ad2546

Context Optimizer

AI 智能体v1.0.0
作者:ad2546更新于 2026-05-11context-optimizer@clawhub_ad2546/context-optimizer
提示词优化上下文管理记忆增强#Context Management#Memory System

据 AlphaMoat 统计,截至 2026-10,Context Optimizer 累计下载 22,036 次、获 21 个星标,按累计下载量在本次参与排名的 10,914 个 AI 技能中排名第 1,276 位,在「AI 智能体」分类(1,632 个)中排名第 187 位。

列表默认按累计下载量排序,也可按星标排序;详情页排名按累计下载量计算。

累计下载
2.2万
星标
21
全站下载量排名
#1,276
全站前 12% · 「AI 智能体」前 12%
平台累计下载星标评论
ClawHub ↗8,41015-
SkillHub ↗2.2万21—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

提供自动压缩、按查询相关性挑选上下文、语义去重与分层记忆归档,目标是在保留关键信息的同时避免上下文溢出。压缩方式包括语义合并、按时间窗摘要与按需抽取片段。源文标注许可证为 MIT。 归档功能可能把删减的对话保存在磁盘并在以后重新放入提示词;敏感任务中关闭归档,使用前检查检索片段。

资料发布于 2026-10-27

可以用来做什么

  • 长对话接近窗口上限时压缩早期消息。
  • 按当前问题只取相关片段而不是整篇文档。

什么时候用

  • 上下文接近上限、开始丢失信息时。
  • 要在大文档里按需截取片段时。

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

这轮对话太长了,把早期消息压缩一下,保留结论和待办。
只挑出和当前问题相关的段落,不要整份文档都塞进来。

月度数据趋势

累计下载2.2万
7,1111.5万2.3万2026-03 · 累计下载 8,2172026-05 · 累计下载 1.0万2026-06 · 累计下载 1.1万2026-07 · 累计下载 1.1万2026-08 · 累计下载 1.1万2026-09 · 累计下载 1.3万2026-10 · 累计下载 2.2万26-0326-0926-10
星标21
1318222026-03 · 星标 142026-05 · 星标 212026-06 · 星标 212026-07 · 星标 212026-08 · 星标 212026-09 · 星标 212026-10 · 星标 2126-0326-0926-10

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。 该技能有同名的其他版本,调整前的数据归属当前下载量最大的这一个。

月份累计下载环比星标
2026-102.2万—21
2026-091.3万—21
2026-081.1万+2.4%21
2026-071.1万+4.1%21
2026-061.1万+4.0%21
2026-051.0万—21
2026-038,217—14

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

6.2 KB · ClawHub v1.0.0
---
name: context-optimizer
description: Advanced context management with auto-compaction and dynamic context optimization for DeepSeek's 64k context window. Features intelligent compaction (merging, summarizing, extracting), query-aware relevance scoring, and hierarchical memory system with context archive. Logs optimization events to chat.
homepage: https://github.com/clawdbot/clawdbot
metadata:
  clawdbot:
    emoji: "🧠"
    requires:
      bins: []
      npm: ["tiktoken", "@xenova/transformers"]
展开全部(共 176 行)
    install:
      - id: npm
        kind: npm
        label: Install Context Pruner dependencies
        command: "cd ~/.clawdbot/skills/context-pruner && npm install"
---

# Context Pruner

Advanced context management optimized for DeepSeek's 64k context window. Provides intelligent pruning, compression, and token optimization to prevent context overflow while preserving important information.

## Key Features

- **DeepSeek-optimized**: Specifically tuned for 64k context window
- **Adaptive pruning**: Multiple strategies based on context usage
- **Semantic deduplication**: Removes redundant information
- **Priority-aware**: Preserves high-value messages
- **Token-efficient**: Minimizes token overhead
- **Real-time monitoring**: Continuous context health tracking

## Quick Start

### Auto-compaction with dynamic context:
```javascript
import { createContextPruner } from './lib/index.js';

const pruner = createContextPruner({
  contextLimit: 64000, // DeepSeek's limit
  autoCompact: true,    // Enable automatic compaction
  dynamicContext: true, // Enable dynamic relevance-based context
  strategies: ['semantic', 'temporal', 'extractive', 'adaptive'],
  queryAwareCompaction: true, // Compact based on current query relevance
});

await pruner.initialize();

// Process messages with auto-compaction and dynamic context
const processed = await pruner.processMessages(messages, currentQuery);

// Get context health status
const status = pruner.getStatus();
console.log(`Context health: ${status.health}, Relevance scores: ${status.relevanceScores}`);

// Manual compaction when needed
const compacted = await pruner.autoCompact(messages, currentQuery);
```

