claude-symphony 0.0.1 → 0.0.2

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 (148) hide show
  1. package/README.md +16 -12
  2. package/bin/create.js +80 -69
  3. package/package.json +1 -1
  4. package/template/.claude/commands/benchmark.md +32 -32
  5. package/template/.claude/commands/brainstorm.md +33 -33
  6. package/template/.claude/commands/checkpoint.md +42 -42
  7. package/template/.claude/commands/codex.md +52 -52
  8. package/template/.claude/commands/collaborate.md +47 -47
  9. package/template/.claude/commands/context.md +77 -77
  10. package/template/.claude/commands/deploy.md +50 -50
  11. package/template/.claude/commands/fork.md +46 -46
  12. package/template/.claude/commands/gemini.md +43 -43
  13. package/template/.claude/commands/handoff.md +42 -42
  14. package/template/.claude/commands/implement.md +42 -42
  15. package/template/.claude/commands/init-project.md +25 -25
  16. package/template/.claude/commands/next.md +67 -67
  17. package/template/.claude/commands/planning.md +38 -38
  18. package/template/.claude/commands/qa.md +47 -47
  19. package/template/.claude/commands/refactor.md +50 -50
  20. package/template/.claude/commands/research.md +31 -31
  21. package/template/.claude/commands/restore.md +53 -53
  22. package/template/.claude/commands/run-stage.md +45 -45
  23. package/template/.claude/commands/stages.md +49 -49
  24. package/template/.claude/commands/status.md +41 -41
  25. package/template/.claude/commands/tasks.md +33 -33
  26. package/template/.claude/commands/test.md +45 -45
  27. package/template/.claude/commands/ui-ux.md +31 -31
  28. package/template/.claude/commands/validate.md +81 -81
  29. package/template/.claude/hooks/ai-selector.sh +39 -39
  30. package/template/.claude/hooks/auto-checkpoint.sh +30 -30
  31. package/template/.claude/hooks/output-validator.sh +45 -45
  32. package/template/.claude/hooks/post-stage.sh +28 -28
  33. package/template/.claude/hooks/pre-stage.sh +47 -47
  34. package/template/.claude/hooks/session-start.sh +27 -27
  35. package/template/.claude/hooks/statusline.sh +24 -24
  36. package/template/.claude/hooks/stop.sh +26 -26
  37. package/template/.claude/settings.json +32 -32
  38. package/template/.claude/skills/ai-collaboration/README.md +31 -31
  39. package/template/.claude/skills/ai-collaboration/debate.md +66 -66
  40. package/template/.claude/skills/ai-collaboration/parallel.md +34 -34
  41. package/template/.claude/skills/ai-collaboration/prompts/CLAUDE.md +59 -63
  42. package/template/.claude/skills/auto-checkpoint/README.md +46 -46
  43. package/template/.claude/skills/auto-checkpoint/prompts/CLAUDE.md +68 -72
  44. package/template/.claude/skills/auto-checkpoint/rollback.md +95 -95
  45. package/template/.claude/skills/auto-checkpoint/trigger.md +37 -37
  46. package/template/.claude/skills/context-compression/README.md +69 -69
  47. package/template/.claude/skills/context-compression/analyze.md +74 -74
  48. package/template/.claude/skills/context-compression/compress.md +103 -103
  49. package/template/.claude/skills/context-compression/prompts/compression.md +78 -78
  50. package/template/.claude/skills/output-validator/README.md +33 -33
  51. package/template/.claude/skills/output-validator/prompts/CLAUDE.md +74 -78
  52. package/template/.claude/skills/output-validator/validate.md +76 -76
  53. package/template/.claude/skills/smart-handoff/README.md +35 -35
  54. package/template/.claude/skills/smart-handoff/extract.md +42 -42
  55. package/template/.claude/skills/smart-handoff/prompts/CLAUDE.md +52 -54
  56. package/template/.claude/skills/smart-handoff/summarize.md +55 -55
  57. package/template/.claude/skills/stage-transition/README.md +50 -50
  58. package/template/.claude/skills/stage-transition/handoff-gen.md +89 -89
  59. package/template/.claude/skills/stage-transition/prompts/transition.md +74 -74
  60. package/template/.claude/skills/stage-transition/validate.md +41 -41
  61. package/template/CLAUDE.md +334 -335
  62. package/template/config/ai_benchmarking.yaml +22 -22
  63. package/template/config/ai_collaboration.yaml +18 -18
  64. package/template/config/ai_logging.yaml +50 -50
  65. package/template/config/auto_checkpoint.yaml +32 -32
  66. package/template/config/context.yaml +20 -20
  67. package/template/config/git.yaml +51 -51
  68. package/template/config/handoff_intelligence.yaml +23 -23
  69. package/template/config/mcp_fallbacks.yaml +71 -71
  70. package/template/config/memory_integration.yaml +23 -23
  71. package/template/config/model_enforcement.yaml +53 -53
  72. package/template/config/models.yaml +24 -24
  73. package/template/config/output_validation.yaml +44 -44
  74. package/template/config/pipeline.yaml +25 -25
  75. package/template/config/pipeline_forking.yaml +40 -40
  76. package/template/config/qa_logging.yaml +67 -67
  77. package/template/config/smart_rollback.yaml +48 -48
