← Browse
eval-first
robertnowell ★ 0
Eval-First is a Claude Code skill that automatically nudges developers to articulate success criteria, failure modes, and evaluation cases whenever they modify prompts, agents, or model outputs. It embeds verification thinking into the workflow without requiring explicit labeling, surfacing test verdicts upfront followed by supporting evidence.
Install
> /plugin marketplace add robertnowell/eval-first
> /plugin install eval-first
What it's made of
1 skill
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (robertnowell).