Context Engineering
技能 已验证 活跃Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.
To empower users to master context engineering and maintain efficient, high-quality AI sessions by providing a structured approach to managing information flow and token budgets.
功能
- Mastering four operations of context engineering: Write, Select, Compress, Isolate
- Strategies for managing token budgets and compaction
- Guidance on context partitioning using subagents and isolation methods
- Detailed patterns and anti-patterns for effective context management
使用场景
- Maintaining long AI coding sessions without context degradation
- Optimizing AI responses by precisely selecting relevant information
- Implementing durable memory and knowledge persistence for AI sessions
- Reducing AI session costs and latency through efficient token usage
非目标
- Providing specific AI model implementations
- Managing external tool execution beyond context impact
- Replacing core AI model capabilities
安装
请先添加 Marketplace
/plugin marketplace add rohitg00/pro-workflow/plugin install pro-workflow@pro-workflow质量评分
已验证类似扩展
Context Engineering Advisor
98Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
Context Optimization
100This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.
Context Compression
100This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Init
100创建或优化存储库的 AGENTS.md 文件，提供最少、高信号的说明，涵盖代理无法从代码库推断的不可发现的编码约定、工具怪癖、工作流偏好和项目特定规则。在为新存储库设置代理说明或 Claude 配置时，当现有的 AGENTS.md 文件过长、通用或过时，当代理反复犯可避免的错误，或当存储库工作流发生变化且需要修剪代理配置时使用。应用可发现性过滤器—省略 Claude 可从 README、代码、配置或目录结构中学到的任何内容—并应用质量门，以验证每行是否仍然准确且具有操作意义。
Horizon Track
100Track long-horizon objectives across multiple sessions with milestone checkpoints, progress persistence, and drift detection
Treat
100修剪臃肿的会话，附带处方。移除进度标记、陈旧读取、重复内容等。