ai-evals plugins

modiqo/skillspec

Plugin Claude Code

Bundles 1 skill · 183 tokens together

SkillSpec is a CLI plus a structured skill plan for making agent skills easier to follow, test, route, and prove.

Calibre-Labs/reforge-ai-evals

Plugin Claude Code

Bundles 9 skills, 9 commands · 1,041 tokens together

Skills for evaluating an AI product: write the eval rubric, build test inputs, turn trace notes into codes, write judges and check them against your labels. You annotate traces and label for calibration. The skills do the rest.

selectess/fde-consultants-protocoles

Plugin Claude Code

Bundles 1 skill, 3 commands, 1 plugin · 65 tokens together

Forward Deployed Engineering (FDE) methodology + 7 MCP tools + DeepSCR Trust Score. Production-grade Skill that turns Claude Code, Cursor, Windsurf, Codex CLI, and OpenClaw into a forward-deployed engineer.

ByteStack-Labs/claude-plugins

Plugin Claude Code

Bundles 4 skills · 933 tokens together

Claude skills for AI agent and ML reliability: reproduce the eval-to-production gap, catch confidently-wrong outputs, and prove root cause with verified numbers. Start with production-autopsy.