Measure output quality, don't vibe it: score a generative task with a two-layer grader — deterministic code metrics + per-dimension LLM-as-judge — over a fixed task set, as signed deltas vs a pinned baseline. Grades cost alongside correctness (pass-slow). Trigger phrases: "eval", "grader", "measure output quality", "LLM-as-judge", "score the output"
$npx -y skills add byerlikaya/claude-starter-kit --skill eval-graderInstalls into the current project.
Run `npx skills use "https://github.com/byerlikaya/claude-starter-kit" --skill "byerlikaya/claude-starter-kit/eval-grader"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/byerlikaya/claude-starter-kit" that are relevant to the current task. Run `npx skills add "https://github.com/byerlikaya/claude-starter-kit"` and select the relevant skills, then follow their instructions.