claude-symphony 0.0.1 → 0.0.3

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 (150) hide show
  1. package/README.md +16 -12
  2. package/assets/claude_symphony.webp +0 -0
  3. package/assets/claude_symphony_ascii.txt +8 -0
  4. package/bin/create.js +80 -69
  5. package/package.json +3 -2
  6. package/template/.claude/commands/benchmark.md +32 -32
  7. package/template/.claude/commands/brainstorm.md +33 -33
  8. package/template/.claude/commands/checkpoint.md +42 -42
  9. package/template/.claude/commands/codex.md +52 -52
  10. package/template/.claude/commands/collaborate.md +47 -47
  11. package/template/.claude/commands/context.md +77 -77
  12. package/template/.claude/commands/deploy.md +50 -50
  13. package/template/.claude/commands/fork.md +46 -46
  14. package/template/.claude/commands/gemini.md +43 -43
  15. package/template/.claude/commands/handoff.md +42 -42
  16. package/template/.claude/commands/implement.md +42 -42
  17. package/template/.claude/commands/init-project.md +25 -25
  18. package/template/.claude/commands/next.md +67 -67
  19. package/template/.claude/commands/planning.md +38 -38
  20. package/template/.claude/commands/qa.md +47 -47
  21. package/template/.claude/commands/refactor.md +50 -50
  22. package/template/.claude/commands/research.md +31 -31
  23. package/template/.claude/commands/restore.md +53 -53
  24. package/template/.claude/commands/run-stage.md +45 -45
  25. package/template/.claude/commands/stages.md +49 -49
  26. package/template/.claude/commands/status.md +41 -41
  27. package/template/.claude/commands/tasks.md +33 -33
  28. package/template/.claude/commands/test.md +45 -45
  29. package/template/.claude/commands/ui-ux.md +31 -31
  30. package/template/.claude/commands/validate.md +81 -81
  31. package/template/.claude/hooks/ai-selector.sh +39 -39
  32. package/template/.claude/hooks/auto-checkpoint.sh +30 -30
  33. package/template/.claude/hooks/output-validator.sh +45 -45
  34. package/template/.claude/hooks/post-stage.sh +28 -28
  35. package/template/.claude/hooks/pre-stage.sh +47 -47
  36. package/template/.claude/hooks/session-start.sh +27 -27
  37. package/template/.claude/hooks/statusline.sh +24 -24
  38. package/template/.claude/hooks/stop.sh +26 -26
  39. package/template/.claude/settings.json +32 -32
  40. package/template/.claude/skills/ai-collaboration/README.md +31 -31
  41. package/template/.claude/skills/ai-collaboration/debate.md +66 -66
  42. package/template/.claude/skills/ai-collaboration/parallel.md +34 -34
  43. package/template/.claude/skills/ai-collaboration/prompts/CLAUDE.md +59 -63
  44. package/template/.claude/skills/auto-checkpoint/README.md +46 -46
  45. package/template/.claude/skills/auto-checkpoint/prompts/CLAUDE.md +68 -72
  46. package/template/.claude/skills/auto-checkpoint/rollback.md +95 -95
  47. package/template/.claude/skills/auto-checkpoint/trigger.md +37 -37
  48. package/template/.claude/skills/context-compression/README.md +69 -69
  49. package/template/.claude/skills/context-compression/analyze.md +74 -74
  50. package/template/.claude/skills/context-compression/compress.md +103 -103
  51. package/template/.claude/skills/context-compression/prompts/compression.md +78 -78
  52. package/template/.claude/skills/output-validator/README.md +33 -33
  53. package/template/.claude/skills/output-validator/prompts/CLAUDE.md +74 -78
  54. package/template/.claude/skills/output-validator/validate.md +76 -76
  55. package/template/.claude/skills/smart-handoff/README.md +35 -35
  56. package/template/.claude/skills/smart-handoff/extract.md +42 -42
  57. package/template/.claude/skills/smart-handoff/prompts/CLAUDE.md +52 -54
  58. package/template/.claude/skills/smart-handoff/summarize.md +55 -55
  59. package/template/.claude/skills/stage-transition/README.md +50 -50
  60. package/template/.claude/skills/stage-transition/handoff-gen.md +89 -89
  61. package/template/.claude/skills/stage-transition/prompts/transition.md +74 -74
  62. package/template/.claude/skills/stage-transition/validate.md +41 -41
  63. package/template/CLAUDE.md +334 -335
  64. package/template/config/ai_benchmarking.yaml +22 -22
  65. package/template/config/ai_collaboration.yaml +18 -18
  66. package/template/config/ai_logging.yaml +50 -50
  67. package/template/config/auto_checkpoint.yaml +32 -32
  68. package/template/config/context.yaml +20 -20
  69. package/template/config/git.yaml +51 -51
  70. package/template/config/handoff_intelligence.yaml +23 -23
  71. package/template/config/mcp_fallbacks.yaml +71 -71
  72. package/template/config/memory_integration.yaml +23 -23
  73. package/template/config/model_enforcement.yaml +53 -53
  74. package/template/config/models.yaml +24 -24
  75. package/template/config/output_validation.yaml +44 -44
  76. package/template/config/pipeline.yaml +25 -25
  77. package/template/config/pipeline_forking.yaml +40 -40
  78. package/template/config/qa_logging.yaml +67 -67
  79. package/template/config/smart_rollback.yaml +48 -48
  80. package/template/config/stage_personas.yaml +154 -154
  81. package/template/config/workflow.yaml +16 -16
