStack
2
-
3
- ## 1. Identificacao
4
- - **Feature**:
5
- - **Intent**: `[caminho-feature]/intent.md`
6
- - **Scope**: `[caminho-feature]/scope.md`
7
- - **Responsavel**:
8
- - **Data**:
9
- - **Status**: Rascunho | Em Andamento | Concluido
10
-
11
- ---
12
-
13
- ## 2. Objetivo Tecnico
14
- O que sera entregue tecnicamente ao final de todas as tasks.
15
-
16
- ---
17
-
18
- ## 3. Macro-Fases (alto nivel)
19
- - **Fase 1 – Preparacao / Fundamentos**
20
- - Objetivo:
21
- - Tasks: T1, T2
22
- - **Fase 2 – Implementacao Principal**
23
- - Objetivo:
24
- - Tasks: T3, T4, T5
25
- - **Fase 3 – Integracoes / Ajustes**
26
- - Objetivo:
27
- - Tasks: T6, T7
28
-
29
- ---
30
-
31
- ## 4. Lista de Tasks (visao macro)
32
- | ID | Nome da Task | Arquivo | Fase | Dependencias | Pode Rodar em Paralelo? | Status |
33
- |----|-------------|---------|------|-------------|------------------------|--------|
34
- | T1 | | [T1](tasks/T1.md) | | — | Sim | A Fazer |
35
- | T2 | | [T2](tasks/T2.md) | | T1 | Nao | A Fazer |
36
-
37
- ---
38
-
39
- ## 5. Ordem de Execucao
40
-
41
- ```
42
- T1 -> T2 -> T3
43
- -> T4 (paralelo)
44
- ```
45
-
46
- ### Grafo de Dependencias
47
- | Task | Depende de | Pode Rodar em Paralelo? | Status |
48
- |------|------------|-------------------------|--------|
49
- | T1 | — | Sim | A Fazer |
50
- | T2 | T1 | Nao | A Fazer |
51
-
52
- ---
53
-
54
- ## 6. Arquivos / Areas Impactadas (visao consolidada)
55
-
56
- | Area | Arquivos | Acao |
57
- |------|----------|------|
58
- | `[camada]/...` | [arquivo] | criar |
59
- | `[camada]/...` | [arquivo] | modificar |
60
-
61
- > **Legenda de Acoes:** `criar` | `modificar` | `remover`
62
-
63
- ---
64
-
65
- ## 7. Criterios de Conclusao Geral
66
- - [ ] Todas as tasks concluidas
67
- - [ ] Objetivo tecnico atingido
68
- - [ ] Codigo compila sem erros
69
- - [ ] Testes unitarios passando
70
- - [ ] Testes de integracao passando (se aplicavel)
71
- - [ ] Testes e2e passando (se aplicavel)
72
-
73
- ---
74
-
75
- ## 8. Notas para a LLM Executora
76
- - Instrucoes especiais de implementacao
77
- - Padroes a seguir
78
- - Convencoes do projeto
1
+ # TASK PLAN – MiniStack
2
+
3
+ ## 1. Identificacao
4
+ - **Feature**:
5
+ - **Intent**: `[caminho-feature]/intent.md`
6
+ - **Scope**: `[caminho-feature]/scope.md`
7
+ - **Responsavel**:
8
+ - **Data**:
9
+ - **Status**: Rascunho | Em Andamento | Concluido
10
+
11
+ ---
12
+
13
+ ## 2. Objetivo Tecnico
14
+ O que sera entregue tecnicamente ao final de todas as tasks.
