strategic-compact

Suggest manual context compaction at logical workflow phase transitions.

Updated Mar 11, 2026

Search Tags:#context management #productivity #prompt engineering #session management #ai workflow #compaction

Ready to run

npx skills add https://github.com/yzlin/supa-opencode --skill strategic-compact-yzlin

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: strategic-compact
Source: https://github.com/yzlin/supa-opencode/tree/main/skills/strategic-compact
Command: npx skills add https://github.com/yzlin/supa-opencode --skill strategic-compact-yzlin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill prevents the loss of crucial context during long AI sessions by suggesting manual context compaction at logical workflow intervals, rather than relying on arbitrary auto-compaction.

Core Features & Use Cases

Strategic Compaction: Prompts users to manually compact context at key transition points (e.g., after research, before implementation).
Phase Awareness: Understands task phases to avoid compacting mid-operation.
Use Case: After completing a detailed research phase for a new feature, this skill will prompt you to manually compact the research notes before you begin writing the implementation plan, ensuring the plan is not diluted by excessive research data.

Quick Start

Use the strategic-compact skill to suggest manual context compaction when you are transitioning from research to planning.

Frequently Asked Questions about strategic-compact

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I prevent context loss during long AI workflow sessions?▼

To prevent context loss during long AI workflow sessions, trigger manual context compaction at logical phase transitions instead of relying on arbitrary auto-compaction. This preserves crucial information by compacting research notes before starting implementation plans.

When should I manually compact context in a multi-phase project?▼

You should manually compact context in a multi-phase project at key transition points, such as after completing research and before writing an implementation plan. Triggering compaction suggestions based on tool call thresholds ensures you do not interrupt complex mid-operation tasks.

Why does auto-compaction interrupt complex AI operations?▼

Auto-compaction interrupts complex AI operations because it triggers arbitrarily based on context window limits rather than logical workflow intervals. This arbitrary timing causes the system to lose critical information mid-operation during multi-phase projects.

What is the best way to manage context across task phases in prompt engineering?▼

The best way to manage context across task phases in prompt engineering is to use strategic compaction. This approach maintains a clean and relevant context by prompting manual compaction when transitioning between phases, preventing excessive data from diluting your next steps.

Can I trigger context compaction based on tool call thresholds?▼

Yes, you can trigger context compaction based on tool call thresholds. This skill monitors tool call counts and phase transitions to prompt manual compaction suggestions, ensuring context is preserved without losing critical information mid-operation.