MS
Model Selection Advisor
🔵 Stable🕐 updated 2026-06-29
🔷 SkillSpec L3
pm-ai
Choose the right LLM for a task by trading off quality, cost, latency, and constraints. Use when asked which model to use, whether to upgrade/downgrade a model, how to cut LLM costs without hurting quality, or to justify a model choice. Produces a recommendation with the decision criteria, a per-option comparison, a routing strategy (cheap-by-default, escalate when needed), and how to validate the choice with an eval.
What to give it
▸The task — what the model does, and an example input/output. How hard is it (extraction vs. reasoning vs. open-ended)?
▸Quality bar — what "good enough" means, and the cost of a wrong answer.
▸Volume & latency — requests/day and how fast a response must come back (interactive vs. batch).
▸Constraints — budget, context-length needs, tool use, privacy/region, and whether outputs must be reproducible.
✅ The bar it holds itself to
Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.
✓The recommendation names a default model/tier and the condition that would change it
✓Reasoning is by tier (small/balanced/frontier), not a single hardcoded model that dates quickly
✓A routing/escalation strategy is considered, not just a single fixed choice
✓The choice is tied to a measurable quality bar and an eval to verify it
✓Cost and latency are estimated at real volume, not per single call
✓Constraints (context length, privacy/region, reproducibility, tool use) are checked against the pick
⚠️ What it refuses to do
Do not default to the biggest model "to be safe" — pay only for the capability the task needs
Do not pick on price alone — a cheap model that fails the bar costs more in rework and trust
Do not recommend without an eval to confirm the quality bar is actually met
Do not hardcode a single model name as the answer — reason by tier and let the eval pick the current best in it
Do not ignore the long tail — design for the hard cases via escalation, not by oversizing everything
Install
npx pm-claude-skills add --agent claude # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcpRelated skills
🔌 Embed this skill
Drop this on your blog, docs, or site — it renders a "Run this skill" card:
<div data-pm-skill="model-selection-advisor"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>💬 Discussion
Model Selection Advisor is one of 551 open-source professional AI agent skills — all SkillSpec L3.
Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog