/xml-prompt-formatter
Reformat a raw prompt using XML tags to clearly delimit each structural layer of meaning
$ npx -y skills add qdhenry/Claude-Command-Suite --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/xml-prompt-formatter
Context preview
What this command does when you run it.
Reformat a raw prompt using XML tags to clearly delimit each structural layer of meaning
Command definition
xml-prompt-formatter.mdname: prompt-formatter description: Reformat a raw prompt using XML tags to clearly delimit each structural layer of meaning allowed-tools: Read, Grep, Glob, Bash author: Quintin Henry (https://github.com/qdhenry/)
<prompt_formatter> You are a prompt formatting assistant. When I give you a raw prompt, reformat it using XML tags to clearly delimit each structural layer of meaning. Follow these rules:
1. Wrap the user's core instruction or goal in <task> tags. 2. Wrap any context, background, or reference material in <context> tags. 3. Wrap examples (input/output pairs, sample data, etc.) in <example> tags. 4. Wrap constraints, tone requirements, or formatting rules in <constraints> tags. 5. Wrap any provided data, documents, or quoted content that Claude should treat as second-order (i.e., material to be operated on, not instructions) in <content> tags. 6. Use nested tags to express layered meaning when needed (e.g., <example><input>...</input><output>...</output></example>). 7. Keep the <task> as the top-level first-order instruction — everything else is second-order material that supports it. Return the fully reformatted prompt, ready to submit to Claude, with no additional commentary. </prompt_formatter>
A comprehensive development toolkit designed following Anthropic's Claude Code Best Practices for AI-assisted software development.
Repo: qdhenry/Claude-Command-Suite
Other commands on claude-command-suite.
- /boundary-bbcr-fallback
Execute automatic BBCR (Collapse-Rebirth Correction) when knowledge boundaries are exceeded or reasoning fails.
Open command - /boundary-detect
Analyze semantic position relative to knowledge boundaries to prevent hallucination and identify uncertainty zones.
Open command - /boundary-heatmap
Generate a visual heatmap of knowledge boundaries showing safe zones, risk areas, and semantic coverage.
Open command - /boundary-risk-assess
Evaluate the current risk level and provide detailed analysis of potential hallucination or reasoning failure.
Open command - /boundary-safe-bridge
Find and construct semantic bridges to safely navigate from current position to target concept without crossing dangerous boundaries.
Open command - /optimize-prompt
Takes an input prompt and returns ONLY a token-optimized version that preserves meaning while minimizing token count. Based on LLM tokenization principles: common words tokenize more efficiently, unusual words break into more tokens, and conciseness reduces cost.
Open command

