Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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.
.claude/skills/majiayu000-xml-standards/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 79% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 80% | 0% |
<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 TodoWrite 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>
xml<orchestration> <allowed_tools>Task, Bash, Read, TodoWrite, 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>
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>
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>
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>
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>
name, priority, order attributesxml<template name="Example">
// code here - note: opening directly under tag
</template>Only in XML attribute values and text nodes (NOT in code blocks):
< for <> for >& for &| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 29,096 | 28,531 | -2% | 1 | 1 | 0% | 5,368 | 6,051 | +13% | 0 | 0 | — |
case-02 | fail→pass | 46,521 | 31,983 | -31% | 1 | 1 | 0% | 7,851 | 7,506 | -4% | 0 | 0 | — |
case-03 | fail→pass | 25,237 | 26,584 | +5% | 1 | 1 | 0% | 3,476 | 5,446 | +57% | 0 | 0 | — |
case-04 | fail→pass | 23,347 | 22,810 | -2% | 1 | 1 | 0% | 3,083 | 5,530 | +79% | 0 | 0 | — |
case-05 | fail→pass | 22,466 | 29,092 | +29% | 1 | 1 | 0% | 3,339 | 6,026 | +80% | 0 | 0 | — |
case-06 | fail→pass | 20,697 | 19,763 | -5% | 1 | 1 | 0% | 2,707 | 5,224 | +93% | 0 | 0 | — |
case-07 | pass→pass | 17,192 | 10,799 | -37% | 1 | 1 | 0% | 2,030 | 3,352 | +65% | 0 | 0 | — |
case-08 | fail→pass | 20,333 | 12,862 | -37% | 1 | 1 | 0% | 3,803 | 3,750 | -1% | 0 | 0 | — |
case-09 | fail→pass | 9,467 | 13,536 | +43% | 1 | 1 | 0% | 1,696 | 2,910 | +72% | 0 | 0 | — |
case-10 | fail→pass | 14,897 | 14,342 | -4% | 1 | 1 | 0% | 1,853 | 3,169 | +71% | 0 | 0 | — |
case-11 | fail→pass | 15,400 | 9,577 | -38% | 1 | 1 | 0% | 2,238 | 2,262 | +1% | 0 | 0 | — |
case-12 | fail→pass | 18,740 | 13,055 | -30% | 1 | 1 | 0% | 2,133 | 2,915 | +37% | 0 | 0 | — |
case-13 | fail→pass | 24,561 | 18,084 | -26% | 1 | 1 | 0% | 3,634 | 4,737 | +30% | 0 | 0 | — |
case-14 | fail→pass | 21,888 | 10,025 | -54% | 1 | 1 | 0% | 3,025 | 3,347 | +11% | 0 | 0 | — |
case-15 | pass→fail | 19,873 | 13,656 | -31% | 1 | 1 | 0% | 4,158 | 4,165 | +0% | 0 | 0 | — |
case-16 | fail→pass | 13,093 | 7,447 | -43% | 1 | 1 | 0% | 2,140 | 2,779 | +30% | 0 | 0 | — |
case-17 | pass→fail | 18,625 | 15,236 | -18% | 1 | 1 | 0% | 3,257 | 3,289 | +1% | 0 | 0 | — |
case-18 | fail→pass | 12,676 | 23,312 | +84% | 1 | 1 | 0% | 2,246 | 4,838 | +115% | 0 | 0 | — |
case-19 | fail→pass | 16,065 | 7,875 | -51% | 1 | 1 | 0% | 1,909 | 2,900 | +52% | 0 | 0 | — |
case-20 | pass→pass | 5,818 | 7,093 | +22% | 1 | 1 | 0% | 1,176 | 2,915 | +148% | 0 | 0 | — |
case-21 | pass→pass | 3,761 | 8,790 | +134% | 1 | 1 | 0% | 617 | 2,168 | +251% | 0 | 0 | — |
case-22 | pass→pass | 14,144 | 27,620 | +95% | 1 | 1 | 0% | 3,211 | 6,954 | +117% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +64 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.