Agent Skills › jjongguet/oh-my-product › context-optimize

context-optimize

GitHub

分析并优化提示词和上下文文件，通过去重、压缩、优先级排序和修剪提升信噪比，降低 Token 消耗。

skills/context-optimize/SKILL.md jjongguet/oh-my-product

Trigger Scenarios

上下文文件过大或焦点分散会话上下文臃肿包含过时信息 Token 预算紧张需节省资源

Install

npx skills add jjongguet/oh-my-product --skill context-optimize -g -y

More Options

Use without installing

npx skills use jjongguet/oh-my-product@context-optimize

指定 Agent (Claude Code)

npx skills add jjongguet/oh-my-product --skill context-optimize -a claude-code -g -y

安装 repo 全部 skill

npx skills add jjongguet/oh-my-product --all -g -y

预览 repo 内 skill

npx skills add jjongguet/oh-my-product --list

SKILL.md

Frontmatter

{
    "name": "context-optimize",
    "aliases": [
        "\/context-optimize",
        "optimize context",
        "compress context"
    ],
    "description": "Analyze and optimize context for signal-to-noise ratio — deduplicate, compress, prioritize, and prune.",
    "primaryRole": "optimizer"
}

Context Optimize Skill (oh-my-product)

Optimize prompt and context files for maximum signal density.

Use when

GEMINI.md or context files have grown large and unfocused
Session context feels bloated with stale information
Token budget is tight and every token must count
After a major feature addition that expanded context

Workflow

Audit: Measure current context size and composition
Score: Rate each section for signal density (useful / total tokens)
Identify issues: Flag duplicates, stale entries, verbose sections
Propose changes: Show diff of recommended optimizations
Apply: With user approval, apply the optimizations

Optimization Strategies

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

Metrics

Before: 4,200 tokens | Signal: 62% | Redundancy: 18% | Stale: 12%
After:  2,800 tokens | Signal: 89% | Redundancy: 3%  | Stale: 0%
Savings: 33% token reduction