Whichmodels — AI skill for Claude Code
Research the latest Anthropic models (docs, benchmarks, user reports), then propose which model and effort each agent and the session in this repo should run.
How to install Whichmodels
Installs to ~/.claude/skills/cesdperez-llmfiles-whichmodels/SKILL.md
mkdir -p ~/.claude/skills/cesdperez-llmfiles-whichmodels && curl -fsSL https://raw.githubusercontent.com/cesdperez/llmfiles/HEAD/commands/whichmodels.md -o ~/.claude/skills/cesdperez-llmfiles-whichmodels/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Whichmodels does
description: Research the latest Anthropic models (docs, benchmarks, user reports), then propose which model and effort each agent and the session in this repo should run. Adversarially reviewed. Outputs a today-vs-proposed table. argument-hint: [optional focus, e.g. a model name or "only the agents"] disable-model-invocation: true
/whichmodels
Decide whether the model and effort pinned to each executor still fits now that newer models exist. Run it after a release, and again a few w
Alternatives in AI
- Dive Into Claude Code — A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems 2.1k ★
- Agentmemory — #1 Persistent memory for AI coding agents based on real-world benchmarks 1.9k ★
- Kimi Cc — Use Kimi's latest model (kimi-k2-0711-preview) to drive Claude Code 1.7k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
AI News Briefing
Search for today's latest AI news and create/update a comprehensive briefing in Notion, with optional Obsidian
Dev Report Weekly
Local-first desktop app that turns reviewed Git history into auditable weekly reports with Codex, Claude Code,
Model Comparison
Local open-weight models (Qwen3.5-397B, MiniMax M2.5) vs cloud coding agents (Codex 5.3, Claude Code) on six w
Qiaomu AI Radar
每日选题助手 - 监控Import AI、Hacker News、James Clear、Wait But Why、Product Hunt等高质量内容源,自动采集最新文章并推荐值得创作的话题。Use when user
App Paywall Pilot
A framework for designing App Store-compliant subscription paywalls. 4 layers: AI skill (Claude/GPT/Cursor) +
Claude Lot
Claude Code skill: shared usage cap for headless claude -p jobs across all projects on a machine (85 % 5-hour
Related Agents
Dependency Vetter
Supply-chain security audit of a third-party package (npm today) at ONE exact resolved version, run BEFORE it
Claude Code Research Agent
Senior Anthropic researcher specializing in Claude Code CLI - researches latest context window and model avail
Factory Decomposer
Agent Factory decomposer — turns an objective ("improve demo assembly until quality ≥ target") into atomic, ad