writing-claude-directives

Official

Guide Claude with clear, safe directives.

Authored3dai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Writing precise Claude directives and system prompts can be error-prone and lead to inconsistent agent behavior. This Skill provides best-practice guidelines for creating CLAUDE.md entries, skill prompts, and governance around token efficiency and discovery optimization.

Core Features & Use Cases

  • DirectiveCrafting: guidelines for composing effective Claude directives that influence behavior without compromising safety.
  • CLAUDE.md Governance: templates and tips for documenting agent roles, systems prompts, and scope.
  • Compliance & Efficiency: techniques to minimize token usage while preserving clarity and compliance.
  • Use Case: PM defines a new skill with explicit system prompts to align agents with project goals, while keeping prompts concise.

Quick Start

To start, write a CLAUDE.md entry describing the skill’s purpose, boundaries, and examples of allowed vs disallowed prompts. Then reference it from the skill's SKILL.md as guidance for activation.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: writing-claude-directives
Download link: https://github.com/ed3dai/ed3d-plugins-testing/archive/main.zip#writing-claude-directives

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.