  82. package/template/scripts/ai-benchmark.sh +41 -41
  83. package/template/scripts/codex-wrapper.sh +32 -32
  84. package/template/scripts/context-manager.sh +136 -136
  85. package/template/scripts/create-checkpoint.sh +34 -34
  86. package/template/scripts/gemini-wrapper.sh +31 -31
  87. package/template/scripts/init-project.sh +40 -40
  88. package/template/scripts/list-stages.sh +30 -30
  89. package/template/scripts/next-stage.sh +67 -67
  90. package/template/scripts/output-validate.sh +2 -2
  91. package/template/scripts/pipeline-fork.sh +68 -68
  92. package/template/scripts/pre-run-check.sh +84 -84
  93. package/template/scripts/restore-checkpoint.sh +50 -50
  94. package/template/scripts/run-stage.sh +44 -44
  95. package/template/scripts/show-status.sh +30 -30
  96. package/template/scripts/smart-handoff.sh +70 -70
  97. package/template/stages/01-brainstorm/CLAUDE.md +70 -74
  98. package/template/stages/01-brainstorm/README.md +54 -54
  99. package/template/stages/01-brainstorm/config.yaml +18 -18
  100. package/template/stages/01-brainstorm/prompts/collaboration.md +24 -24
  101. package/template/stages/01-brainstorm/prompts/ideation.md +41 -41
  102. package/template/stages/01-brainstorm/prompts/persona.md +50 -50
  103. package/template/stages/01-brainstorm/prompts/requirements.md +55 -55
  104. package/template/stages/01-brainstorm/prompts/validation.md +28 -28
  105. package/template/stages/01-brainstorm/templates/ideas.md +47 -47
  106. package/template/stages/01-brainstorm/templates/requirements_analysis.md +61 -61
  107. package/template/stages/02-research/CLAUDE.md +72 -76
  108. package/template/stages/02-research/config.yaml +12 -12
  109. package/template/stages/02-research/prompts/collaboration.md +29 -29
  110. package/template/stages/02-research/prompts/feasibility.md +38 -38
  111. package/template/stages/02-research/prompts/market_analysis.md +29 -29
  112. package/template/stages/02-research/prompts/tech_stack.md +34 -34
  113. package/template/stages/02-research/prompts/validation.md +29 -29
  114. package/template/stages/03-planning/CLAUDE.md +88 -92
  115. package/template/stages/03-planning/config.yaml +10 -10
  116. package/template/stages/03-planning/prompts/architecture.md +43 -43
  117. package/template/stages/03-planning/prompts/collaboration.md +34 -34
  118. package/template/stages/03-planning/prompts/validation.md +34 -34
  119. package/template/stages/04-ui-ux/CLAUDE.md +68 -72
  120. package/template/stages/04-ui-ux/config.yaml +5 -5
  121. package/template/stages/04-ui-ux/prompts/collaboration.md +35 -35
  122. package/template/stages/04-ui-ux/prompts/validation.md +30 -30
  123. package/template/stages/05-task-management/CLAUDE.md +81 -85
  124. package/template/stages/05-task-management/config.yaml +17 -17
  125. package/template/stages/05-task-management/prompts/collaboration.md +30 -30
  126. package/template/stages/05-task-management/prompts/validation.md +33 -33
  127. package/template/stages/05-task-management/templates/notion_integration.md +70 -70
  128. package/template/stages/05-task-management/templates/parallel_groups.yaml +64 -64
  129. package/template/stages/05-task-management/templates/task_schema.yaml +33 -33
  130. package/template/stages/06-implementation/CLAUDE.md +117 -121
  131. package/template/stages/06-implementation/config.yaml +10 -10
  132. package/template/stages/06-implementation/prompts/collaboration.md +29 -29
  133. package/template/stages/06-implementation/prompts/validation.md +36 -36
  134. package/template/stages/07-refactoring/CLAUDE.md +120 -124
  135. package/template/stages/07-refactoring/config.yaml +11 -11
  136. package/template/stages/07-refactoring/prompts/collaboration.md +36 -36
  137. package/template/stages/07-refactoring/prompts/validation.md +40 -40
  138. package/template/stages/08-qa/CLAUDE.md +80 -84
  139. package/template/stages/08-qa/config.yaml +7 -7
  140. package/template/stages/08-qa/prompts/collaboration.md +34 -34
  141. package/template/stages/08-qa/prompts/validation.md +41 -41
  142. package/template/stages/09-testing/CLAUDE.md +86 -90
  143. package/template/stages/09-testing/config.yaml +10 -10
  144. package/template/stages/09-testing/prompts/collaboration.md +38 -38
  145. package/template/stages/09-testing/prompts/validation.md +41 -41
  146. package/template/stages/10-deployment/CLAUDE.md +86 -90
  147. package/template/stages/10-deployment/config.yaml +11 -11
  148. package/template/stages/10-deployment/prompts/collaboration.md +37 -37
  149. package/template/stages/10-deployment/prompts/validation.md +54 -54
  150. package/template/stages/10-deployment/templates/github-actions-cd.yaml +1 -1
@@ -1,9 +1,9 @@
1
1
  #!/bin/bash
2
- # session-start.sh - 세션 시작 시 자동 복구
2
+ # session-start.sh - Session start auto-recovery
3
3
  # claude-symphony workflow pipeline
4
4
  #
5
- # SessionStart hook: Claude Code 세션 시작/재개 시 실행
6
- # /compact 저장된 스냅샷이 있으면 자동으로 컨텍스트 복구 안내
5
+ # SessionStart hook: Runs when Claude Code session starts/resumes
6
+ # If snapshot exists from /compact, provides auto context recovery guidance
7
7
 
