Agent Skills: model-comparator
Use this skill when comparing AI or LLM models on benchmarks, capability, cost, latency, context window, or task-specific fit to help teams select the right model for their use case and budget. Not for training or fine-tuning models. Not for building eval frameworks from scratch.
ID: nickcrew/claude-ctx-plugin/model-comparator
4114
Install this agent skill to your local
Skill Files
The files that make up model-comparator.
Loading file tree…
More agent skills
- setup-arxiv-mcpGuide for setup arXiv paper search MCP server using Docker MCP
- audit-env-variablesAnalyze environment variables in JavaScript/TypeScript projects. Identifies unused variables, infers permission scopes, detects specific services (Stripe, AWS, Supabase), and documents code paths. Includes optional cleanup of unused variables with regression detection. Use when auditing .env files, reviewing security, or documenting project configuration.
- systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
- phoenix-error-analysisFind out what is going wrong in LLM or agent traffic by reading sampled Phoenix traces, spans, or sessions, writing free-form notes (open coding), then grouping the notes into a few narrow annotations, one per failure dimension with a small label set and counts, that pick eval targets and fix priorities (axial coding). Use for "what's going wrong with this agent", "I just instrumented my app, where do I start", "review these traces", "the chatbot keeps losing context", "what kinds of mistakes is the model making", "what categories of failures do we have", "what should I build evals for", "how do I prioritize fixes", "group these notes", "MECE breakdown" — or any framing that needs observations or categories grounded in real traces rather than invented top-down, even without naming the technique.
- add-uint-supportAdd unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
- create-an-assetGenerate tailored sales assets (landing pages, decks, one-pagers, workflow demos) from your deal context. Describe your prospect, audience, and goal — get a polished, branded asset ready to share with customers.