What do I need to use Model Migration Plan?

Current and target model; The feature's traffic and blast radius; Existing evals; The deadline.

Is Model Migration Plan free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Model Migration Plan

Q: How do I know the Model Migration Plan output is good?

The skill verifies itself against its own quality checks: Every phase promotion criterion is a number against the recorded baseline; Shadow phase compares distributions, not anecdotes ("outputs look good" is not a gate); Rollback is a config flip with a named owner, tested before canary; The plan re-baselines the regression suite after cutover — the new model becomes the new normal.

🔵 Stable🕐 updated 2026-07-01 🔷 SkillSpec L3 pm-agentops

Plan the migration of an LLM feature from one model to another without breaking production. Use when a model is being deprecated, a newer model looks better or cheaper, or when asked how to upgrade models safely, run shadow traffic, or set rollback criteria for a model change. Produces a phased migration plan with eval gates, shadow/canary stages, prompt-adaptation notes, and rollback triggers. For choosing which model in the first place use model-selection-advisor.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸Current and target model — and why: deprecation, quality, cost, latency

▸The feature's traffic and blast radius — requests/day, who sees the output, what a bad output costs

▸Existing evals — a regression suite (see `prompt-regression-suite`) or at minimum golden examples; if none exist, phase 0 is building one

▸The deadline — , if the migration is forced by a deprecation date

✅ 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.

✓Every phase promotion criterion is a number against the recorded baseline

✓Shadow phase compares distributions, not anecdotes ("outputs look good" is not a gate)

✓Rollback is a config flip with a named owner, tested before canary

✓The plan re-baselines the regression suite after cutover — the new model becomes the new normal

✓Deprecation deadlines leave slack for at least one failed phase-1 iteration

⚠️ What it refuses to do

Do not skip shadow because offline evals passed — real traffic finds what golden sets miss

Do not migrate the feature and the prompt redesign in one change — you won't know which moved the metrics

Do not compare models with an unpinned judge, or a judge that is the target model grading itself

Do not leave the old model path in code indefinitely "just in case" — set the removal date in the plan

Do not treat a cheaper model as free savings without re-checking quality at the tails, not just the mean

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-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="model-migration-plan"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Model Migration Plan 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