8
8
  set -e
9
9
 
@@ -12,64 +12,64 @@ TRIGGER_FILE="$PROJECT_ROOT/state/context/auto-trigger.json"
12
12
  CONTEXT_DIR="$PROJECT_ROOT/state/context"
13
13
  PROGRESS_FILE="$PROJECT_ROOT/state/progress.json"
14
14
 
15
- # 컨텍스트 디렉토리 확인
15
+ # Ensure context directory
16
16
  mkdir -p "$CONTEXT_DIR"
17
17
 
18
- # jq 필요
18
+ # jq required
19
19
  if ! command -v jq &> /dev/null; then
20
20
  exit 0
21
21
  fi
22
22
 
23
- # 1. 트리거 파일 확인 - compact 실행되었는지
23
+ # 1. Check trigger file - if compact was executed
24
24
  if [ ! -f "$TRIGGER_FILE" ]; then
25
- exit 0 # 복구 필요 없음
25
+ exit 0 # No recovery needed
26
26
  fi
27
27
 
28
28
  COMPACT_SCHEDULED=$(jq -r '.compact_scheduled // false' "$TRIGGER_FILE" 2>/dev/null || echo "false")
29
29
  if [ "$COMPACT_SCHEDULED" != "true" ]; then
30
- exit 0 # compact 예정되지 않았음
30
+ exit 0 # compact not scheduled
31
31
  fi
32
32
 
33
- # 2. 최근 스냅샷 찾기
33
+ # 2. Find latest snapshot
34
34
  LATEST_SNAPSHOT=$(ls -1t "$CONTEXT_DIR"/auto-snapshot-*.md 2>/dev/null | head -1)
35
35
  if [ -z "$LATEST_SNAPSHOT" ]; then
36
- # 스냅샷 없음 - 트리거 파일 정리
36
+ # No snapshot - cleanup trigger file
37
37
  rm -f "$TRIGGER_FILE"
38
38
  exit 0
39
39
  fi
40
40
 
41
- # 3. 현재 스테이지 정보
41
+ # 3. Get current stage info
42
42
  CURRENT_STAGE="none"
43
43
  if [ -f "$PROGRESS_FILE" ]; then
44
44
  CURRENT_STAGE=$(jq -r '.current_stage // "none"' "$PROGRESS_FILE" 2>/dev/null || echo "none")
45
45
  fi
46
46
 
47
- # 4. 복구 컨텍스트 생성 (Claude에게 전달)
47
+ # 4. Create recovery context (passed to Claude)
48
48
  RECOVERY_CONTEXT=$(cat << EOF
49
49
 
50
50
  ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
51
- 🔄 세션 복구 - 자동 /compact 후 재시작
51
+ 🔄 Session Recovery - Restart after auto /compact
52
52
  ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
53
53
 
54
- ## 복구 정보
55
- - 스냅샷: $(basename "$LATEST_SNAPSHOT")
56
- - 스테이지: $CURRENT_STAGE
57
- - 저장 시간: $(jq -r '.timestamp // "unknown"' "$TRIGGER_FILE" 2>/dev/null)
54
+ ## Recovery Information
55
+ - Snapshot: $(basename "$LATEST_SNAPSHOT")
56
+ - Stage: $CURRENT_STAGE
57
+ - Save time: $(jq -r '.timestamp // "unknown"' "$TRIGGER_FILE" 2>/dev/null)
58
58
 
59
- ## 스냅샷 내용
59
+ ## Snapshot Contents
60
60
  $(cat "$LATEST_SNAPSHOT" 2>/dev/null | head -50)
61
61
 
62
- ## 복구 지침
63
- 1. 스냅샷 내용을 참고하여 작업 컨텍스트 파악
64
- 2. stages/$CURRENT_STAGE/CLAUDE.md 확인
65
- 3. 중단된 작업부터 재개
62
+ ## Recovery Instructions
63
+ 1. Review snapshot contents above to understand work context
64
+ 2. Check stages/$CURRENT_STAGE/CLAUDE.md
65
+ 3. Resume from interrupted work
66
66
 
67
67
  ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
68
68
  EOF
69
69
  )
70
70
 
