Guide for using Team-Shinchan plugin's agents, skills, and memory system. Use when you need help.
Scanned 2/12/2026
Install via CLI
Skills Directoryopenskills install seokan-jeong/team-shinchan---
name: team-shinchan:help
description: Guide for using Team-Shinchan plugin's agents, skills, and memory system. Use when you need help.
user-invocable: true
---
# Help Skill
## Agent Team
### Orchestration
| Character | Role | Description |
|-----------|------|-------------|
| Shinnosuke | Orchestrator | Task analysis and delegation |
| Himawari | Atlas | Complex task decomposition |
### Execution
| Character | Role | Description |
|-----------|------|-------------|
| Bo | Executor | Code writing/modification |
| Kazama | Hephaestus | Complex implementation |
### Specialists
| Character | Role | Description |
|-----------|------|-------------|
| Aichan | Frontend | UI/UX development |
| Bunta | Backend | Server/API development |
| Masao | DevOps | Infrastructure/deployment |
### Advisors (Read-only)
| Character | Role | Description |
|-----------|------|-------------|
| Hiroshi | Oracle | Architecture advice |
| Nene | Planner | Strategic planning |
| Misae | Metis | Requirements analysis |
| Action Kamen | Reviewer | Code review |
### Exploration (Read-only)
| Character | Role | Description |
|-----------|------|-------------|
| Shiro | Explorer | Fast code search |
| Masumi | Librarian | Documentation search |
| Ume | Multimodal | Image analysis |
## Skills List
| Skill | Trigger | Description |
|-------|---------|-------------|
| `/ultrawork` | fast, parallel, ulw | Parallel execution |
| `/ralph` | until done, complete | Loop until complete |
| `/autopilot` | auto, automatically | Autonomous execution |
| `/plan` | plan, design | Planning |
| `/analyze` | analyze, debug | Deep analysis |
| `/deepsearch` | find, search | Code search |
| `/debate` | debate, opinion, compare | Agent debate |
| `/memories` | - | View memories |
| `/learn` | - | Add learning |
| `/forget` | - | Delete memory |
## Memory System
Team-Shinchan gets smarter with use:
- Automatically learns patterns, preferences, mistakes
- Applies learnings to future tasks
- `/memories` to view learnings
- `/learn` to manually add learnings
No comments yet. Be the first to comment!
Create Mermaid diagrams for flowcharts, sequences, ERDs, and
Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.
Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".
Review a pull request or contribution deeply, explain it tutorial-style for a maintainer, and produce a polished report artifact such as HTML or Markdown. Use when asked to analyze a PR, explain a contributor's design decisions, compare it with similar systems, or prepare a merge recommendation.
Generate the stable Paperclip release changelog at releases/vYYYY.MDD.P.md by reading commits, changesets, and merged PR context since the last stable tag.
