القائمة
5 expert personas debate proposed changes before implementation. Catches architectural, security, performance, and UX issues early. Use before major features or risky refactors.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Unity engine adapter: .asmdef graph, Roslyn class diagrams with Unity stereotypes (MonoBehaviour, ScriptableObject, DOTS), UPM package deps, and C4 architecture views
Cocos Creator 3.8.7 playable-ad parameter discovery + implementation. Scans project config files (constant.ts, *Config.ts) AND all Canvas UI nodes via MCP, reads scene values for defaults, wires bindings, auto-assigns. Modes: --quick, --standard, --deep, --exhaustive, --auto.
Compare CK updates against GameKit baseline, suggest which changes to incorporate.
Answer technical questions with context-aware skill activation. Use for 'how does X work', 'what is the best way to', 'explain this pattern' queries.
Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking about context window, token budget, or agent context sizing.
Implement features end-to-end: plan, code, test, review via registry agents. Use for 'implement X', 'build Y feature', 'add Z functionality'. Handles full workflow.
| name | omg-predict |
| description | 5 expert personas debate proposed changes before implementation. Catches architectural, security, performance, and UX issues early. Use before major features or risky refactors. |
This skill was ported from upstream reference material. Interpret command names, paths, and agent-routing guidance as Codex/Oh My Game Kit equivalents. Prefer active Codex tools and local project instructions over Codex-specific mechanics when they conflict.
5 expert personas review a proposed change and debate its merits, risks, and alternatives.
omg-predict "Add caching layer to API responses"
| # | Persona | Focus | Looks For |
|---|---|---|---|
| 1 | Architect | System design, scalability, coupling | Over-engineering, tight coupling, wrong abstractions, missing extensibility |
| 2 | Security | Attack surface, data flow, trust boundaries | Auth bypass, injection, data exposure, insufficient logging |
| 3 | Performance | Bottlenecks, memory, latency | N+1 queries, unnecessary allocations, cache invalidation issues |
| 4 | UX/DX | User/developer impact, edge cases | Breaking changes, poor error messages, confusing APIs |
| 5 | Devil's Advocate | Assumptions, alternatives, hidden costs | "What if this is the wrong approach entirely?" |
## Prediction: {change description}
### Architect (Risk: 3/5)
- Concern: ...
- Mitigation: ...
### Security (Risk: 2/5)
- Concern: ...
- Mitigation: ...
### Performance (Risk: 4/5)
- Concern: ...
- Mitigation: ...
### UX/DX (Risk: 1/5)
- Concern: ...
- Mitigation: ...
### Devil's Advocate (Risk: 3/5)
- Alternative: ...
- Hidden cost: ...
### Consensus
- **Overall Risk: 2.6/5**
- **Recommendation: GO with conditions**
- **Top 3 concerns to address:**
1. ...
2. ...
3. ...
| Trap | Reality |
|---|---|
| "This change is too simple for a debate" | Simple changes with hidden complexity cause the worst incidents. |
| "We already discussed this" | Discussion ≠ structured risk assessment. |
| "The user wants to start coding" | 5 minutes of prediction saves 5 hours of debugging. |
Sub-agent forking: see .agents/skills/omg-architecture/references/fork-hygiene.md.