Guidance for selecting appropriate AI model (sonnet vs haiku) based on task complexity, reasoning requirements, and performance needs.
SkillScore96Maintained
Automatic
◆AI Engineer pack
Last verified 9/3/2026
What it changes
Passed 22 of 23 test cases with the skill, and 10 of 23 without it.
Without skill43%
With skill96%
Checks it passed that the model alone missed
Selects `haiku` for local JSON cache management.
Selects `haiku` as the model for the file operations agent.
States in the justification that no complex reasoning is required.
and 16 more in the full report
12 fixed10 passed either way1 still failing0 broke
Pass-rate lift
+52 pp
Tokens
+63%
Agent turns
0%
Response time
-33%
Model gemini-3.6-flashMeasured 9/3/2026v122 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
Where exactly within an agent's specification document should the Model Selection Justification block be positioned relative to YAML frontmatter and headings?
What was checked, without and with the skill
Checked
Without skill
With skill
Positions the justification block directly after the main title heading of the agent specification.
Missed
Passed
Places the main title heading immediately following the opening YAML frontmatter block.
Passed
Passed
case-11 · gemini-3.6-flash · 9/3/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md360 linessingle file
Selecting AI Models for Agents
Guidelines for choosing between sonnet and haiku models based on agent capabilities and task requirements.
When This Skill Loads
This Skill auto-loads when implementing agents or documenting model selection rationale.