15
+
16
+ ---
17
+
18
+ ## 3. Macro-Fases (alto nivel)
19
+ - **Fase 1 – Preparacao / Fundamentos**
20
+ - Objetivo:
21
+ - Tasks: T1, T2
22
+ - **Fase 2 – Implementacao Principal**
23
+ - Objetivo:
24
+ - Tasks: T3, T4, T5
25
+ - **Fase 3 – Integracoes / Ajustes**
26
+ - Objetivo:
27
+ - Tasks: T6, T7
28
+
29
+ ---
30
+
31
+ ## 4. Lista de Tasks (visao macro)
32
+ | ID | Nome da Task | Arquivo | Fase | Dependencias | Pode Rodar em Paralelo? | Status |
33
+ |----|-------------|---------|------|-------------|------------------------|--------|
34
+ | T1 | | [T1](tasks/T1.md) | | — | Sim | A Fazer |
35
+ | T2 | | [T2](tasks/T2.md) | | T1 | Nao | A Fazer |
36
+
37
+ ---
38
+
39
+ ## 5. Ordem de Execucao
40
+
41
+ ```
42
+ T1 -> T2 -> T3
43
+ -> T4 (paralelo)
44
+ ```
45
+
46
+ ### Grafo de Dependencias
47
+ | Task | Depende de | Pode Rodar em Paralelo? | Status |
48
+ |------|------------|-------------------------|--------|
49
+ | T1 | — | Sim | A Fazer |
50
+ | T2 | T1 | Nao | A Fazer |
51
+
52
+ ---
53
+
54
+ ## 6. Arquivos / Areas Impactadas (visao consolidada)
55
+
56
+ | Area | Arquivos | Acao |
57
+ |------|----------|------|
58
+ | `[camada]/...` | [arquivo] | criar |
59
+ | `[camada]/...` | [arquivo] | modificar |
60
+
61
+ > **Legenda de Acoes:** `criar` | `modificar` | `remover`
62
+
63
+ ---
64
+
65
+ ## 7. Criterios de Conclusao Geral
66
+ - [ ] Todas as tasks concluidas
67
+ - [ ] Objetivo tecnico atingido
68
+ - [ ] Codigo compila sem erros
69
+ - [ ] Testes unitarios passando
70
+ - [ ] Testes de integracao passando (se aplicavel)
71
+ - [ ] Testes e2e passando (se aplicavel)
72
+
73
+ ---
74
+
75
+ ## 8. Notas para a LLM Executora
76
+ - Instrucoes especiais de implementacao
77
+ - Padroes a seguir
78
+ - Convencoes do projeto
@@ -1,103 +1,103 @@
1
- # TASK – Detalhamento da Task
2
-
3
- ## 1. Identificacao
4
- - **ID**:
5
- - **Nome da Task**:
6
- - **Status**: A Fazer | Em Progresso | Revisao | Concluido
7
- - **Fase**:
8
- - **Dependencias**:
9
- - **Criterio de Conclusao**: Como saber que esta pronta
10
-
11
- ---
12
-
13
- ## 2. Objetivo da Task
14
- O que esta task entrega (resultado tecnico direto).
15
-
16
- ---
17
-
18
- ## 3. Arquivos Impactados
19
-
20
- ### 3.1 Arquivos a Criar
21
- | Arquivo | Descricao |
22
- |---------|-----------|
23
- | | |
24
-
25
- ### 3.2 Arquivos a Modificar
26
- | Arquivo | Modificacao |
27
- |---------|------------|
28
- | | |
29
-
30
- ### 3.3 Arquivos de Referencia
31
- | Arquivo | Motivo da Consulta |
32
- |---------|-------------------|
33
- | | |
34
-
35
- ---
36
-
37
- ## 4. Detalhes de Implementacao
38
- - [ ] Subtask 1
39
- - [ ] Subtask 2
40
-
41
- ---
42
-
43
- ## 5. Testes
44
-
45
- <!-- LLM-ONLY: Coluna "Objetivo": Descreva em 1 frase O QUE o teste valida e POR QUE importa. Use o padrao: Verbo + comportamento especifico + condicao. Exemplo: "Verificar que apenas categorias com ativo=1 sao retornadas, ordenadas pelo campo 'ordem'". NAO repita o nome do teste. -->
46
-
47
- ### 5.1 Testes Unitarios
48
-
49
- #### [Camada]: [NomeComponente] (`arquivo_test.go`)
50
-
51
- Mock: [interfaces mockadas]
52
-
53
- | CT | Teste | Objetivo | Input | Expected | Mock |
54
- |----|-------|----------|-------|----------|------|
55
- | CT-XX | TestMetodo_Cenario | Verificar que [comportamento] quando [condicao] | dados entrada | resultado esperado | dependencias mockadas |
56
-
57
- ### 5.2 Testes de Integracao
58
-
59
- #### [CamadaA + CamadaB] (`arquivo_test.go`)
60
-
61
- Setup: [banco in-memory, migracoes, fixtures]
62
-
63
- | CT | Teste | Objetivo | Fluxo | Validacao |
64
- |----|-------|----------|-------|-----------|
65
- | CT-XX | TestIntegracao_Cenario | Verificar que [comportamento] quando [condicao] | Passos do fluxo | Assertions esperadas |
66
-
67
- ### 5.3 Testes E2E
68
-
69
- #### Fluxo: [Nome do Fluxo] (CT-XX)
70
- - **Objetivo**: (1 frase descrevendo o que este fluxo E2E valida de ponta a ponta)
71
- - **Pre-condicoes**: (estado inicial do sistema)
72
- - **Passos**:
73
- 1. Passo 1
74
- 2. Passo 2
75
- - **Validacoes**: (assertions sobre dados e estado final)
76
-
77
- ### 5.4 Cenarios de Erro
78
-
79
- | Cenario | Objetivo | Trigger | Codigo/Status | Log Esperado |
80
- |---------|----------|---------|---------------|-------------|
81
- | Descricao do cenario | Verificar que [constraint] impede [operacao] | Acao trigger | Codigo erro | Mensagem log |
82
-
83
- ### Testes Existentes a Modificar
84
-
85
- | Arquivo | Motivo da Modificacao |
86
- |---------|----------------------|
87
- | | |
88
-
89
- <!-- LLM-ONLY: Se nenhum teste existente precisa ser modificado, escreva: "Nenhum teste existente impactado." -->
90
-
91
- ---
92
-
93
- ## 6. Notas / Observacoes
94
- Anotacoes tecnicas, decisoes, pontos relevantes.
