菜单
Analyze and optimize context for signal-to-noise ratio — deduplicate, compress, prioritize, and prune.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Run a focused Gemini advisor prompt and save the result as a reusable artifact.
Autonomously drive a feature from clarified objective through implementation and verification.
Safely stop active work, note what was interrupted, and preserve resumable context.
Configure notification delivery for Slack, Discord, or Telegram.
Summarize token usage and cost-style session metrics across daily, weekly, or monthly windows.
Reproduce or inspect a failure, isolate root cause, and validate a fix.
| name | context-optimize |
| aliases | ["/context-optimize","optimize context","compress context"] |
| primaryRole | optimizer |
| description | Analyze and optimize context for signal-to-noise ratio — deduplicate, compress, prioritize, and prune. |
Optimize prompt and context files for maximum signal density.
| Strategy | Description | Risk |
|---|---|---|
| Deduplicate | Remove repeated instructions across layers | Low |
| Compress | Shorten verbose sections preserving meaning | Low |
| Prioritize | Move high-signal content earlier in context | Low |
| Prune | Remove stale or irrelevant entries | Medium |
| Restructure | Improve formatting for model parsing | Low |
Before: 4,200 tokens | Signal: 62% | Redundancy: 18% | Stale: 12%
After: 2,800 tokens | Signal: 89% | Redundancy: 3% | Stale: 0%
Savings: 33% token reduction
oh-my-product contexts follow this priority hierarchy:
Optimization targets layers 2-5 (layer 1 is immutable).
/omp:optimize — quick context optimization command/omp:memory compact — compact memory entries specifically