Evaluation Rubrics

Builds structured scoring frameworks with criteria, performance levels, and descriptors so you can evaluate work consistently and reduce subjective bias. Covers analytic rubrics for detailed feedback, holistic for quick judgments, single-point for growth-focused assessment, and binary checklists for compliance. The workflow walks you through defining scope, identifying 4-8 criteria, designing scales (typically 1-5), writing observable descriptors for each level, and calibrating with multiple reviewers to hit 70%+ inter-rater agreement. Strong on practical guardrails like making criteria measurable, providing concrete examples at each level, and sharing rubrics upfront so people know expectations. Worth using when you're grading student work, reviewing code, comparing vendor proposals, or any scenario where you need defensible, repeatable quality judgments.

skills.sh installs: 790
GitHub stars: 193
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add lyndonkl/claude --skill evaluation-rubrics --agent claude-code

Installs into .claude/skills of the current project.

Files

Example

Scenario: Evaluating technical blog posts (1-5 scale)

Criterion	1 (Poor)	3 (Adequate)	5 (Excellent)
Technical Accuracy	Multiple factual errors, misleading	Mostly correct, minor inaccuracies	Fully accurate, technically rigorous
Clarity	Confusing, jargon-heavy, poor structure	Clear to experts, some structure	Accessible to target audience, well-organized
Practical Value	No actionable guidance, theoretical only	Some examples, limited applicability	Concrete examples, immediately applicable
Originality	Rehashes common knowledge, no new insight	Some fresh perspective, builds on existing	Novel approach, advances understanding

Scoring: Post A [4, 5, 3, 2] = 3.5 avg. Post B [5, 4, 5, 4] = 4.5 avg. Feedback for Post A: "Strong clarity (5) and good accuracy (4), but needs more practical examples (3) and offers less original insight (2)."