michaelhazza

Eval Prompts — Development skill for Claude Code

Development community

Run a golden-set prompt eval suite against the pinned baseline; fail on any regression beyond threshold.

How to install Eval Prompts

Installs to ~/.claude/commands/michaelhazza-claude-code-framework-eval-prompts.md

Terminal

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/michaelhazza/claude-code-framework/HEAD/.claude/commands/eval-prompts.md -o ~/.claude/commands/michaelhazza-claude-code-framework-eval-prompts.md

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

What Eval Prompts does

description: "Run a golden-set prompt eval suite against the pinned baseline; fail on any regression beyond threshold."

/eval-prompts

Run a repo-local golden-set eval suite through its target prompt and score it against the last-accepted baseline. Use before shipping a prompt change: the change lands only if its suite still passes. Suites are repo-owned under `eval//`; the framework ships the runner + the format spec (`references/eval-suite-format.md`) + `/framework-doctor` Ch

Alternatives in Development

10 Context And Prompts — Prompt 10: Wire Up System Prompt, Context Gathering & Memory System 2.3k ★
Codex Prompt Handgepflegte Mega Und Mini Prompts — Codex-Prompt — Handgepflegte Mega- und Mini-Prompts fuer alle Plugins 1.5k ★
Scaling Prompts — Scaling Prompts — Road to 1M+ Users & Beyond CoinGecko 313 ★