  78. package/template/config/stage_personas.yaml +154 -154
  79. package/template/config/workflow.yaml +16 -16
  80. package/template/scripts/ai-benchmark.sh +41 -41
  81. package/template/scripts/codex-wrapper.sh +32 -32
  82. package/template/scripts/context-manager.sh +136 -136
  83. package/template/scripts/create-checkpoint.sh +34 -34
  84. package/template/scripts/gemini-wrapper.sh +31 -31
  85. package/template/scripts/init-project.sh +40 -40
  86. package/template/scripts/list-stages.sh +30 -30
  87. package/template/scripts/next-stage.sh +67 -67
  88. package/template/scripts/output-validate.sh +2 -2
  89. package/template/scripts/pipeline-fork.sh +68 -68
  90. package/template/scripts/pre-run-check.sh +84 -84
  91. package/template/scripts/restore-checkpoint.sh +50 -50
  92. package/template/scripts/run-stage.sh +44 -44
  93. package/template/scripts/show-status.sh +30 -30
  94. package/template/scripts/smart-handoff.sh +70 -70
  95. package/template/stages/01-brainstorm/CLAUDE.md +70 -74
  96. package/template/stages/01-brainstorm/README.md +54 -54
  97. package/template/stages/01-brainstorm/config.yaml +18 -18
  98. package/template/stages/01-brainstorm/prompts/collaboration.md +24 -24
  99. package/template/stages/01-brainstorm/prompts/ideation.md +41 -41
  100. package/template/stages/01-brainstorm/prompts/persona.md +50 -50
  101. package/template/stages/01-brainstorm/prompts/requirements.md +55 -55
  102. package/template/stages/01-brainstorm/prompts/validation.md +28 -28
  103. package/template/stages/01-brainstorm/templates/ideas.md +47 -47
  104. package/template/stages/01-brainstorm/templates/requirements_analysis.md +61 -61
  105. package/template/stages/02-research/CLAUDE.md +72 -76
  106. package/template/stages/02-research/config.yaml +12 -12
  107. package/template/stages/02-research/prompts/collaboration.md +29 -29
  108. package/template/stages/02-research/prompts/feasibility.md +38 -38
  109. package/template/stages/02-research/prompts/market_analysis.md +29 -29
  110. package/template/stages/02-research/prompts/tech_stack.md +34 -34
  111. package/template/stages/02-research/prompts/validation.md +29 -29
  112. package/template/stages/03-planning/CLAUDE.md +88 -92
  113. package/template/stages/03-planning/config.yaml +10 -10
  114. package/template/stages/03-planning/prompts/architecture.md +43 -43
  115. package/template/stages/03-planning/prompts/collaboration.md +34 -34
  116. package/template/stages/03-planning/prompts/validation.md +34 -34
  117. package/template/stages/04-ui-ux/CLAUDE.md +68 -72
  118. package/template/stages/04-ui-ux/config.yaml +5 -5
  119. package/template/stages/04-ui-ux/prompts/collaboration.md +35 -35
  120. package/template/stages/04-ui-ux/prompts/validation.md +30 -30
  121. package/template/stages/05-task-management/CLAUDE.md +81 -85
  122. package/template/stages/05-task-management/config.yaml +17 -17
  123. package/template/stages/05-task-management/prompts/collaboration.md +30 -30
  124. package/template/stages/05-task-management/prompts/validation.md +33 -33
  125. package/template/stages/05-task-management/templates/notion_integration.md +70 -70
  126. package/template/stages/05-task-management/templates/parallel_groups.yaml +64 -64
  127. package/template/stages/05-task-management/templates/task_schema.yaml +33 -33
  128. package/template/stages/06-implementation/CLAUDE.md +117 -121
  129. package/template/stages/06-implementation/config.yaml +10 -10
  130. package/template/stages/06-implementation/prompts/collaboration.md +29 -29
  131. package/template/stages/06-implementation/prompts/validation.md +36 -36
  132. package/template/stages/07-refactoring/CLAUDE.md +120 -124
  133. package/template/stages/07-refactoring/config.yaml +11 -11
  134. package/template/stages/07-refactoring/prompts/collaboration.md +36 -36
  135. package/template/stages/07-refactoring/prompts/validation.md +40 -40
  136. package/template/stages/08-qa/CLAUDE.md +80 -84
  137. package/template/stages/08-qa/config.yaml +7 -7
  138. package/template/stages/08-qa/prompts/collaboration.md +34 -34
  139. package/template/stages/08-qa/prompts/validation.md +41 -41
  140. package/template/stages/09-testing/CLAUDE.md +86 -90
  141. package/template/stages/09-testing/config.yaml +10 -10
  142. package/template/stages/09-testing/prompts/collaboration.md +38 -38
  143. package/template/stages/09-testing/prompts/validation.md +41 -41
  144. package/template/stages/10-deployment/CLAUDE.md +86 -90
  145. package/template/stages/10-deployment/config.yaml +11 -11
  146. package/template/stages/10-deployment/prompts/collaboration.md +37 -37
  147. package/template/stages/10-deployment/prompts/validation.md +54 -54
  148. package/template/stages/10-deployment/templates/github-actions-cd.yaml +1 -1
@@ -1,50 +1,50 @@
1
1
  # AI Collaboration - Debate Mode
2
2
 
