Excel-Adeniyi

Eval Check — AI skill for Claude Code

AI community

Fast offline regression check — no model calls, no usage spent.

How to install Eval Check

Installs to ~/.claude/commands/excel-adeniyi-ea-skill-eval-eval-check.md

Terminal

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Excel-Adeniyi/ea-skill-eval/HEAD/.claude/commands/eval-check.md -o ~/.claude/commands/excel-adeniyi-ea-skill-eval-eval-check.md

Restart Claude Code, or start a new session, for it to be picked up.

What Eval Check does

description: Fast offline regression check — no model calls, no usage spent allowed-tools: Bash(cargo run), Bash(cargo test), Bash(cargo clippy), Bash(cargo fmt)

Run the offline checks for this repository. **Make no model calls** — this command must not spend usage.

cargo test — all unit and integration tests.
cargo clippy --all-targets — must be warning-free.
cargo fmt --check — must be clean.
If samples/captured.json exists, run `cargo run -- samples/captur

Alternatives in AI

Osaurus — Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cry 5.1k ★
Fast Agent — Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support 3.7k ★
Cwc Long Running Agents — Claude Code's built-in /goal command gives you a generator/evaluator loop out of the box: set a completion con 668 ★