95
-
96
- ---
97
-
98
- ## 7. Checklist Final
99
- - [ ] Implementada conforme Scope
100
- - [ ] Testes unitarios criados/atualizados
101
- - [ ] Testes de integracao criados/atualizados
102
- - [ ] Criterio de conclusao atendido
103
- - [ ] Revisada
1
+ # TASK – Detalhamento da Task
2
+
3
+ ## 1. Identificacao
4
+ - **ID**:
5
+ - **Nome da Task**:
6
+ - **Status**: A Fazer | Em Progresso | Revisao | Concluido
7
+ - **Fase**:
8
+ - **Dependencias**:
9
+ - **Criterio de Conclusao**: Como saber que esta pronta
10
+
11
+ ---
12
+
13
+ ## 2. Objetivo da Task
14
+ O que esta task entrega (resultado tecnico direto).
15
+
16
+ ---
17
+
18
+ ## 3. Arquivos Impactados
19
+
20
+ ### 3.1 Arquivos a Criar
21
+ | Arquivo | Descricao |
22
+ |---------|-----------|
23
+ | | |
24
+
25
+ ### 3.2 Arquivos a Modificar
26
+ | Arquivo | Modificacao |
27
+ |---------|------------|
28
+ | | |
29
+
30
+ ### 3.3 Arquivos de Referencia
31
+ | Arquivo | Motivo da Consulta |
32
+ |---------|-------------------|
33
+ | | |
34
+
35
+ ---
36
+
37
+ ## 4. Detalhes de Implementacao
38
+ - [ ] Subtask 1
39
+ - [ ] Subtask 2
40
+
41
+ ---
42
+
43
+ ## 5. Testes
44
+
45
+ <!-- LLM-ONLY: Coluna "Objetivo": Descreva em 1 frase O QUE o teste valida e POR QUE importa. Use o padrao: Verbo + comportamento especifico + condicao. Exemplo: "Verificar que apenas categorias com ativo=1 sao retornadas, ordenadas pelo campo 'ordem'". NAO repita o nome do teste. -->
46
+
47
+ ### 5.1 Testes Unitarios
48
+
49
+ #### [Camada]: [NomeComponente] (`arquivo_test.go`)
50
+
51
+ Mock: [interfaces mockadas]
52
+
53
+ | CT | Teste | Objetivo | Input | Expected | Mock |
54
+ |----|-------|----------|-------|----------|------|
55
+ | CT-XX | TestMetodo_Cenario | Verificar que [comportamento] quando [condicao] | dados entrada | resultado esperado | dependencias mockadas |
56
+
57
+ ### 5.2 Testes de Integracao
58
+
59
+ #### [CamadaA + CamadaB] (`arquivo_test.go`)
60
+
61
+ Setup: [banco in-memory, migracoes, fixtures]
62
+
63
+ | CT | Teste | Objetivo | Fluxo | Validacao |
64
+ |----|-------|----------|-------|-----------|
65
+ | CT-XX | TestIntegracao_Cenario | Verificar que [comportamento] quando [condicao] | Passos do fluxo | Assertions esperadas |
66
+
67
+ ### 5.3 Testes E2E
68
+
69
+ #### Fluxo: [Nome do Fluxo] (CT-XX)
70
+ - **Objetivo**: (1 frase descrevendo o que este fluxo E2E valida de ponta a ponta)
71
+ - **Pre-condicoes**: (estado inicial do sistema)
72
+ - **Passos**:
73
+ 1. Passo 1
74
+ 2. Passo 2
75
+ - **Validacoes**: (assertions sobre dados e estado final)
76
+
77
+ ### 5.4 Cenarios de Erro
78
+
79
+ | Cenario | Objetivo | Trigger | Codigo/Status | Log Esperado |
80
+ |---------|----------|---------|---------------|-------------|
81
+ | Descricao do cenario | Verificar que [constraint] impede [operacao] | Acao trigger | Codigo erro | Mensagem log |
82
+
83
+ ### Testes Existentes a Modificar
84
+
85
+ | Arquivo | Motivo da Modificacao |
86
+ |---------|----------------------|
87
+ | | |
88
+
89
+ <!-- LLM-ONLY: Se nenhum teste existente precisa ser modificado, escreva: "Nenhum teste existente impactado." -->
90
+
91
+ ---
92
+
93
+ ## 6. Notas / Observacoes
94
+ Anotacoes tecnicas, decisoes, pontos relevantes.