3
- ## 토론 모드
3
+ ## Debate Mode
4
4
 
5
- 여러 AI 모델이 다양한 관점에서 토론하여 최적의 결론을 도출합니다.
5
+ Multiple AI models debate from various perspectives to derive optimal conclusions.
6
6
 
7
- ## 사용 시나리오
7
+ ## Use Scenarios
8
8
 
9
- 1. **아키텍처 결정**: 여러 설계 대안 비교
10
- 2. **기술 선택**: 프레임워크/라이브러리 선택
11
- 3. **트레이드오프 분석**: 성능 vs 유지보수성
9
+ 1. **Architecture Decisions**: Compare multiple design alternatives
10
+ 2. **Technology Selection**: Framework/library selection
11
+ 3. **Trade-off Analysis**: Performance vs maintainability, etc.
12
12
 
13
- ## 토론 구조
13
+ ## Debate Structure
14
14
 
15
- ### 참가자 역할
15
+ ### Participant Roles
16
16
 
17
17
  ```yaml
18
18
  participants:
19
19
  advocate:
20
20
  model: "claude"
21
- perspective: "기술적 실현 가능성"
22
- stance: "안정적이고 검증된 접근법"
21
+ perspective: "Technical feasibility"
22
+ stance: "Stable and proven approach"
23
23
 
24
24
  challenger:
25
25
  model: "gemini"
26
- perspective: "혁신적 접근법"
27
- stance: "새로운 기술과 방법론"
26
+ perspective: "Innovative approach"
27
+ stance: "New technologies and methodologies"
28
28
  ```
29
29
 
