메뉴
Use when you need to view or manage learned memories and preferences.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when you have a large-scale, multi-phase project requiring orchestrated execution.
Use when you need persistent looping until a task is fully complete.
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, completeness + interaction critics, and a deterministic 3-lens rubric judge panel. Opt-in main-loop Workflow tier.
Use when the user wants to review accumulated skill feedback, verdict trends, or improvement candidates collected during Stage 4 retrospectives. Trigger on "show skill feedback", "스킬 피드백 보여줘", or finding which skills need /writing-skills work.
Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.
| name | team-shinchan:memories |
| description | Use when you need to view or manage learned memories and preferences. |
| user-invocable | false |
View what Team-Shinchan has learned about this project.
/team-shinchan:memories # View all learnings
/team-shinchan:memories pattern # Filter by category
/team-shinchan:memories search auth # Search for keyword
Read .shinchan-docs/learnings.md
If file doesn't exist:
📚 [Memories] No learnings yet.
Start teaching with:
/team-shinchan:learn "Your learning here"
Or just work - I learn automatically after tasks!
Full view (/memories):
📚 [Memories] {N} learnings stored
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔹 PREFERENCE TIER ({count}) — always loaded
• Use Zustand over Redux [high] #state-management
• Prefer functional components [high] #react
🔸 PROCEDURAL TIER ({count}) — project-scoped
📌 PATTERNS ({count})
• Early returns for validation [high] #typescript
• Repository pattern for data access [medium] #architecture
📌 CONVENTIONS ({count})
• Use pnpm, not npm [high] #tooling
• camelCase for functions [high] #naming
📌 MISTAKES ({count})
• Always null-check before .map() [high] #typescript
📌 DECISIONS ({count})
• JWT with refresh token rotation [high] #auth
🔧 TOOL TIER ({count}) — execution-stage only
• Always pass --json to gh CLI [high] #github
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
💡 These learnings are applied automatically.
🗑️ Use /team-shinchan:forget to remove outdated ones.
Filter by tier (/memories --tier preference): Show only entries matching the specified tier.
Filtered view (/memories pattern):
📚 [Memories] Showing: patterns
• Early returns for validation [high]
Context: Learned from UserService refactor
• Repository pattern for data access [medium]
Context: Applied during database migration
Found 2 patterns.
Search view (/memories search auth):
📚 [Memories] Search: "auth"
1. [decision] JWT with refresh token rotation
Tags: #auth #security #jwt
2. [pattern] Auth middleware pattern
Tags: #auth #middleware
Found 2 results.
| Category | Description | Icon |
|---|---|---|
preference | User preferences | 💜 |
pattern | Reusable code patterns | 🔷 |
convention | Project conventions | 📏 |
mistake | Errors to avoid | ⚠️ |
decision | Architecture decisions | 🏗️ |
insight | General insights | 💡 |
.shinchan-docs/learnings.md/forget