This Claude skill provides a comprehensive framework of XML tag standards designed to optimize AI prompts and technical documentation. By establishing clear structural rules for Claude, GPT-5, Gemini, and Harmony formats, it ensures superior instruction following, improved reasoning through structured thinking tags, and consistent markdown rendering across various LLM platforms.

When should I use smith-xml?

smith-xml is useful in the following scenarios: • Standardizing prompt architectures for multi-agent systems to ensure consistent behavior and instruction adherence across different model providers. • Developing professional AGENTS.md files and technical documentation that require precise XML tagging for better machine parsing and human readability. • Optimizing Claude-specific workflows by utilizing specialized tags like for chain-of-thought reasoning and for strict constraint enforcement. • Cross-platform prompt engineering, allowing developers to adapt prompt structures between GPT-5's snake_case specs and Gemini's behavioral guidelines. • Ensuring correct markdown rendering within AI responses by following specific blank-line rules for XML tag containers.

name	smith-xml
description	XML tag standards for AI prompts and documentation. Use when writing prompts, documentation, or AGENTS.md files. Covers approved tags for Claude, GPT-5, Gemini, and Harmony formats with markdown rendering rules.

XML Tag Standards

Load if: Writing prompts, documentation, AGENTS.md files
Prerequisites: None

CRITICAL: Approved Tags Only (Primacy Zone)

Only use well-established XML tags. Do NOT invent placeholder-style tags.

Universal Tags (All Platforms)

<instructions> - Step-by-step guidance
<task> - Specific user request
<context> - Background information
<examples> - Few-shot examples
<constraints> - Behavioral limitations

Claude-Specific Tags

<metadata> - File/component metadata
<forbidden> - Prohibited actions
<required> - Mandatory requirements
<related> - Cross-references
<formatting> - Output format specs
<thinking> - Chain-of-thought reasoning
<answer> - Final output

Tag Selection Criteria

<required> = "DO this" (imperative, mandatory behavior)

Agent MUST follow; failure causes incorrect behavior
Use for: MUST/ALWAYS/NEVER statements, mandatory behaviors, action directives

<context> = "KNOW this" (informational, may deprioritize)

Agent uses to inform decisions; not mandatory
Use for: Explanations, methodologies, background, reference material

GPT-5.x Tags (Updated Dec 2025)

GPT-5/5.1 Tags:

<plan_tool_usage> - Planning and task management
<context_gathering> - Search depth strategy
<exploration> - Codebase investigation
<verification> - Testing requirements
<code_editing_rules> - Coding standards
<guiding_principles> - Foundational philosophies
<final_instructions> - Critical closing directives

GPT-5.2 Tags (Dec 2025):

<planning> - Scaffolds reasoning before execution
<response> - Contains output after planning phase
<solution_persistence> - Maintains global context across agent turns
<user_updates_spec> - Defines scope boundaries
<tool_preambles> - Tool usage instructions
<output_verbosity_spec> - Output length/format constraints

Pattern: GPT-5.2 favors _spec suffix for instruction categories

Pattern: Gemini 3 uses snake_case, prefers direct/concise prompts

Harmony Format (gpt-oss-120b)

Harmony uses special tokens, NOT XML tags. Do not mix formats.

Essential tokens: <|start|>, <|end|>, <|message|>, <|channel|>, <|return|>

agentskills.io Tags

<available_skills> - Container for skill index in AGENTS.md
<skill name="..." description="..."> - Individual skill entry

Quick Reference

Claude: <required>, <forbidden>, <context> - Instructions, constraints
GPT-5.2: <planning>, <response>, *_spec tags - Agentic workflows
Gemini 3: <rules>, <planning_process>, <output_format> - Structured output
Harmony: <|start|>, <|end|> - Special tokens only
agentskills.io: <available_skills>, <skill> - Skill discovery

Naming Conventions

Platform-specific patterns:

Claude: lowercase concepts (e.g., <required>, <forbidden>, <context>)
GPT-5.2: snake_case with _spec suffix (e.g., <user_updates_spec>, <output_verbosity_spec>)
Gemini 3: snake_case (e.g., <planning_process>, <error_handling>)

Universal tags (work across platforms):

<context>, <instructions>, <task>, <examples>, <constraints>

Markdown Rendering

Blank lines required after opening and before closing XML tags:

<required>

- List item renders as bullet
- Another item

</required>

Without blank lines, markdown renders as literal text.

Content Organization

Good examples → <examples> only
Bad examples → <forbidden> only
NEVER mix good and bad in same tag

Placeholders

Use: Backticks `placeholder` or brackets [placeholder] Avoid: <placeholder>, {{placeholder}}

@smith-prompts/SKILL.md - Prompt engineering
@smith-guidance/SKILL.md - Agent behavior

ACTION (Recency Zone)

Before using XML tags:

Is it a documented tag? → Use it
Is it model-specific? → Check compatibility
Need markdown inside? → Add blank lines

smith-xml

When & Why to Use This Skill

Use Cases