30
- ### 토론 라운드
30
+ ### Debate Rounds
31
31
 
32
32
  ```
33
- Round 1: 초기 입장 제시
34
- - Advocate: [입장 + 근거]
35
- - Challenger: [반대 입장 + 근거]
36
-
37
- Round 2: 반박 보완
38
- - Advocate: [반박 + 추가 근거]
39
- - Challenger: [반박 + 추가 근거]
40
-
41
- Round 3: 수렴 결론
42
- - 공통점 도출
43
- - 합의점 정리
44
- - 최종 권장사항
33
+ Round 1: Present initial positions
34
+ - Advocate: [Position + Evidence]
35
+ - Challenger: [Counter position + Evidence]
36
+
37
+ Round 2: Rebuttals and supplements
38
+ - Advocate: [Rebuttal + Additional evidence]
39
+ - Challenger: [Rebuttal + Additional evidence]
40
+
41
+ Round 3: Convergence and conclusion
42
+ - Extract common points
43
+ - Summarize agreements
44
+ - Final recommendations
45
45
  ```
46
46
 
47
- ## 토론 규칙
47
+ ## Debate Rules
48
48
 
49
49
  ```yaml
50
50
  rules:
@@ -54,95 +54,95 @@ rules:
54
54
  convergence_check: true
55
55
  ```
56
56
 
57
- ### 증거 요구사항
58
- - 주장에는 반드시 근거 제시
59
- - 가능한 경우 수치/데이터 포함
60
- - 사례 인용 권장
57
+ ### Evidence Requirements
58
+ - Claims must include supporting evidence
59
+ - Include numbers/data when possible
60
+ - Case citations recommended
61
61
 
62
- ## 실행 방법
62
+ ## Execution Method
63
63
 
64
- ### 1. 토론 주제 설정
64
+ ### 1. Set Debate Topic
65
65
  ```bash
66
- /collaborate --mode debate --topic "모놀리식 vs 마이크로서비스"
66
+ /collaborate --mode debate --topic "monolithic vs microservices"
67
67
  ```
68
68
 
69
- ### 2. 관점 할당
69
+ ### 2. Assign Perspectives
70
70
  ```yaml
71
71
  debate_setup:
72
- topic: "모놀리식 vs 마이크로서비스"
72
+ topic: "monolithic vs microservices"
73
73
  advocate:
74
74
  model: "claude"
75
- position: "모놀리식 (초기 단계)"
75
+ position: "Monolithic (initial phase)"
76
76
  challenger:
77
77
  model: "gemini"
78
- position: "마이크로서비스 (확장성)"
78
+ position: "Microservices (scalability)"
79
79
  ```
80
80
 
81
- ### 3. 토론 진행
82
- 라운드별로 순차적으로 응답 수집
81
+ ### 3. Conduct Debate
82
+ Collect responses sequentially per round
83
83
 
84
- ### 4. 결론 도출
84
+ ### 4. Derive Conclusion
85
85
  ```yaml
86
86
  conclusion:
87
87
  method: "consensus" # or "vote", "weighted"
88
88
  include_dissenting: true
89
89
  ```
90
90
 
91
- ## 출력 형식
91
+ ## Output Format
92
92
 
93
93
  ```markdown
94
94
  # Debate Results
95
95
 
96
96
  ## Topic
97
- [토론 주제]
97
+ [Debate topic]
98
98
 
99
99
  ## Round 1: Initial Positions
100
100
 
101
101
  ### Advocate (Claude)
102
- **Position**: [입장]
102
+ **Position**: [Position]
103
103
  **Arguments**:
104
- 1. [근거 1]
105
- 2. [근거 2]
104
+ 1. [Evidence 1]
105
+ 2. [Evidence 2]
106
106
 
107
107
  ### Challenger (Gemini)
108
- **Position**: [입장]
108
+ **Position**: [Position]
109
109
  **Arguments**:
110
- 1. [근거 1]
111
- 2. [근거 2]
110
+ 1. [Evidence 1]
111
+ 2. [Evidence 2]
112
112
 
113
113
  ## Round 2: Rebuttals
114
- [반박 내용]
114
+ [Rebuttal content]
115
115
 
116
116
  ## Round 3: Convergence
117
- [수렴 과정]
117
+ [Convergence process]
118
118
 
119
119
  ## Conclusion
120
120
 
121
121
  ### Consensus Points
122
- - [합의점 1]
123
- - [합의점 2]
122
+ - [Consensus 1]
123
+ - [Consensus 2]
124
124
 
125
125
  ### Remaining Differences
126
- - [의견 차이]
126
+ - [Differences]
127
127
 
128
128
  ### Recommendation
129
- [최종 권장사항]
129
+ [Final recommendation]
130
130
 
131
131
  ### Dissenting Opinion
132
- [소수 의견 - 선택적]
132
+ [Minority opinion - optional]
133
133
  ```
134
134
 
