rubric-designer
Design, normalize, lint, and freeze evaluation rubrics before substantive review or benchmarking, with observable criteria, explicit pass/fail semantics, evidence floors, materiality, blocker rules, scope boundaries, and immutable rubric hashes. Use when the user asks to create grading criteria, an evaluation rubric, acceptance scoring framework, reviewer scorecard, red-team rubric, or repeatable assessment contract. Do not use to judge the candidate itself, to write the artifact, to run empirical skill benchmarks, or to move criteria after seeing the result; use the relevant reviewer, artifact-acceptance, skill-evaluator, or quality-loop-operator for those tasks.
Pinned to revision 6626bb65beb0, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/rubric-designer/SKILL.md
- skills/rubric-designer/CHANGELOG.md
- skills/rubric-designer/LICENSE
- skills/rubric-designer/README.md
- skills/rubric-designer/VERSION
- skills/rubric-designer/agents/openai.yaml
- skills/rubric-designer/assets/icon.svg
- skills/rubric-designer/evals/cases.json
- skills/rubric-designer/evals/real-host.json
- skills/rubric-designer/references/anti-gaming.md
- skills/rubric-designer/references/evaluation.md
- skills/rubric-designer/references/output-contract.md
- skills/rubric-designer/references/rubric-model.md
- skills/rubric-designer/references/untrusted-input.md
- skills/rubric-designer/scripts/kernel.py
- skills/rubric-designer/scripts/run_evals.py
Every link opens the file at its source, pinned to the revision this page describes.