Sentence-level and section-level craft for instructions Claude will actually follow, in any container — project instructions, a standalone prompt, or skill body text. Use when the text exists or is being drafted and the question is quality: "why is Claude ignoring this instruction", "rewrite this prompt so it works", "improve my project instructions", "make this instruction stick", "is this too prescriptive", "how much structure does Sonnet need versus Opus". Covers imperative construction, positive framing, strategic-versus-procedural calibration per model, extended thinking, complexity scaling, and a quality checklist. For deciding WHICH container the instruction belongs in, use crafting-instructions. For building, testing and packaging a whole skill directory, use creating-skill.
Ask your Agent
Use this Skill: https://skilld.dev/gh/oaustegard/claude-skills/writing-instructions
This session only. Nothing lands on disk.
≈145 tokens on demand. Your agent reads this file only when SKILL.md points to it.
All notable changes to the writing-instructions skill are documented in this file. The format is based on Keep a Changelog.
Source: SKILL.md on GitHub
The skill provides instructional content and best practices for writing effective prompts and project instructions for Claude. It focuses on principles such as imperative construction, model calibration, and format selection. Analysis of the content reveals no malicious code, network activity, or security vulnerabilities.
No alerts
Risk: LOW · No issues
Signed by skilld at 5e58100. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub yesterday.
{
"version": "0.3.0"
}