Writing Claude Directives

by ed3dai

Writing Claude Directives is an AI Engineering skill for Claude Code, published by ed3dai in ed3d-plugins.

248 stars32 forkson ed3dai/ed3d-pluginsAdded 2026/09/02Repository updated 2026/06/16

View source on GitHub Download repo ZIP

claudeclaude-codeclaude-code-pluginclaude-code-plugin-marketplaceskills

Install in seconds

Install Writing Claude Directives

Copy Writing Claude Directives into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/ed3dai/ed3d-plugins/tree/main/plugins/ed3d-extending-claude/skills/writing-claude-directives ~/.claude/skills/writing-claude-directives

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/ed3dai/ed3d-plugins.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugins/ed3d-extending-claude/skills/writing-claude-directives/SKILL.md in ed3dai/ed3d-plugins
Installs to: ~/.claude/skills/writing-claude-directives
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2631 skills

What Writing Claude Directives does

Writing Claude Directives helps you write instructions for Claude behavior, including skills, CLAUDE.md files, and agent or system prompts. Use it when you need clearer compliance, token-efficient guidance, or better skill discovery.

Writing Claude Directives is cataloged under AI Engineering on DirSkills. Writing Claude Directives comes from a repository tagged claude, claude-code, claude-code-plugin, claude-code-plugin-marketplace and skills.

Documentation

README

Excerpt

Writing Claude Directives

REQUIRED: Also apply ed3d-extending-claude:prompt-security-hardening when using this skill. Directives that demonstrate unsafe secrets handling teach agents to leak secrets.

Core Principles

1. Claude is smart. Only write what it doesn't already know. Challenge each line: does this justify its token cost?

2. Positive > Negative framing. "Don't do X" triggers thinking about X (pink elephant problem). Say what TO do, not what to avoid.

# Bad: triggers the behavior
Don't create duplicate files

# Good: directs to correct behavior
Update existing files in place

3. Context motivates compliance. Explain WHY, not just WHAT. Claude generalizes from motivation.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Writing Claude Directives

What else does ed3dai publish alongside Writing Claude Directives?
Writing Claude Directives is one of 25 skills that DirSkills catalogs from ed3dai/ed3d-plugins, the repository it ships in. Its siblings there include Asking Clarifying Questions, Brainstorming and Coding Effectively. Each one is a separate skill with its own page in this directory, installs the same way Writing Claude Directives does, and is maintained by ed3dai in that same repository. The rest of the collection is listed on the ed3dai/ed3d-plugins page.
How does Writing Claude Directives compare to other AI Engineering skills?
Writing Claude Directives ranks #2327 by stars among the 2631 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Writing Claude Directives against them. Open each page to compare what they document and how they install.