71
- # 5. JSON 출력 (Claude에게 컨텍스트 전달)
72
- # additionalContext를 통해 Claude가 복구 정보를 받음
71
+ # 5. JSON output (passing context to Claude)
72
+ # Claude receives recovery info through additionalContext
73
73
  cat << EOF
74
74
  {
75
75
  "hookSpecificOutput": {
@@ -79,12 +79,12 @@ cat << EOF
79
79
  }
80
80
  EOF
81
81
 
82
- # 6. 트리거 파일 정리 (복구 완료 표시)
82
+ # 6. Cleanup trigger file (mark recovery complete)
83
83
  jq '. + {"recovered": true, "recovery_time": "'"$(date -Iseconds)"'"}' \
84
84
  "$TRIGGER_FILE" > "$TRIGGER_FILE.tmp" && mv "$TRIGGER_FILE.tmp" "$TRIGGER_FILE"
85
85
 
86
- # 일정 시간 트리거 파일 삭제 (다음 세션에서 중복 복구 방지)
87
- # 백그라운드에서 5 후 삭제
86
+ # Delete trigger file after some time (prevent duplicate recovery in next session)
87
+ # Delete in background after 5 minutes
88
88
  (sleep 300 && rm -f "$TRIGGER_FILE" 2>/dev/null) &
89
89
 
90
90
  exit 0
@@ -1,9 +1,9 @@
1
1
  #!/bin/bash
2
- # statusline.sh - Claude Code Statusline API를 통한 실시간 컨텍스트 모니터링
2
+ # statusline.sh - Real-time context monitoring via Claude Code Statusline API
3
3
  # claude-symphony workflow pipeline
4
4
  #
5
- # Claude Code ~300ms마다 JSON stdin으로 전달합니다.
6
- # 스크립트는 remaining_percentage 분석하여 임계값 도달 자동 조치를 수행합니다.
5
+ # Claude Code passes JSON to stdin every ~300ms.
6
+ # This script analyzes remaining_percentage and performs auto actions when thresholds are reached.
7
7
 
8
8
  set -e
9
9
 
@@ -12,69 +12,69 @@ STATE_FILE="$PROJECT_ROOT/state/context/auto-trigger.json"
12
12
  PROGRESS_FILE="$PROJECT_ROOT/state/progress.json"
13
13
  CONTEXT_DIR="$PROJECT_ROOT/state/context"
14
14
 
15
- # 컨텍스트 디렉토리 확인
15
+ # Ensure context directory
16
16
  mkdir -p "$CONTEXT_DIR"
17
17
 
18
- # stdin에서 JSON 읽기
18
+ # Read JSON from stdin
19
19
  input=$(cat)
20
20
 
21
- # JSON 파싱 (jq 필요)
21
+ # JSON parsing (jq required)
22
22
  if ! command -v jq &> /dev/null; then
23
- echo "[CTX] jq 필요"
23
+ echo "[CTX] jq required"
24
24
  exit 0
25
25
  fi
26
26
 
27
- # 컨텍스트 데이터 추출
27
+ # Extract context data
28
28
  REMAINING=$(echo "$input" | jq -r '.context_window.remaining_percentage // 100' 2>/dev/null || echo "100")
29
29
  USED=$(echo "$input" | jq -r '.context_window.used_percentage // 0' 2>/dev/null || echo "0")
30
30
  MODEL=$(echo "$input" | jq -r '.model.display_name // "Claude"' 2>/dev/null || echo "Claude")
31
31
  CONTEXT_SIZE=$(echo "$input" | jq -r '.context_window.context_window_size // 200000' 2>/dev/null || echo "200000")
32
32
 
33
- # 현재 스테이지 가져오기
33
+ # Get current stage
34
34
  if [ -f "$PROGRESS_FILE" ]; then
35
35
  CURRENT_STAGE=$(jq -r '.current_stage // "none"' "$PROGRESS_FILE" 2>/dev/null || echo "none")
36
36
  else
37
37
  CURRENT_STAGE="none"
38
38
  fi
39
39
 
40
- # 숫자 비교를 위한 정수 변환
40
+ # Convert to integer for numeric comparison
41
41
  REMAINING_INT=$(printf "%.0f" "$REMAINING" 2>/dev/null || echo "100")
42
42
 
43
- # 상태 색상 결정
44
- # 임계값: 60% 경고, 50% 자동저장, 40% 크리티컬
43
+ # Determine status and color
44
+ # Thresholds: 60% warning, 50% auto-save, 40% critical
45
45
  if [ "$REMAINING_INT" -le 40 ]; then
46
- # 40% 이하: 크리티컬 - /clear 권고
46
+ # 40% or below: Critical - recommend /clear
47
47
  STATUS_ICON="🔴"
48
48
  STATUS_TEXT="CTX≤40%"
49
49
  NEEDS_ACTION="critical"
50
50
  elif [ "$REMAINING_INT" -le 50 ]; then
51
- # 50% 이하: 자동 스냅샷 트리거
51
+ # 50% or below: Auto snapshot trigger
52
52
  STATUS_ICON="⚠️"
53
53
  STATUS_TEXT="CTX≤50%"
54
54
  NEEDS_ACTION="warning"
55
55
  elif [ "$REMAINING_INT" -le 60 ]; then
56
- # 60% 이하: 경고 표시
56
+ # 60% or below: Warning display
57
57
  STATUS_ICON="⚡"
58
58
  STATUS_TEXT="CTX≤60%"
59
59
  NEEDS_ACTION="notice"
60
60
  else
61
- # 정상
61
+ # Normal
62
62
  STATUS_ICON="✓"
63
63
  STATUS_TEXT=""
64
64
  NEEDS_ACTION="none"
65
65
  fi
66
66
 