135
- ## 결론 도출 방법
135
+ ## Conclusion Methods
136
136
 
137
- ### Consensus (합의)
138
- - 공통점 추출
139
- - 차이점 명시
140
- - 절충안 제시
137
+ ### Consensus
138
+ - Extract common points
139
+ - Specify differences
140
+ - Propose compromise
141
141
 
142
- ### Vote (투표)
143
- - AI 최종 선택
144
- - 다수결
142
+ ### Vote
143
+ - Each AI's final choice
144
+ - Majority rule
145
145
 
146
- ### Weighted (가중치)
147
- - 전문성에 따른 가중치
148
- - 가중 평균으로 결정
146
+ ### Weighted
147
+ - Weight by expertise
148
+ - Weighted average decision
@@ -1,47 +1,47 @@
1
1
  # AI Collaboration - Parallel Execution
2
2
 
3
- ## 병렬 실행 모드
3
+ ## Parallel Execution Mode
4
4
 
5
- 동일한 작업을 여러 AI 모델이 동시에 수행하여 다양한 결과물 최적을 선택합니다.
5
+ Multiple AI models perform the same task simultaneously to select optimal from various results.
6
6
 
7
- ## 사용 시나리오
7
+ ## Use Scenarios
8
8
 
9
- 1. **아이디어 생성**: 다양한 관점의 아이디어 수집
10
- 2. **코드 구현**: 여러 접근법 비교
11
- 3. **문서 작성**: 스타일 비교
9
+ 1. **Idea Generation**: Collect ideas from various perspectives
10
+ 2. **Code Implementation**: Compare multiple approaches
11
+ 3. **Documentation**: Compare styles
12
12
 
13
- ## 실행 프로세스
13
+ ## Execution Process
14
14
 
15
- ### 1. 작업 정의
15
+ ### 1. Task Definition
16
16
  ```yaml
17
17
  task:
18
- description: "사용자 인증 시스템 설계"
18
+ description: "User authentication system design"
19
19
  type: "design"
20
20
  constraints:
21
- - "JWT 기반"
22
- - "OAuth 지원"
21
+ - "JWT based"
22
+ - "OAuth support"
23
23
  ```
24
24
 
25
- ### 2. 모델 선택
25
+ ### 2. Model Selection
26
26
  ```yaml
27
27
  models:
28
28
  - gemini:
29
- focus: "창의적 접근"
29
+ focus: "Creative approach"
30
30
  - claude:
31
- focus: "실용적 구현"
31
+ focus: "Practical implementation"
32
32
  ```
33
33
 
34
- ### 3. 병렬 실행
34
+ ### 3. Parallel Execution
35
35
  ```bash
36
- # tmux 세션을 통한 동시 실행
36
+ # Simultaneous execution via tmux sessions
37
37
  scripts/gemini-wrapper.sh "prompts/task.md" &
38
- # Claude 현재 세션에서 실행
38
+ # Claude runs in current session
39
39
  ```
40
40
 
41
- ### 4. 결과 수집
42
- AI 출력을 `state/collaborations/{task_id}/` 에 저장
41
+ ### 4. Collect Results
42
+ Save each AI's output to `state/collaborations/{task_id}/`
43
43
 
44
- ### 5. 평가 선택
44
+ ### 5. Evaluate and Select
45
45
  ```yaml
46
46
  evaluation:
47
47
  metrics:
@@ -50,32 +50,32 @@ evaluation:
50
50
  - feasibility: 0.4
51
51
  ```
52
52
 
53
- ## 병합 전략
53
+ ## Merge Strategies
54
54
 
55
55
  ### Best-of-N
56
- - 점수가 가장 높은 결과 선택
57
- - 임계값 이상(0.85)이면 자동 선택
56
+ - Select result with highest score
57
+ - Auto-select if above threshold (0.85)
58
58
 
