Guides a new developer through five staged challenge sets covering architecture, domain, patterns, and hardening. Use when onboarding contributors.
Scanned 5/28/2026
Install to Claude Code
npx -y skills add athola/claude-night-market --skill onboard --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Onboard?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/athola-onboard)More formats (shields.io, HTML) on the badges page.
---
name: onboard
description: Guides a new developer through five staged challenge sets covering architecture, domain, patterns, and hardening. Use when onboarding contributors.
model_hint: standard
---
# Guided Onboarding
Walk a new developer through the codebase in structured stages.
## Stages
| Stage | Focus | Categories | Difficulty |
|-------|-------|------------|------------|
| 1 | Big picture | architecture, data_flow | 1-2 |
| 2 | Core domain | business_logic | 2-3 |
| 3 | Interfaces | api_contract, data_flow | 3 |
| 4 | Patterns | pattern, dependency | 3-4 |
| 5 | Hardening | error_handling, business_logic | 4-5 |
## Steps
1. Load onboarding progress
2. Show current stage and progress summary
3. Present 5 challenges from current stage
4. Enable hints on first attempt
5. Track mastery (correct twice = mastered)
6. Check advancement (80% across 10+ challenges)
7. Report progress
## Graduation
After stage 5, the developer enters the regular gauntlet.
Answer history carries over.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
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', ...