67
- # 50% 이하일 때 자동 조치
67
+ # Auto action when 50% or below
68
68
  if [ "$NEEDS_ACTION" = "warning" ] || [ "$NEEDS_ACTION" = "critical" ]; then
69
- # 이미 트리거 되었는지 확인 (중복 방지)
69
+ # Check if already triggered (prevent duplicates)
70
70
  ALREADY_TRIGGERED=false
71
71
  if [ -f "$STATE_FILE" ]; then
72
72
  TRIGGERED=$(jq -r '.triggered // false' "$STATE_FILE" 2>/dev/null || echo "false")
73
73
  TRIGGER_REMAINING=$(jq -r '.remaining // 100' "$STATE_FILE" 2>/dev/null || echo "100")
74
74
 
75
- # 같은 레벨에서 이미 트리거 되었으면 스킵
75
+ # Skip if already triggered at same level
76
76
  if [ "$TRIGGERED" = "true" ]; then
77
- # 낮은 레벨로 떨어지면 다시 트리거
77
+ # Re-trigger if dropped to lower level
78
78
  if [ "$REMAINING_INT" -lt "$TRIGGER_REMAINING" ]; then
79
79
  ALREADY_TRIGGERED=false
80
80
  else
@@ -84,7 +84,7 @@ if [ "$NEEDS_ACTION" = "warning" ] || [ "$NEEDS_ACTION" = "critical" ]; then
84
84
  fi
85
85
 
86
86
  if [ "$ALREADY_TRIGGERED" = false ]; then
87
- # 트리거 상태 기록
87
+ # Record trigger state
88
88
  cat > "$STATE_FILE" << EOF
89
89
  {
90
90
  "triggered": true,
@@ -95,19 +95,19 @@ if [ "$NEEDS_ACTION" = "warning" ] || [ "$NEEDS_ACTION" = "critical" ]; then
95
95
  }
96
96
  EOF
97
97
 
98
- # 자동 스냅샷 생성 (백그라운드)
98
+ # Create auto snapshot (background)
99
99
  if [ -x "$PROJECT_ROOT/scripts/context-manager.sh" ]; then
100
100
  "$PROJECT_ROOT/scripts/context-manager.sh" --auto-compact "$NEEDS_ACTION" 2>/dev/null &
101
101
  fi
102
102
  fi
103
103
  fi
104
104
 
105
- # 컨텍스트가 충분해지면 (70% 이상) 트리거 상태 리셋
105
+ # Reset trigger state when context is sufficient (70% or above)
106
106
  if [ "$REMAINING_INT" -ge 70 ] && [ -f "$STATE_FILE" ]; then
107
107
  rm -f "$STATE_FILE"
108
108
  fi
109
109
 
110
- # 상태줄 출력
110
+ # Output statusline
111
111
  if [ -n "$STATUS_TEXT" ]; then
112
112
  echo "[$MODEL] $STATUS_ICON $STATUS_TEXT ${REMAINING_INT}% | Stage: $CURRENT_STAGE"
113
113
  else
@@ -1,9 +1,9 @@
1
1
  #!/bin/bash
2
- # stop.sh - Claude 응답 완료 컨텍스트 자동 관리
2
+ # stop.sh - Auto context management after Claude response
3
3
  # claude-symphony workflow pipeline
4
4
  #
5
- # Stop hook: Claude 응답이 완료된 실행됨
6
- # 컨텍스트가 50% 이하이면 자동으로 /compact 실행
5
+ # Stop hook: Runs after Claude response completes
6
+ # If context is 50% or below, automatically runs /compact
7
7
 
8
8
  set -e
9
9
 
@@ -13,23 +13,23 @@ COOLDOWN_FILE="$PROJECT_ROOT/state/context/.last-compact"
13
13
  CONTEXT_DIR="$PROJECT_ROOT/state/context"
14
14
  PROGRESS_FILE="$PROJECT_ROOT/state/progress.json"
15
15
 
16
- # 쿨다운 시간 () - 5
16
+ # Cooldown time (seconds) - 5 minutes
17
17
  COOLDOWN_SECONDS=300
18
18
 
19
- # 컨텍스트 디렉토리 확인
19
+ # Ensure context directory
20
20
  mkdir -p "$CONTEXT_DIR"
21
21
 
22
- # jq 필요
22
+ # jq required
23
23
  if ! command -v jq &> /dev/null; then
24
24
  exit 0
25
25
  fi
26
26
 
27
- # stdin에서 hook 데이터 읽기
27
+ # Read hook data from stdin
28
28
  input=$(cat)
29
29
 