59
59
  ### Synthesis
60
- - 결과의 장점만 추출
61
- - 새로운 통합 결과물 생성
60
+ - Extract only advantages from each result
61
+ - Generate new integrated result
62
62
 
63
- ## 출력 형식
63
+ ## Output Format
64
64
 
65
65
  ```markdown
66
66
  # Parallel Execution Results
67
67
 
68
68
  ## Task
69
- [작업 설명]
69
+ [Task description]
70
70
 
71
71
  ## Results
72
72
 
73
73
  ### Gemini Result
74
- [결과 내용]
74
+ [Result content]
75
75
  **Score**: 0.82
76
76
 
77
77
  ### Claude Result
78
- [결과 내용]
78
+ [Result content]
79
79
  **Score**: 0.88
80
80
 
81
81
  ## Analysis
@@ -86,11 +86,11 @@ evaluation:
86
86
  | Feasibility | 0.75 | 0.90 |
87
87
 
88
88
  ## Selected: Claude Result
89
- **Reason**: 높은 실현 가능성과 완성도
89
+ **Reason**: High feasibility and completeness
90
90
  ```
91
91
 
92
- ## 리소스 관리
92
+ ## Resource Management
93
93
 
94
- - 최대 동시 실행: 2 모델
95
- - 토큰 예산: 협업당 50,000
96
- - 타임아웃: 모델당 5분
94
+ - Max concurrent execution: 2 models
95
+ - Token budget: 50,000 per collaboration
96
+ - Timeout: 5 minutes per model
@@ -1,107 +1,103 @@
1
1
  # AI Collaboration Skill - AI Instructions
2
2
 
3
- ## 역할
3
+ ## Role
4
4
 
5
- 당신은 Multi-AI 협업 조정자입니다. 여러 AI 모델의 결과물을 조율하고 최적의 결과를 도출합니다.
5
+ You are a Multi-AI collaboration coordinator. You coordinate the results from multiple AI models to derive optimal outcomes.
6
6
 
7
- ## 협업 모드별 지침
7
+ ## Mode-Specific Instructions
8
8
 
9
9
  ### Parallel Execution Mode
10
10
 
11
- **목표**: 다양한 관점의 결과물 최적 선택
11
+ **Goal**: Select optimal from results with various perspectives
12
12
 
13
- **프로세스**:
14
- 1. 작업을 명확히 정의
15
- 2. AI 모델에 적합한 프롬프트 준비
16
- 3. 결과물 수집 평가
17
- 4. 객관적 기준으로 선택/병합
13
+ **Process**:
14
+ 1. Clearly define the task
15
+ 2. Prepare appropriate prompts for each AI model
16
+ 3. Collect and evaluate results
17
+ 4. Select/merge based on objective criteria
18
18
 
19
- **평가 기준**:
20
- - 완성도 (Completeness): 요구사항 충족도
21
- - 창의성 (Creativity): 독창적 접근
22
- - 실현 가능성 (Feasibility): 구현 가능성
19
+ **Evaluation Criteria**:
20
+ - Completeness: Requirement fulfillment
21
+ - Creativity: Original approach
22
+ - Feasibility: Implementation possibility
23
23
 
24
24
  ### Sequential Handoff Mode
25
25
 
26
- **목표**: AI 강점을 순차적으로 활용
26
+ **Goal**: Leverage each AI's strengths sequentially
27
27
 
28
- **프로세스**:
29
- 1. 체인 순서에 따라 작업 전달
30
- 2. 단계에서 핵심 컨텍스트 유지
31
- 3. 이전 결과물을 기반으로 개선
32
- 4. 최종 통합 결과물 생성
28
+ **Process**:
29
+ 1. Pass work according to chain order
30
+ 2. Maintain core context at each step
31
+ 3. Improve based on previous results
32
+ 4. Generate final integrated result
33
33
 
34
- **핸드오프 포함 사항**:
35
- - 현재까지의 핵심 성과
36
- - 유지해야 결정사항
37
- - 다음 단계 명확한 지시
34
+ **Handoff Inclusions**:
35
+ - Key achievements so far
36
+ - Decisions to maintain
37
+ - Clear instructions for next step
38
38
 
