Persistently loops until task is fully complete. Used for "until done", "complete it", "dont stop" requests.
Scanned 2/12/2026
Install via CLI
openskills install seokan-jeong/team-shinchan---
name: team-shinchan:ralph
description: Persistently loops until task is fully complete. Used for "until done", "complete it", "dont stop" requests.
user-invocable: true
---
# EXECUTE IMMEDIATELY
**Do not read further. Execute this Task NOW:**
```typescript
Task(
subagent_type="team-shinchan:kazama",
model="opus",
prompt=`/team-shinchan:ralph has been invoked.
## Persistent Execution Until Complete Mode
Don't stop until complete:
1. Check TODO list
2. Execute next task (delegate to appropriate agent)
3. Verify results
4. On failure → Analyze cause → Retry
5. On success → Next task
6. All tasks complete → Action Kamen final verification
7. Verification fails → Fix and re-verify
## Completion Conditions
Complete only when all conditions met:
- All TODO list items completed
- Build/tests pass
- Action Kamen review approved
**If conditions not met, automatically continue!**
User request: ${args || '(Task to complete)'}
`
)
```
**STOP HERE. The above Task handles everything.**
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...