seokan-jeong/team-shinchan:help
skills/help/SKILL.md
Use when you need guidance on Team-Shinchan agents, skills, or memory system.
$ install --global
skillsauthnpx skillsauth add seokan-jeong/team-shinchan team-shinchan:helpInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 5, 2026, 5:04 AM218.6s1 file scanned
SKILL.md
- name:
- team-shinchan:help
- description:
- Use when you need guidance on Team-Shinchan agents, skills, or memory system.
- user-invocable:
- true
Team-Shinchan Help
Commands
| Command | Description |
|---------|-------------|
| /team-shinchan:start | Start a new task — requirements, planning, execution, review all handled |
| /team-shinchan:resume | Resume an interrupted workflow from where it left off |
| /team-shinchan:autopilot | Autonomous execution from idea to working code |
| /team-shinchan:review | Code review with Action Kamen |
| /team-shinchan:version | Show current/published version and changelog diff |
| /team-shinchan:help | This guide |
Quick Start
/team-shinchan:start Add user authentication
Shinnosuke orchestrates 15 agents through 4 stages:
- Requirements — Nene interviews you, Misae checks risks
- Planning — Nene creates phased plan with acceptance criteria
- Execution — Bo/Aichan/Buriburi/Masao implement, Action Kamen reviews each phase
- Completion — Documentation, retrospective, final verification
What Happens Automatically
- Project Ontology — knowledge graph auto-built on first session, updated incrementally
- Workflow Guard — blocks code edits during planning, enforces stage transitions
- Security Hook — blocks secrets, destructive git, sensitive files
- Budget Guard — token budget with 80%/100% alerts
- Agent Narration — Shinnosuke announces every delegation and result
- Session Wrap — auto-summary on session end
15 Agents
| Layer | Agents | |-------|--------| | Orchestration | Shinnosuke (conductor), Himawari (large projects), Midori (debates) | | Execution | Bo (code), Kazama (deep work) | | Specialists | Aichan (frontend), Buriburi (backend), Masao (devops) | | Advisors | Hiroshi (architecture), Nene (planning), Misae (requirements), Action Kamen (review) | | Utility | Shiro (explorer), Masumi (docs), Ume (vision) |
All agents are invoked automatically by Shinnosuke. You just describe your task.
Keyword Map
Use these trigger words to reach the right skill quickly. Korean equivalents are listed alongside each entry.
| Trigger (EN) | Trigger (KO) | Skill |
|-------------|-------------|-------|
| fix, debug, error | 버그, 디버그 | systematic-debugging |
| plan, design | 계획, 설계 | plan |
| implement, add, feature | 구현, 추가 | implement |
| review, check | 리뷰, 검토 | review |
| test | 테스트 | test-driven-development |
| release | 릴리스 | release |
| version | 버전 | version |
| analyze, understand | 분석, 이해 | analyze |
Related Skills
seokan-jeong/team-shinchan:fierce-option-panel
testing
VerifiedTrustedCommunity
Default-on interview option-quality panel — N diverse generators produce structure-free options, a SelfCheckGPT majority-vote consensus filters hallucinations, a SteerConf cautious-confidence judge scores survivors, and a deterministic top-K is returned. Workflow tier; the single fierce-* skill that is ON by default.
8SKILL.mdUpdated Jun 11, 2026
seokan-jeong/team-shinchan:fierce-review
development
VerifiedTrustedCommunity
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.
8SKILL.mdUpdated Jun 5, 2026
seokan-jeong/team-shinchan:fierce-ralph
data-ai
VerifiedTrustedCommunity
Deterministic loop-until-done for high-stakes long-running tasks — a worker/verifier loop the script bounds by iteration cap, token budget, and stagnation, closed by an Action-Kamen gate. Opt-in main-loop Workflow tier.
8SKILL.mdUpdated Jun 5, 2026
seokan-jeong/team-shinchan:fierce-debate
testing
VerifiedTrustedCommunity
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.
8SKILL.mdUpdated Jun 5, 2026