39
39
  ### Debate Mode
40
40
 
41
- **목표**: 다양한 관점에서 최적 결론 도출
41
+ **Goal**: Derive optimal conclusions from various perspectives
42
42
 
43
- **토론 진행 시**:
44
- 1. 입장을 공정하게 대변
45
- 2. 증거 기반 논증 요구
46
- 3. 반박은 건설적으로
47
- 4. 공통점과 차이점 명확히
43
+ **When Conducting Debate**:
44
+ 1. Fairly represent each position
45
+ 2. Require evidence-based arguments
46
+ 3. Rebuttals should be constructive
47
+ 4. Clarify common points and differences
48
48
 
49
- **결론 도출 시**:
50
- - 합의점 우선 정리
51
- - 미합의 사항 명시
52
- - 실행 가능한 권장사항 제시
49
+ **When Deriving Conclusions**:
50
+ - Prioritize summarizing consensus points
51
+ - Specify non-consensus items
52
+ - Present actionable recommendations
53
53
 
54
- ## 공통 원칙
54
+ ## Common Principles
55
55
 
56
- ### 공정성
57
- - 특정 모델 편향 없이 평가
58
- - 객관적 기준 적용
59
- - 결과의 근거 명시
56
+ ### Fairness
57
+ - Evaluate without bias toward specific models
58
+ - Apply objective criteria
59
+ - Specify rationale for results
60
60
 
61
- ### 효율성
62
- - 토큰 예산 준수
63
- - 중복 작업 최소화
64
- - 명확한 작업 분배
61
+ ### Efficiency
62
+ - Adhere to token budget
63
+ - Minimize duplicate work
64
+ - Clear task distribution
65
65
 
66
- ### 통합성
67
- - 결과물 일관성 유지
68
- - 충돌 사항 해결
69
- - 최종 결과물 완성도 확보
66
+ ### Integration
67
+ - Maintain consistency between results
68
+ - Resolve conflicts
69
+ - Ensure final result completeness
70
70
 
71
- ## 출력 형식
71
+ ## Output Format
72
72
 
73
- ### 협업 결과 리포트
73
+ ### Collaboration Result Report
74
74
  ```markdown
75
75
  # Collaboration Report
76
76
 
77
77
  ## Mode: [parallel/sequential/debate]
78
- ## Task: [작업 설명]
78
+ ## Task: [Task description]
79
79
 
80
80
  ## Participants
81
- - [AI 1]: [역할/관점]
82
- - [AI 2]: [역할/관점]
81
+ - [AI 1]: [Role/Perspective]
82
+ - [AI 2]: [Role/Perspective]
83
83
 
84
84
  ## Results Summary
85
- [ AI의 핵심 기여]
85
+ [Key contribution from each AI]
86
86
 
87
87
  ## Evaluation
88
88
  | Metric | AI 1 | AI 2 |
89
89
  |--------|------|------|
90
90
 
91
91
  ## Final Decision
92
- [선택/병합 결과]
92
+ [Selection/Merge result]
93
93
 
94
94
  ## Rationale
95
- [결정 근거]
95
+ [Decision rationale]
96
96
  ```
97
97
 
98
- ## 금지 사항
99
-
100
- - 근거 없는 모델 우대
101
- - 불완전한 결과물 선택
102
- - 핵심 정보 누락
103
- - 비교 없이 임의 선택
104
-
105
-
106
-
98
+ ## Prohibited Actions
107
99
 
100
+ - Model favoritism without evidence
101
+ - Selecting incomplete results
102
+ - Omitting key information
103
+ - Arbitrary selection without comparison
@@ -1,77 +1,77 @@
1
1
  # Auto-Checkpoint Skill
2
2
 
3
- 자동 체크포인트 생성 스마트 롤백 스킬
3
+ Automatic checkpoint creation and smart rollback skill
4
4
 
5
- ## 개요
5
+ ## Overview
6
6
 
7
- 작업 안전망을 위한 자동 체크포인트 시스템:
8
- - 조건 기반 자동 체크포인트 생성
9
- - 스마트 롤백 제안 실행
10
- - 파이프라인 분기 지원
7
+ Automatic checkpoint system for work safety:
8
+ - Condition-based automatic checkpoint creation
9
+ - Smart rollback suggestion and execution
10
+ - Pipeline forking support
11
11
 
