Load domain-specific evaluation rubrics from YAML frontmatter in markdown files.
npx skills add https://github.com/ats-kinoshita-iso/trine-eval --skill eval-rubric
Please help me install this Agent Skill. Skill: eval-rubric Source: https://github.com/ats-kinoshita-iso/trine-eval/tree/main/skills/eval-rubric Command: npx skills add https://github.com/ats-kinoshita-iso/trine-eval --skill eval-rubric
This Skill enables users to load and access tailored evaluation criteria and grading weights based on project types, improving systematic assessment consistency.
Load the evaluation rubric for the current project type by specifying the rubric category and apply it during assessment.
High-intent search queries and answers about installing and using this skill.
You can define consistent grading criteria by loading domain-specific evaluation rubrics that use YAML frontmatter in markdown files to organize scoring dimensions, thresholds, and test methods for systematic project assessment.
Standardize project assessment rubrics by loading tailored evaluation criteria and grading weights based on project types, ensuring uniform evaluation across domains like APIs, web applications, and evaluation harnesses.
Load the evaluation rubric by specifying the rubric category for your current project type. The system retrieves specific evaluation criteria structured with YAML frontmatter in markdown files to guide the assessment.
Yes, you can apply custom scoring thresholds and test methods during a project review. The rubric files use YAML frontmatter to organize these specific grading standards and evaluation dimensions for consistent application.
Yes, this rubric evaluation approach works for different types of software projects. It provides domain-specific evaluation criteria applicable across project types such as web applications, APIs, and evaluation harnesses.
Ensure uniform evaluation criteria by loading the relevant API rubric during review meetings. This applies consistent grading standards and weights tailored to the API service's specific project domain.
mhismail3Construct evaluation suites with multi-dimensional rubrics and automated scoring for agent systems.
GRCEngClubManage organizational risk registers and generate board-ready risk reports.
selcukyucelGenerate structured evaluation datasets with binary rubric scoring for AI outputs.
daymadeConfigure and run Promptfoo LLM evaluation workflows with YAML configs and CLI commands.
