xml-standards
XML tag structure patterns for Claude Code agents and commands. Use when designing or implementing agents to ensure proper XML structure following Anthropic best practices.
What this skill does
plugin: agentdev
updated: 2026-01-20
# XML Tag Standards
## Core Tags (Required for ALL Agents/Commands)
### `<role>`
Defines agent identity and purpose.
```xml
<role>
<identity>Expert [Domain] Specialist</identity>
<expertise>
- Core skill 1
- Core skill 2
- Core skill 3
</expertise>
<mission>
Clear statement of what this agent accomplishes
</mission>
</role>
```
### `<instructions>`
Defines behavior constraints and workflow.
```xml
<instructions>
<critical_constraints>
<constraint_name>
Description of critical rule that must be followed
</constraint_name>
<todowrite_requirement>
You MUST use Tasks to track workflow progress.
</todowrite_requirement>
</critical_constraints>
<core_principles>
<principle name="Name" priority="critical|high|medium">
Description of principle
</principle>
</core_principles>
<workflow>
<phase number="1" name="Phase Name">
<step>Step description</step>
<step>Step description</step>
</phase>
</workflow>
</instructions>
```
### `<knowledge>`
Domain-specific best practices and templates.
```xml
<knowledge>
<section_name>
Best practices, patterns, or reference material
</section_name>
<templates>
<template name="Template Name">
Template content
</template>
</templates>
</knowledge>
```
### `<examples>`
Concrete usage scenarios (2-4 required).
```xml
<examples>
<example name="Descriptive Name">
<user_request>What user asks for</user_request>
<correct_approach>
1. Step one
2. Step two
3. Step three
</correct_approach>
</example>
</examples>
```
### `<formatting>`
Communication style and output format.
```xml
<formatting>
<communication_style>
- Style guideline 1
- Style guideline 2
</communication_style>
<completion_message_template>
Template for completion messages
</completion_message_template>
</formatting>
```
---
## Specialized Tags by Agent Type
### Orchestrators (Commands)
```xml
<orchestration>
<allowed_tools>Task, Bash, Read, TaskCreate, TaskUpdate, TaskList, TaskGet, AskUserQuestion</allowed_tools>
<forbidden_tools>Write, Edit</forbidden_tools>
<delegation_rules>
<rule scope="design">ALL design → architect agent</rule>
<rule scope="implementation">ALL implementation → developer agent</rule>
<rule scope="review">ALL reviews → reviewer agent</rule>
</delegation_rules>
<phases>
<phase number="1" name="Phase Name">
<objective>What this phase achieves</objective>
<steps>
<step>Step description</step>
</steps>
<quality_gate>Exit criteria for this phase</quality_gate>
</phase>
</phases>
</orchestration>
<error_recovery>
<strategy>
Recovery steps for common failures
</strategy>
</error_recovery>
```
### Planners (Architects)
```xml
<planning_methodology>
<approach>How planning is performed</approach>
<deliverables>What planning produces</deliverables>
</planning_methodology>
<gap_analysis>
<checklist>Items to verify during planning</checklist>
</gap_analysis>
<output_structure>
<format>Structure of planning output</format>
</output_structure>
```
### Implementers (Developers)
```xml
<implementation_standards>
<file_writing_standards>
<standard name="Standard Name">Description</standard>
</file_writing_standards>
<quality_checks mandatory="true">
<check name="check_name" order="1">
<tool>Tool name</tool>
<command>Command to run</command>
<requirement>What must pass</requirement>
<on_failure>Recovery action</on_failure>
</check>
</quality_checks>
<validation_checks>
<check order="1" name="Check Name">
Validation criteria
</check>
</validation_checks>
</implementation_standards>
```
### Reviewers
```xml
<review_criteria>
<focus_areas>
<area name="Area Name" priority="critical|high|medium" weight="20%">
**Check:**
- Item to verify
- Item to verify
**Common Issues:**
- Issue description
**Critical if**: Condition for critical severity
**High if**: Condition for high severity
</area>
</focus_areas>
<feedback_format>
Template for review feedback
</feedback_format>
</review_criteria>
<approval_criteria>
<status name="PASS">Criteria for passing</status>
<status name="CONDITIONAL">Criteria for conditional approval</status>
<status name="FAIL">Criteria for failure</status>
</approval_criteria>
```
### Testers
```xml
<testing_strategy>
<approach>Testing methodology</approach>
<test_types>
<type name="Type Name">Description</type>
</test_types>
</testing_strategy>
<coverage_requirements>
<requirement>Coverage criteria</requirement>
</coverage_requirements>
```
---
## Nesting Rules
1. **Proper Hierarchy** - Tags must be properly nested
2. **Closing Tags** - All opening tags must have closing tags
3. **Semantic Attributes** - Use `name`, `priority`, `order` attributes
4. **Consistent Naming** - Use lowercase-with-hyphens for tag names
## Code Blocks in XML
```xml
<template name="Example">
```language
// code here - note: opening ``` directly under tag
```
</template>
```
## Character Escaping
Only in XML attribute values and text nodes (NOT in code blocks):
- `<` for `<`
- `>` for `>`
- `&` for `&`
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.