### Archive Retrieval (Hierarchical Memory):
```javascript
// When something isn't in current context, search archive
const archiveResult = await pruner.retrieveFromArchive('query about previous conversation', {
  maxContextTokens: 1000,
  minRelevance: 0.4,
});

if (archiveResult.found) {
  // Add relevant snippets to current context
  const archiveContext = archiveResult.snippets.join('\n\n');
  // Use archiveContext in your prompt
  console.log(`Found ${archiveResult.sources.length} relevant sources`);
  console.log(`Retrieved ${archiveResult.totalTokens} tokens from archive`);
}
```

## Auto-Compaction Strategies

1. **Semantic Compaction**: Merges similar messages instead of removing them
2. **Temporal Compaction**: Summarizes older conversations by time windows  
3. **Extractive Compaction**: Extracts key information from verbose messages
4. **Adaptive Compaction**: Chooses best strategy based on message characteristics
5. **Dynamic Context**: Filters messages based on relevance to current query

## Dynamic Context Management

- **Query-aware Relevance**: Scores messages based on similarity to current query
- **Relevance Decay**: Relevance scores decay over time for older conversations
- **Adaptive Filtering**: Automatically filters low-relevance messages
- **Priority Integration**: Combines message priority with semantic relevance

## Hierarchical Memory System

The context archive provides a RAM vs Storage approach:

- **Current Context (RAM)**: Limited (64k tokens), fast access, auto-compacted
- **Archive (Storage)**: Larger (100MB), slower but searchable
- **Smart Retrieval**: When information isn't in current context, efficiently search archive
- **Selective Loading**: Extract only relevant snippets, not entire documents
- **Automatic Storage**: Compacted content automatically stored in archive

## Configuration

```javascript
{
  contextLimit: 64000, // DeepSeek's context window
  autoCompact: true, // Enable automatic compaction
  compactThreshold: 0.75, // Start compacting at 75% usage
  aggressiveCompactThreshold: 0.9, // Aggressive compaction at 90%
  
  dynamicContext: true, // Enable dynamic context management
  relevanceDecay: 0.95, // Relevance decays 5% per time step
  minRelevanceScore: 0.3, // Minimum relevance to keep
  queryAwareCompaction: true, // Compact based on current query relevance
  
  strategies: ['semantic', 'temporal', 'extractive', 'adaptive'],
  preserveRecent: 10, // Always keep last N messages
  preserveSystem: true, // Always keep system messages
  minSimilarity: 0.85, // Semantic similarity threshold
  
  // Archive settings
  enableArchive: true, // Enable hierarchical memory system
  archivePath: './context-archive',
  archiveSearchLimit: 10,
  archiveMaxSize: 100 * 1024 * 1024, // 100MB
  archiveIndexing: true,
  
  // Chat logging
  logToChat: true, // Log optimization events to chat
  chatLogLevel: 'brief', // 'brief', 'detailed', or 'none'
  chatLogFormat: '📊 {action}: {details}', // Format for chat messages
  
  // Performance
  batchSize: 5, // Messages to process in batch
  maxCompactionRatio: 0.5, // Maximum 50% compaction in one pass
}
```

## Chat Logging

The context optimizer can log events directly to chat:

```javascript
// Example chat log messages:
// 📊 Context optimized: Compacted 15 messages → 8 (47% reduction)
// 📊 Archive search: Found 3 relevant snippets (42% similarity)
// 📊 Dynamic context: Filtered 12 low-relevance messages

// Configure logging:
const pruner = createContextPruner({
  logToChat: true,
  chatLogLevel: 'brief', // Options: 'brief', 'detailed', 'none'
  chatLogFormat: '📊 {action}: {details}',
  
  // Custom log handler (optional)
  onLog: (level, message, data) => {
    if (level === 'info' && data.action === 'compaction') {
      // Send to chat
      console.log(`🧠 Context optimized: ${message}`);
    }
  }
});
```

## Integration with Clawdbot

Add to your Clawdbot config:

```yaml
skills:
  context-pruner:
    enabled: true
    config:
      contextLimit: 64000
      autoPrune: true
```

The pruner will automatically monitor context usage and apply appropriate pruning strategies to stay within DeepSeek's 64k limit.

「AI 智能体」分类下的热门技能

数据月份:2026-10 · 下载/星标数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。