skill-zipper-v1

Restructure Claude Code skills to reduce token consumption and improve trigger accuracy.

5|Updated Jun 5, 2026
One-click install
npx skills add https://github.com/VincentJiang06/skills --skill skill-zipper-v1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-zipper-v1
Source: https://github.com/VincentJiang06/skills/tree/main/archive/skill-zipper-v1
Command: npx skills add https://github.com/VincentJiang06/skills --skill skill-zipper-v1

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tiktoken, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the problem of bloated, unreliable Claude Code skills that waste tokens, trigger incorrectly, or contain vague rules. It restructures an existing skill to be leaner, more reliable, and better-triggering without changing its actual behavior or losing any content.

Core Features & Use Cases

  • Lossless Restructuring: Every line of the original skill is preserved or explicitly classified as a hardening rewrite, ensuring zero content loss.
  • Token Optimization: Moves content from the always-loaded SKILL.md body into on-demand rules/ and references/ files, reducing per-invocation token costs.
  • Trigger Accuracy: Rewrites the frontmatter description to fix mis-triggering, ensuring the skill loads exactly when needed.
  • Use Case: You have a 3,000-token skill that triggers on irrelevant turns and costs too much context. Use this Skill to compress it to 1,200 always-loaded tokens with precise trigger phrases.

Quick Start

Use the skill-zipper-v1 skill to restructure the attached skill directory for token efficiency and better triggering.

Frequently Asked Questions about skill-zipper-v1

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

FAQPage Schema
How do I reduce token consumption in Claude Code skills without losing content?

You can reduce token consumption by applying progressive disclosure, which moves content from the always-loaded SKILL.md body into on-demand rules and references files, cutting per-invocation context costs without losing content.

What is progressive disclosure for Claude Code skills?

Progressive disclosure is a restructuring technique that encapsulates skill content into on-demand rules and references files, ensuring only essential instructions load initially to minimize token waste while preserving full content accessibility.

Why does my Claude Code skill trigger on irrelevant turns?

Your skill triggers incorrectly due to vague or ambiguous frontmatter descriptions. Rewriting the frontmatter description hardens ambiguous instructions and fixes mis-triggering, ensuring the skill loads exactly when needed.

How do I verify lossless compression when restructuring skills?

You verify lossless compression by using diff and token measurement scripts. Every line of the original skill is preserved or explicitly classified as a hardening rewrite, ensuring zero content loss during structural audits.

Does restructuring skills require the tiktoken dependency?

Yes, restructuring skills requires the tiktoken dependency to accurately measure token counts before and after compression, verifying that the progressive disclosure strategy effectively reduces per-invocation context costs.

When should I perform a structural audit on my Claude Code skill?

You should perform a structural audit when your skill is too long, has vague rules, fails to trigger correctly, or wastes context. This identifies opportunities for lossless compression and trigger accuracy improvements.