MigrateModel — AI skill for Claude Code
(+ai) Eval-gated migration to a new/replacement model — never migrate blind.
How to install MigrateModel
Installs to ~/.claude/skills/linofcp007-dev-spec-driven-migratemodel/SKILL.md
mkdir -p ~/.claude/skills/linofcp007-dev-spec-driven-migratemodel && curl -fsSL https://raw.githubusercontent.com/linofcp007/dev-spec-driven/HEAD/commands/migrateModel.md -o ~/.claude/skills/linofcp007-dev-spec-driven-migratemodel/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What MigrateModel does
description: (+ai) Eval-gated migration to a new/replacement model — never migrate blind. PT - migração de modelo com evals (+ai). ES - migración de modelo con evals (+ai). argument-hint: "[feature name] [target model]"
Use the **dev-spec-driven** skill model-migration workflow (+ai track).
Args: $ARGUMENTS
Run the current eval set (golden + adversarial + regression) through the target model and compare per set. Switch only if the new model matches or beats the current one on every se
Alternatives in AI
- Semble Rs — Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & imp 210 ★
- Token Cost Tracker — Estimate, log, and report token usage using runtime-supplied billing rates; never rely on embedded model price 138 ★
- Coder Eval Code Review — Run a multi-model code review on uncommitted changes or a described set of files 116 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claude Evals
Production eval framework for Claude Agent SDK — implements Anthropic's published eval patterns with native SD
M0s Indicator
Never hit your AI token limit blind, real-time usage bars for Claude Code, Codex & Gemini
Ground Truth Evals
An LLM eval harness graded by computed ground truth, not an LLM judge. Worked example: poker, served to models
EvalPlan
Phase 3 (+ai) — build golden / adversarial / regression eval sets, graders, thresholds, baseline. PT - plano d
Agentic Review Gate
Governed, auditable AI review platform: the review and approval work a team does by hand, as a webhook-trigger
Saurabh AI Systems
AI architect for GTM and martech. I design and ship production agentic systems for B2B sales and marketing: le
Related Agents
Eval Runner
Run eval suites for Salesforce Apex and org quality — define pass/fail, grade with code/model graders, run pip
Blind Evaluator
Structurally separate eval agent. Receives ONLY the problem statement + rubric, NEVER the solution or the impl
Effect Prober
Adversarial effect-verifier for irreversible actions. Given an action that reports success (a deploy, migratio