95
+
96
+ ---
97
+
98
+ ## 7. Checklist Final
99
+ - [ ] Implementada conforme Scope
100
+ - [ ] Testes unitarios criados/atualizados
101
+ - [ ] Testes de integracao criados/atualizados
102
+ - [ ] Criterio de conclusao atendido
103
+ - [ ] Revisada
@@ -1,99 +1,99 @@
1
- {
2
- "skill_name": "sdd-task-plan-expert",
3
- "iteration": 1,
4
- "configurations": [
5
- {
6
- "name": "with_skill",
7
- "pass_rate": 0.933,
8
- "mean_tokens": 55027,
9
- "stddev_tokens": 10217,
10
- "mean_duration_seconds": 184.9,
11
- "stddev_duration_seconds": 85.7,
12
- "evals": [
13
- {
14
- "eval_name": "happy-path-spec-tech-usuario",
15
- "pass_rate": 0.8,
16
- "passed": 4,
17
- "total": 5,
18
- "tokens": 61221,
19
- "duration_seconds": 138.2,
20
- "failed_assertions": ["Le as rules do projeto (.claude/rules/ e CLAUDE.md) ANTES de gerar tasks"]
21
- },
22
- {
23
- "eval_name": "spec-tech-simples-alteracao-pontual",
24
- "pass_rate": 1.0,
25
- "passed": 5,
26
- "total": 5,
27
- "tokens": 60596,
28
- "duration_seconds": 286.6,
29
- "failed_assertions": []
30
- },
31
- {
32
- "eval_name": "spec-tech-sem-user-stories-explicitas",
33
- "pass_rate": 1.0,
34
- "passed": 5,
35
- "total": 5,
36
- "tokens": 43263,
37
- "duration_seconds": 130.0,
38
- "failed_assertions": []
39
- }
40
- ]
41
- },
42
- {
43
- "name": "without_skill",
44
- "pass_rate": 0.333,
45
- "mean_tokens": 38834,
46
- "stddev_tokens": 3912,
47
- "mean_duration_seconds": 151.2,
48
- "stddev_duration_seconds": 14.5,
49
- "evals": [
50
- {
51
- "eval_name": "happy-path-spec-tech-usuario",
52
- "pass_rate": 0.2,
53
- "passed": 1,
54
- "total": 5,
55
- "tokens": 40363,
56
- "duration_seconds": 141.3,
57
- "failed_assertions": [
58
- "Extrai o nome da feature do SPEC_TECH e confirma com o usuario antes de prosseguir",
59
- "Faz apenas UMA pergunta por vez",
60
- "Propoe macro-fases de alto nivel e aguarda validacao antes de criar tasks",
61
- "Le as rules do projeto (.claude/rules/ e CLAUDE.md) ANTES de gerar tasks"
62
- ]
63
- },
64
- {
65
- "eval_name": "spec-tech-simples-alteracao-pontual",
66
- "pass_rate": 0.2,
67
- "passed": 1,
68
- "total": 5,
69
- "tokens": 41818,
70
- "duration_seconds": 167.6,
71
- "failed_assertions": [
72
- "Gera um numero proporcional de tasks (entre 3 e 6)",
73
- "Mapeia a US-10 na tabela de rastreabilidade do task_plan",
74
- "Cada task segue o template completo (secoes 1-8)",
75
- "Salva task_plan.md como documento de REFERENCIA"
76
- ]
77
- },
78
- {
79
- "eval_name": "spec-tech-sem-user-stories-explicitas",
80
- "pass_rate": 0.4,
81
- "passed": 2,
82
- "total": 5,
83
- "tokens": 34322,
84
- "duration_seconds": 144.7,
85
- "failed_assertions": [
86
- "PERGUNTA ao usuario sobre User Stories / PRD em vez de inventar ou ignorar",
87
- "Extrai corretamente o nome da feature em kebab-case",
88
- "Segue o processo interativo (uma pergunta por vez)"
89
- ]
90
- }
91
- ]
92
- }
93
- ],
94
