Structured Context Compressor

Structured Context Compressor

Use this skill when a free-form summary is too lossy and you need a reliable continuation artifact.

Use It For

• long coding conversations
• session handoff
• agent-to-agent continuation
• preserving user intent under context pressure

Quick Start

Render the standard template:

python3 {baseDir}/scripts/render_template.py

Then apply the prompt in references/prompt-template.md.

Nine Sections

1. primary request and intent 2. key technical concepts 3. files and code sections 4. errors and fixes 5. problem solving 6. all user messages 7. pending tasks 8. current work 9. next aligned step

Highest-Value Rule

Preserve all user messages or an accurate equivalent. Do not compress away the corrections that changed the direction of work.

Supporting Files

• Prompt template: references/prompt-template.md
• Source notes: references/source-notes.md
• Helper script: python3 {baseDir}/scripts/render_template.py

CC Context Compressor

structured-context-compressor is a portable continuation-summary skill for long coding sessions.

Instead of a vague free-form summary, it produces a nine-part artifact that preserves request, files, errors, user messages, pending work, current work, and the next aligned step.

Best For

• long coding conversations
• agent handoff
• continuation after context pressure
• preserving user corrections and constraints

Included Files

• SKILL.md
• references/prompt-template.md
• references/source-notes.md
• scripts/render_template.py

Quick Start

python3 ./scripts/render_template.py

Then fill the generated structure using the workflow from SKILL.md.

Host Fit

• Claude Code: strong fit
• Codex: strong fit
• OpenClaw: strong fit

Portable Prompt Template

Create a structured continuation summary for a long conversation.

Return exactly these sections:
1. Primary request and intent
2. Key technical concepts
3. Files and code sections
4. Errors and fixes
5. Problem solving
6. All user messages
7. Pending tasks
8. Current work
9. Next aligned step

Rules:
- preserve user intent precisely
- include all user messages or an accurate condensed equivalent
- keep the next step aligned to the most recent explicit request
- if the current work is unclear, say that explicitly rather than guessing

Source Notes

This skill was derived from these Claude Code areas:

• src/services/compact/prompt.ts
• src/services/compact/compact.ts
• src/query.ts

Portable extraction decisions:

• keep the nine-section structure
• keep the emphasis on user-message preservation
• drop host-specific cache-editing and transcript-boundary mechanics