Btw

/btw - By-The-Way Suggestion Collector

작업 중 "이거 스킬로 만들면 좋겠다", "이 패턴 자동화하면 좋겠다" 등의 개선 제안을 즉시 기록하고 관리하는 도구.

Commands

/btw {suggestion} - Record a suggestion

1. Read .bkit/btw-suggestions.json (create if not exists)
2. Generate next ID: btw-NNN (zero-padded, sequential)
3. Create suggestion entry:

   jsonCopy code
   {
     "id": "btw-001",
     "timestamp": "ISO-8601",
     "suggestion": "{user input}",
     "context": {
       "file": "{current working file if identifiable}",
       "pdcaPhase": "{current PDCA phase from .bkit-memory.json or null}",
       "feature": "{current feature or null}"
     },
     "category": "auto-detect",
     "status": "pending",
     "promotedTo": null,
     "priority": null,
     "teamContext": {
       "isTeamSession": false,
       "phase": "{PDCA phase or null}",
       "role": "{teammate role that discovered this, or 'user'}",
       "pattern": "{orchestration pattern or null}"
     }
   }
   

4. Auto-detect category from suggestion text:
   • skill-request: mentions "skill", "스킬", "자동화", "automate"
   • bug-pattern: mentions "bug", "버그", "오류", "error", "fix"
   • improvement: mentions "개선", "improve", "better", "refactor"
   • documentation: mentions "문서", "doc", "설명", "explain"
   • general: default
5. Update stats.total count
6. Respond: "Recorded btw-{NNN}: {truncated suggestion}. Use /btw list to view all."

/btw list - List all suggestions

1. Read .bkit/btw-suggestions.json
2. Display table:

   Copy code
   ID       | Status   | Category       | Suggestion (truncated)
   ---------|----------|----------------|----------------------
   btw-001  | pending  | skill-request  | @Flow 모델에서 옵션 목록을 자동...
   btw-002  | promoted | improvement    | DataProxy 패턴에 검증 로직을...
   

3. Show summary: Total: N | Pending: N | Promoted: N | Dismissed: N

/btw analyze - Analyze suggestions for skill candidates

1. Read all pending suggestions from .bkit/btw-suggestions.json
2. Group by category and find patterns:
   • Cluster similar suggestions (keyword overlap)
   • Count frequency of similar topics
   • Identify suggestions that map to existing bkit skills vs. new skill needs
3. For each skill candidate:
   • Estimate skill classification: workflow vs capability
   • Suggest skill name and description
   • Reference source suggestion IDs
4. Output analysis:

   Copy code
   Skill Candidates from /btw Analysis
   =====================================
   
   1. [NEW SKILL] hunikflow-validation (capability)
      Based on: btw-001, btw-005, btw-008
      Frequency: 3 mentions
      Description: Validation pattern guide for @Flow entities
   
   2. [EXISTING SKILL ENHANCEMENT] code-review
      Based on: btw-003
      Suggestion: Add DataProxy-specific review rules
   

5. Save analysis timestamp to stats.lastAnalyzed

/btw promote {id} - Promote suggestion to skill creation

1. Find suggestion by ID in .bkit/btw-suggestions.json
2. Validate status is "pending" (cannot promote already promoted/dismissed)
3. Update suggestion:
   • status: "promoted"
   • promotedTo: skill name (derived from suggestion)
4. Trigger skill-create workflow with context from the suggestion:
   • Pass suggestion text as skill description seed
   • Pass context (file, feature) as project context
5. Respond: "Promoted btw-{id} -> skill-create pipeline. Run /skill-create to continue."

/btw stats - Show statistics

1. Read .bkit/btw-suggestions.json
2. Calculate and display:

   Copy code
   /btw Statistics
   ===============
   Total suggestions: 12
   By status: pending=8, promoted=3, dismissed=1
   By category: skill-request=5, improvement=4, bug-pattern=2, general=1
   Promotion rate: 25.0%
   Last analyzed: 2026-03-13T10:00:00Z
   Top keywords: @Flow(3), DataProxy(2), validation(2)
   

Data File: .bkit/btw-suggestions.json

Initialize with this structure if file does not exist:

jsonCopy code
{
  "version": "1.0",
  "suggestions": [],
  "stats": {
    "total": 0,
    "promoted": 0,
    "dismissed": 0,
    "lastAnalyzed": null
  }
}

Category Auto-Detection Rules

Integration Points

• PDCA Context: Reads .bkit-memory.json for current phase/feature
• skill-create: /btw promote triggers skill-create workflow
• skill-needs-extractor: /btw analyze results feed into gap analysis
• CTO Team: Phase transition triggers btw summary (see below)

CTO Team Integration

When /btw is used during a CTO Team session (/pdca team):

Auto-Detection

• Check if team session is active via .bkit/runtime/agent-state.json
• If active: set teamContext.isTeamSession = true and populate phase/role/pattern
• If not active: set teamContext.isTeamSession = false (default behavior)

Phase Transition Hook

CTO Lead automatically reads btw-suggestions.json at every phase transition:

• 0 pending: Silent skip (no output, no turns spent)
• 1+ pending: Brief summary (top 3, category counts) in 1-2 turns
• CTO does NOT auto-promote — user decides via /btw promote {id}

Session End

cto-stop.js hook outputs btw stats at session end:

• Total suggestions collected during session
• Category breakdown
• Promotion rate

teamContext Field

Added to each suggestion entry when recorded during a team session:

jsonCopy code
"teamContext": {
  "isTeamSession": true,
  "phase": "do",
  "role": "user",
  "pattern": "swarm"
}

This enables /btw analyze to group suggestions by PDCA phase and identify phase-specific patterns.