30
- # 1. 트리거 파일 확인 (statusline.sh에서 생성)
30
+ # 1. Check trigger file (created by statusline.sh)
31
31
  if [ ! -f "$TRIGGER_FILE" ]; then
32
- exit 0 # 트리거 없음 - 정상 상태
32
+ exit 0 # No trigger - normal state
33
33
  fi
34
34
 
35
35
  TRIGGERED=$(jq -r '.triggered // false' "$TRIGGER_FILE" 2>/dev/null || echo "false")
@@ -40,65 +40,65 @@ fi
40
40
  REMAINING=$(jq -r '.remaining // 100' "$TRIGGER_FILE" 2>/dev/null || echo "100")
41
41
  LEVEL=$(jq -r '.level // "warning"' "$TRIGGER_FILE" 2>/dev/null || echo "warning")
42
42
 
43
- # 50% 이하가 아니면 스킵
43
+ # Skip if not 50% or below
44
44
  if [ "$REMAINING" -gt 50 ]; then
45
45
  exit 0
46
46
  fi
47
47
 
48
- # 2. 쿨다운 확인 (5분 재실행 방지)
48
+ # 2. Check cooldown (prevent re-run within 5 minutes)
49
49
  if [ -f "$COOLDOWN_FILE" ]; then
50
50
  LAST_COMPACT=$(cat "$COOLDOWN_FILE" 2>/dev/null || echo "0")
51
51
  NOW=$(date +%s)
52
52
  ELAPSED=$((NOW - LAST_COMPACT))
53
53
 
54
54
  if [ "$ELAPSED" -lt "$COOLDOWN_SECONDS" ]; then
55
- # 쿨다운 - 스킵
55
+ # In cooldown - skip
56
56
  REMAINING_COOLDOWN=$((COOLDOWN_SECONDS - ELAPSED))
57
57
  exit 0
58
58
  fi
59
59
  fi
60
60
 
61
- # 3. tmux 세션 확인
61
+ # 3. Check tmux session
62
62
  if [ -z "$TMUX" ]; then
63
- # tmux 세션이 아님 - 수동 안내만 제공
63
+ # Not in tmux session - provide manual guidance only
64
64
  echo ""
65
65
  echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
66
- echo "⚠️ 컨텍스트 ${REMAINING}% - /compact 실행을 권장합니다"
66
+ echo "⚠️ Context ${REMAINING}% - Running /compact is recommended"
67
67
  echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
68
68
  exit 0
69
69
  fi
70
70
 
71
- # 4. 스냅샷 저장 확인 (이미 statusline.sh에서 저장했어야 함)
71
+ # 4. Verify snapshot saved (should be saved by statusline.sh already)
72
72
  LATEST_SNAPSHOT=$(ls -1t "$CONTEXT_DIR"/auto-snapshot-*.md 2>/dev/null | head -1)
73
73
  if [ -z "$LATEST_SNAPSHOT" ]; then
74
- # 스냅샷 없음 - 먼저 저장
74
+ # No snapshot - save first
75
75
  "$PROJECT_ROOT/scripts/context-manager.sh" --auto-compact "$LEVEL" 2>/dev/null || true
76
76
  LATEST_SNAPSHOT=$(ls -1t "$CONTEXT_DIR"/auto-snapshot-*.md 2>/dev/null | head -1)
77
77
  fi
78
78
 
79
- # 스냅샷이 여전히 없으면 안전을 위해 스킵
79
+ # Skip for safety if snapshot still doesn't exist
80
80
  if [ -z "$LATEST_SNAPSHOT" ]; then
81
81
  echo ""
82
- echo "⚠️ 스냅샷 저장 실패 - /compact 자동 실행 취소"
82
+ echo "⚠️ Snapshot save failed - Auto /compact cancelled"
83
83
  exit 0
84
84
  fi
85
85
 
86
- # 5. 사전 알림
86
+ # 5. Pre-notification
87
87
  echo ""
88
88
  echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
89
- echo "🔄 컨텍스트 ${REMAINING}% - 자동 /compact 실행 중..."
90
- echo " 스냅샷: $(basename "$LATEST_SNAPSHOT")"
89
+ echo "🔄 Context ${REMAINING}% - Running auto /compact..."
90
+ echo " Snapshot: $(basename "$LATEST_SNAPSHOT")"
91
91
  echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
92
92
 
93
- # 6. 쿨다운 타이머 기록
93
+ # 6. Record cooldown timer
94
94
  date +%s > "$COOLDOWN_FILE"
95
95
 
96
- # 7. 트리거 파일에 compact 예정 표시
96
+ # 7. Mark compact scheduled in trigger file
97
97
  jq '. + {"compact_scheduled": true, "compact_time": "'"$(date -Iseconds)"'"}' \
98
98
  "$TRIGGER_FILE" > "$TRIGGER_FILE.tmp" && mv "$TRIGGER_FILE.tmp" "$TRIGGER_FILE"
99
99
 
100
- # 8. tmux send-keys /compact 실행 (현재 pane)
101
- sleep 1 # 잠시 대기 (출력이 보이도록)
100
+ # 8. Run /compact via tmux send-keys (to current pane)
101
+ sleep 1 # Brief wait (for output to be visible)
102
102
  tmux send-keys "/compact" Enter
103
103
 