12
- ## 트리거
12
+ ## Trigger
13
13
 
14
- ### 자동 트리거
15
- - 5 태스크 완료마다
16
- - 100 이상 파일 변경
17
- - 파괴적 작업 감지
18
- - 30 간격 (변경 있을 )
19
- - 스테이지 완료
14
+ ### Auto Trigger
15
+ - Every 5 completed tasks
16
+ - When 100+ lines of file changes
17
+ - When destructive action detected
18
+ - 30 minute intervals (when changes exist)
19
+ - On stage completion
20
20
 
21
- ### 수동 트리거
22
- - `/checkpoint` 명령어
21
+ ### Manual Trigger
22
+ - `/checkpoint` command
23
23
 
24
- ## 기능
24
+ ## Features
25
25
 
26
- ### 1. 자동 체크포인트 (trigger.md)
27
- - 조건 감지 체크포인트 생성
28
- - 메타데이터 기록
29
- - Git 태그 연동
26
+ ### 1. Auto Checkpoint (trigger.md)
27
+ - Condition detection and checkpoint creation
28
+ - Metadata recording
29
+ - Git tag integration
30
30
 
31
- ### 2. 스마트 롤백 (rollback.md)
32
- - 에러 분석 관련 체크포인트 찾기
33
- - 부분 롤백 지원 (파일/함수/스테이지)
34
- - 롤백 미리보기
31
+ ### 2. Smart Rollback (rollback.md)
32
+ - Error analysis and finding related checkpoints
33
+ - Partial rollback support (file/function/stage)
34
+ - Rollback preview
35
35
 
36
- ### 3. 파이프라인 분기
37
- - 여러 접근법 동시 탐색
38
- - 분기 비교 병합
36
+ ### 3. Pipeline Forking
37
+ - Explore multiple approaches simultaneously
38
+ - Fork comparison and merge
39
39
 
40
- ## 파일 구조
40
+ ## File Structure
41
41
 
42
42
  ```
43
43
  auto-checkpoint/
44
- ├── README.md # 파일
45
- ├── trigger.md # 체크포인트 트리거 가이드
46
- ├── rollback.md # 롤백 가이드
44
+ ├── README.md # This file
45
+ ├── trigger.md # Checkpoint trigger guide
46
+ ├── rollback.md # Rollback guide
47
47
  └── prompts/
48
- └── CLAUDE.md # AI 지침
48
+ └── CLAUDE.md # AI instructions
49
49
  ```
50
50
 
51
- ## 설정
51
+ ## Configuration
52
52
 
53
- - `config/auto_checkpoint.yaml` - 자동 체크포인트
54
- - `config/smart_rollback.yaml` - 스마트 롤백
55
- - `config/pipeline_forking.yaml` - 파이프라인 분기
53
+ - `config/auto_checkpoint.yaml` - Auto checkpoint
54
+ - `config/smart_rollback.yaml` - Smart rollback
55
+ - `config/pipeline_forking.yaml` - Pipeline forking
56
56
 
57
- ## 사용 예시
57
+ ## Usage Examples
58
58
 
59
59
  ```bash
60
- # 수동 체크포인트 생성
60
+ # Manual checkpoint creation
61
61
  /checkpoint --name "feature-complete"
62
62
 
63
- # 롤백 제안 보기
63
+ # View rollback suggestions
64
64
  /restore --suggest
65
65
 
66
- # 특정 체크포인트로 롤백
66
+ # Rollback to specific checkpoint
67
67
  /restore --checkpoint "stage_06_complete_20240120"
68
68
 
69
- # 파이프라인 분기
70
- /fork --reason "아키텍처 대안 탐색"
69
+ # Pipeline fork
70
+ /fork --reason "Architecture alternative exploration"
71
71
  ```
72
72
 
73
- ## 저장 위치
73
+ ## Storage Locations
74
74
 
75
- - 체크포인트: `state/checkpoints/`
76
- - 분기: `state/forks/`
77
- - 롤백 히스토리: `state/rollback_history/`
75
+ - Checkpoints: `state/checkpoints/`
76
+ - Forks: `state/forks/`
77
+ - Rollback history: `state/rollback_history/`