- "delta": {
95
- "pass_rate_improvement": "+60.0pp",
96
- "tokens_overhead": "+41.7%",
97
- "duration_overhead": "+22.3%"
98
- }
99
- }
1
+ {
2
+ "skill_name": "sdd-task-plan-expert",
3
+ "iteration": 1,
4
+ "configurations": [
5
+ {
6
+ "name": "with_skill",
7
+ "pass_rate": 0.933,
8
+ "mean_tokens": 55027,
9
+ "stddev_tokens": 10217,
10
+ "mean_duration_seconds": 184.9,
11
+ "stddev_duration_seconds": 85.7,
12
+ "evals": [
13
+ {
14
+ "eval_name": "happy-path-spec-tech-usuario",
15
+ "pass_rate": 0.8,
16
+ "passed": 4,
17
+ "total": 5,
18
+ "tokens": 61221,
19
+ "duration_seconds": 138.2,
20
+ "failed_assertions": ["Le as rules do projeto (.claude/rules/ e CLAUDE.md) ANTES de gerar tasks"]
21
+ },
22
+ {
23
+ "eval_name": "spec-tech-simples-alteracao-pontual",
24
+ "pass_rate": 1.0,
25
+ "passed": 5,
26
+ "total": 5,
27
+ "tokens": 60596,
28
+ "duration_seconds": 286.6,
29
+ "failed_assertions": []
30
+ },
31
+ {
32
+ "eval_name": "spec-tech-sem-user-stories-explicitas",
33
+ "pass_rate": 1.0,
34
+ "passed": 5,
35
+ "total": 5,
36
+ "tokens": 43263,
37
+ "duration_seconds": 130.0,
38
+ "failed_assertions": []
39
+ }
40
+ ]
41
+ },
42
+ {
43
+ "name": "without_skill",
44
+ "pass_rate": 0.333,
45
+ "mean_tokens": 38834,
46
+ "stddev_tokens": 3912,
47
+ "mean_duration_seconds": 151.2,
48
+ "stddev_duration_seconds": 14.5,
49
+ "evals": [
50
+ {
51
+ "eval_name": "happy-path-spec-tech-usuario",
52
+ "pass_rate": 0.2,
53
+ "passed": 1,
54
+ "total": 5,
55
+ "tokens": 40363,
56
+ "duration_seconds": 141.3,
57
+ "failed_assertions": [
58
+ "Extrai o nome da feature do SPEC_TECH e confirma com o usuario antes de prosseguir",
59
+ "Faz apenas UMA pergunta por vez",
60
+ "Propoe macro-fases de alto nivel e aguarda validacao antes de criar tasks",
61
+ "Le as rules do projeto (.claude/rules/ e CLAUDE.md) ANTES de gerar tasks"
62
+ ]
63
+ },
64
+ {
65
+ "eval_name": "spec-tech-simples-alteracao-pontual",
66
+ "pass_rate": 0.2,
67
+ "passed": 1,
68
+ "total": 5,
69
+ "tokens": 41818,
70
+ "duration_seconds": 167.6,
71
+ "failed_assertions": [
72
+ "Gera um numero proporcional de tasks (entre 3 e 6)",
73
+ "Mapeia a US-10 na tabela de rastreabilidade do task_plan",
74
+ "Cada task segue o template completo (secoes 1-8)",
75
+ "Salva task_plan.md como documento de REFERENCIA"
76
+ ]
77
+ },
78
+ {
79
+ "eval_name": "spec-tech-sem-user-stories-explicitas",
80
+ "pass_rate": 0.4,
81
+ "passed": 2,
82
+ "total": 5,
83
+ "tokens": 34322,
84
+ "duration_seconds": 144.7,
85
+ "failed_assertions": [
86
+ "PERGUNTA ao usuario sobre User Stories / PRD em vez de inventar ou ignorar",
87
+ "Extrai corretamente o nome da feature em kebab-case",
88
+ "Segue o processo interativo (uma pergunta por vez)"
89
+ ]
90
+ }
91
+ ]
92
+ }
93
+ ],
94
+ "delta": {
95
+ "pass_rate_improvement": "+60.0pp",
96
+ "tokens_overhead": "+41.7%",
97
+ "duration_overhead": "+22.3%"
98
+ }
99
+ }