skills.rest
MoeGolibrary
MoeGolibraryOFFICIAL
Explore all skills by this author →
WebsiteGitHub

writing-system-documents

Write and review compact system-level documents for persistent Agent context.

Updated Aug 23, 2026
Search Tags:#documentation#writing guide#system prompt#token optimization#claudemd#agent context
One-click install
npx skills add https://github.com/MoeGolibrary/moego-ai-plugin --skill writing-system-documents
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-system-documents
Source: https://github.com/MoeGolibrary/moego-ai-plugin/tree/main/skills/writing-system-documents
Command: npx skills add https://github.com/MoeGolibrary/moego-ai-plugin --skill writing-system-documents

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you write and review system-level documents that are designed to be compact and efficient, residing in an Agent's context window throughout an entire session, thereby minimizing token costs.

Core Features & Use Cases

  • Token Cost Optimization: Ensures every line of system documentation justifies its token expenditure.
  • Clarity and Specificity: Promotes writing clear, actionable rules using verb-object structures and avoiding vague language.
  • Use Case: Crafting precise system prompts, role definitions, or project rules that an AI agent must adhere to consistently during a long-running task.

Quick Start

Use the writing-system-documents skill to help write a new CLAUDE.md file.

Frequently Asked Questions about writing-system-documents

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

FAQPage Schema
How do I write a CLAUDE.md file that minimizes token costs?▼

To write a CLAUDE.md file that minimizes token costs, enforce principles of token cost justification, density, and specificity so every line justifies its persistent context window expenditure.

What is a compact-immune system prompt for agent context?▼

A compact-immune system prompt is a dense, efficient document residing in an agent's context window throughout a session, designed to maintain clarity and minimize token usage.

How do I create project rules and role definitions for a long-running AI task?▼

Creating project rules and role definitions for long-running AI tasks involves writing clear, actionable rules using verb-object structures to ensure consistent agent adherence without vague language.

Does this approach help review existing system documents for token efficiency?▼

Yes, this approach reviews existing system-level documents by evaluating them against guardrails, proximity, and verifiability principles to ensure they remain token cost-efficient and clear.

What is the best way to format persistent AI agent instructions?▼

The best way to format persistent AI agent instructions is using compact-immune system-level documents that enforce verifiability and guardrails, ensuring high density and actionable specificity.

Related Skills

Explore More Content & Communication Skills→
rogsmerogsme

gsd-new-project

Initialize and plan a GSD project with essential documentation.

Community
Intermediate
bthillerupbthillerup
1

filesystem-context

Offload large tool outputs to files for dynamic context discovery.

Community
Intermediate
kinnerkarmanishkinnerkarmanish

assemble

Assemble tiered L0, L1, and L2 contexts into a token-counted bundle.

Community
Intermediate
daffy0208daffy0208
34

Skill Name

Generate semantic metadata and toxicity reports from Skill Unit documentation.

Community
Basic