skills.rest
tstapler
tstaplerCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

model-selection

Select Claude models by task complexity, reasoning depth, and cost constraints.

8|2|Updated Jul 13, 2015
Search Tags:#claude#prompt-engineering#ai-models#model-selection#task-routing#decision-matrix#cost-speed
One-click install
npx skills add https://github.com/tstapler/dotfiles --skill model-selection-tstapler
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-selection
Source: https://github.com/tstapler/dotfiles/tree/main/.claude/skills/model-selection
Command: npx skills add https://github.com/tstapler/dotfiles --skill model-selection-tstapler

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Selecting the optimal Claude model (Opus 4.5, Sonnet, Haiku) for a given task to balance reasoning depth, speed, and cost.

Core Features & Use Cases

  • Task-driven model tiering using a clear decision matrix.
  • Guidelines for when to apply each model based on complexity and domain requirements.
  • Reusable prompts and templates to standardize model assignment in AI workflows.

Quick Start

Describe your task to the AI and request the most appropriate Claude model based on complexity and cost.

Frequently Asked Questions about model-selection

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I choose the right Claude model for a specific task?▼

To choose the right Claude model, evaluate task complexity, reasoning depth, and cost-speed constraints against a decision matrix to assign Opus 4.5, Sonnet, or Haiku for optimal multi-domain agent workflows.

When should I use Opus 4.5 instead of Sonnet or Haiku for prompt orchestration?▼

Use Opus 4.5 for prompt orchestration when tasks demand high reasoning depth and complex multi-domain agent workflows, whereas Sonnet and Haiku suit execution tasks with tighter cost-speed constraints.

Can I standardize AI model selection across different execution tasks?▼

Yes, you can standardize AI model selection by applying reusable prompts and templates that implement explicit usage guidelines, ensuring consistent and auditable model assignment across execution tasks.

What is the best way to balance cost and speed when routing Claude models?▼

The best way to balance cost and speed is applying a task-routing decision matrix that matches execution task complexity to the appropriate Claude model tier, optimizing latency and budget.

Does this model selection approach work for multi-domain agent workflows?▼

Yes, this model selection approach works for multi-domain agent workflows by implementing a decision matrix that determines model assignment based on domain requirements, complexity, and cost-speed constraints.

Related Skills

Explore More Software Engineering Skills→
digital-stoic-orgdigital-stoic-org
19

pick-model

Evaluate task descriptions against a decision matrix to recommend a Claude model.

Official
Advanced
nrslibnrslib
1.3k

takt

Orchestrate multi-agent teams across piece YAML workflows with auditable prompts.

Community
Advanced
mdjubaerhossensabbirmdjubaerhossensabbir

create-agent

Generate structured agent configuration files for AI personas and tool usage.

Community
Basic
sigridjinethsigridjineth
20

ecomode

Route AI tasks to lower-cost model tiers based on complexity.

Community
Intermediate