104
104
  exit 0
@@ -20,129 +20,129 @@
20
20
  },
21
21
 
22
22
  "hooks_info": {
23
- "note": "실제 hooks 설정은 settings.local.json에 있음",
24
- "stop": ".claude/hooks/stop.sh - 자동 /compact",
25
- "session_start": ".claude/hooks/session-start.sh - 자동 복구"
23
+ "note": "Actual hooks settings are in settings.local.json",
24
+ "stop": ".claude/hooks/stop.sh - auto /compact",
25
+ "session_start": ".claude/hooks/session-start.sh - auto recovery"
26
26
  },
27
27
 
28
28
  "commands": {
29
29
  "init-project": {
30
- "description": " 프로젝트 초기화",
30
+ "description": "Initialize new project",
31
31
  "file": "commands/init-project.md"
32
32
  },
33
33
  "run-stage": {
34
- "description": "스테이지 실행",
34
+ "description": "Run stage",
35
35
  "file": "commands/run-stage.md"
36
36
  },
37
37
  "handoff": {
38
- "description": "핸드오프 문서 생성",
38
+ "description": "Generate handoff document",
39
39
  "file": "commands/handoff.md"
40
40
  },
41
41
  "checkpoint": {
42
- "description": "체크포인트 생성",
42
+ "description": "Create checkpoint",
43
43
  "file": "commands/checkpoint.md"
44
44
  },
45
45
  "gemini": {
46
- "description": "Gemini CLI 호출 (tmux)",
46
+ "description": "Call Gemini CLI (tmux)",
47
47
  "file": "commands/gemini.md"
48
48
  },
49
49
  "codex": {
50
- "description": "Codex CLI 호출 (tmux)",
50
+ "description": "Call Codex CLI (tmux)",
51
51
  "file": "commands/codex.md"
52
52
  },
53
53
  "status": {
54
- "description": "파이프라인 상태 확인",
54
+ "description": "Check pipeline status",
55
55
  "file": "commands/status.md"
56
56
  },
57
57
  "stages": {
58
- "description": "스테이지 목록 상세",
58
+ "description": "Stage list and details",
59
59
  "file": "commands/stages.md"
60
60
  },
61
61
  "restore": {
62
- "description": "체크포인트 복구",
62
+ "description": "Restore checkpoint",
63
63
  "file": "commands/restore.md"
64
64
  },
65
65
  "next": {
66
- "description": "다음 스테이지 전환",
66
+ "description": "Transition to next stage",
67
67
  "file": "commands/next.md"
68
68
  },
69
69
  "context": {
70
- "description": "컨텍스트 상태 관리",
70
+ "description": "Context state management",
71
71
  "file": "commands/context.md"
72
72
  },
73
73
  "brainstorm": {
74
- "description": "01-brainstorm 스테이지 시작",
74
+ "description": "Start 01-brainstorm stage",
75
75
  "file": "commands/brainstorm.md"
76
76
  },
77
77
  "research": {
78
- "description": "02-research 스테이지 시작",
78
+ "description": "Start 02-research stage",
79
79
  "file": "commands/research.md"
80
80
  },
81
81
  "planning": {
82
- "description": "03-planning 스테이지 시작",
82
+ "description": "Start 03-planning stage",
83
83
  "file": "commands/planning.md"
84
84
  },
85
85
  "ui-ux": {
86
- "description": "04-ui-ux 스테이지 시작",
86
+ "description": "Start 04-ui-ux stage",
87
87
  "file": "commands/ui-ux.md"
88
88
  },
89
89
  "tasks": {
90
- "description": "05-task-management 스테이지 시작",
90
+ "description": "Start 05-task-management stage",
91
91
  "file": "commands/tasks.md"
92
92
  },
93
93
  "implement": {
94
- "description": "06-implementation 스테이지 시작",
94
+ "description": "Start 06-implementation stage",
95
95
  "file": "commands/implement.md"
96
96
  },
97
97
  "refactor": {
98
- "description": "07-refactoring 스테이지 시작",
98
+ "description": "Start 07-refactoring stage",
99
99
  "file": "commands/refactor.md"
100
100
  },
101
101
  "qa": {
102
- "description": "08-qa 스테이지 시작",
102
+ "description": "Start 08-qa stage",
103
103
  "file": "commands/qa.md"
104
104
  },
105
105
  "test": {
106
- "description": "09-testing 스테이지 시작",
106
+ "description": "Start 09-testing stage",
107
107
  "file": "commands/test.md"
108
108
  },
109
109
  "deploy": {
110
- "description": "10-deployment 스테이지 시작",
110
+ "description": "Start 10-deployment stage",
111
111
  "file": "commands/deploy.md"
112
112
  },
113
113
  "collaborate": {
114
- "description": "Multi-AI 협업 실행",
114
+ "description": "Run Multi-AI collaboration",
115
115
  "file": "commands/collaborate.md"
116
116
  },
117
117
  "benchmark": {
118
- "description": "AI 모델 벤치마킹",
118
+ "description": "AI model benchmarking",
119
119
  "file": "commands/benchmark.md"
120
120
  },
121
121
  "fork": {
122
- "description": "파이프라인 분기 관리",
122
+ "description": "Pipeline branch management",
123
123
  "file": "commands/fork.md"
124
124
  },
125
125
  "validate": {
126
- "description": "산출물 검증 실행",
126
+ "description": "Run output validation",
127
127
  "file": "commands/validate.md"
128
128
  }
129
129
  },
130
130
 
131
131
  "skills": {
132
132
  "smart-handoff": {
133
- "description": "스마트 컨텍스트 추출 HANDOFF 생성",
133
+ "description": "Smart context extraction and HANDOFF generation",
134
134
  "directory": "skills/smart-handoff"
135
135
  },
136
136
  "ai-collaboration": {
137
- "description": "Multi-AI 협업 오케스트레이션",
137
+ "description": "Multi-AI collaboration orchestration",
138
138
  "directory": "skills/ai-collaboration"
139
139
  },
140
140
  "auto-checkpoint": {
141
- "description": "자동 체크포인트 생성",
141
+ "description": "Automatic checkpoint generation",
142
142
  "directory": "skills/auto-checkpoint"
143
143
  },
144
144
  "output-validator": {
145
- "description": "산출물 검증 품질 확인",
145
+ "description": "Output validation and quality verification",
146
146
  "directory": "skills/output-validator"
147
147
  }
148
148
  }
@@ -1,61 +1,61 @@
1
1
  # AI Collaboration Skill
2
2
 
3
- Multi-AI 협업 오케스트레이션 스킬
3
+ Multi-AI Collaboration and Orchestration Skill
4
4
 
5
- ## 개요
5
+ ## Overview
6
6
 
7
- 여러 AI 모델(Claude, Gemini, Codex) 협업시켜 나은 결과물을 생성합니다:
8
- - 병렬 실행으로 다양한 관점 확보
9
- - 순차 핸드오프로 점진적 개선
10
- - 토론 모드로 최적 결론 도출
7
+ Collaborate multiple AI models (Claude, Gemini, Codex) to generate better results:
8
+ - Gain diverse perspectives through parallel execution
9
+ - Gradual improvement through sequential handoff
10
+ - Derive optimal conclusions through debate mode
11
11
 
12
- ## 트리거
12
+ ## Trigger
13
13
 
14
- - `/collaborate` 명령어
15
- - 복잡한 태스크 감지 자동 제안
16
- - 낮은 확신도 감지
14
+ - `/collaborate` command
15
+ - Auto-suggested when complex task detected
16
+ - When low confidence detected
17
17
 
18
- ## 협업 모드
18
+ ## Collaboration Modes
19
19
 
20
- ### 1. Parallel Execution (병렬 실행)
21
- 동일 작업을 여러 AI가 동시 수행최적 결과 선택
20
+ ### 1. Parallel Execution
21
+ Multiple AIs perform the same task simultaneously Select optimal result
22
22
 
23
23
  ```bash
24
- /collaborate --mode parallel --task "아이디어 생성" --models "gemini,claude"
24
+ /collaborate --mode parallel --task "idea generation" --models "gemini,claude"
25
25
  ```
26
26
 
27
- ### 2. Sequential Handoff (순차 핸드오프)
28
- AI 릴레이로 결과물 점진적 개선
27
+ ### 2. Sequential Handoff
28
+ AI relay to gradually improve results
29
29
 
30
30
  ```bash
31
31
  /collaborate --mode sequential --chain "code_review"
32
32
  ```
33
33
 
34
- ### 3. Debate Mode (토론 모드)
35
- AI 토론으로 다양한 관점에서 최적 결론 도출
34
+ ### 3. Debate Mode
35
+ AI debate to derive optimal conclusions from various perspectives
36
36
 
37
37
  ```bash
38
- /collaborate --mode debate --topic "아키텍처 선택" --rounds 3
38
+ /collaborate --mode debate --topic "architecture selection" --rounds 3
39
39
  ```
40
40
 
41
- ## 파일 구조
41
+ ## File Structure
42
42
 
43
43
  ```
44
44
  ai-collaboration/
45
- ├── README.md # 파일
46
- ├── parallel.md # 병렬 실행 가이드
47
- ├── debate.md # 토론 모드 가이드
45
+ ├── README.md # This file
46
+ ├── parallel.md # Parallel execution guide
47
+ ├── debate.md # Debate mode guide
48
48
  └── prompts/
49
- └── CLAUDE.md # AI 지침
49
+ └── CLAUDE.md # AI instructions
50
50
  ```
51
51
 
52
- ## 설정
52
+ ## Configuration
53
53
 
54
- `config/ai_collaboration.yaml` 참조
54
+ See `config/ai_collaboration.yaml`
55
55
 
56
- ## 출력
56
+ ## Output
57
57
 
58
- - AI 결과물
59
- - 비교 분석 리포트
60
- - 최종 선택/병합 결과
61
- - `state/collaborations/` 저장
58
+ - Each AI's result
59
+ - Comparative analysis report
60
+ - Final selection/merge result
61
+ - Saved to `state/collaborations/`