skills.rest
kaiohenricunha
kaiohenricunhaCOMMUNITY
Explore all skills by this author →
𝕏@kaiohenricunhaGitHub

create-assessment

Generate standardized markdown assessment documents with weighted scoring and evidence citations.

Updated Apr 14, 2026
Search Tags:#code review#pull request#assessment#grading#architecture decision#evidence-based scoring#weighted rubric
One-click install
npx skills add https://github.com/kaiohenricunha/dotbabel --skill create-assessment
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: create-assessment
Source: https://github.com/kaiohenricunha/dotbabel/tree/main/plugins/dotbabel/templates/claude/skills/create-assessment
Command: npx skills add https://github.com/kaiohenricunha/dotbabel --skill create-assessment

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates inconsistent, subjective grading of software projects, code, architecture decisions, and other targets by enforcing a structured, evidence-backed weighted rubric system that produces reproducible, actionable 0-10 scores.

Core Features & Use Cases

  • Multi-target assessment: Supports grading packages, source files, architecture decisions, pull requests, documents, and full projects with pre-built weighted rubrics tailored to each target type.
  • Custom rubric support: Allows users to override default rubrics with custom dimensions and weights to match specific assessment needs.
  • Standardized output: Generates consistent markdown assessment documents with scored dimensions, evidence citations, improvement recommendations, and clear grade band classifications.
  • Use Case: An engineering lead can use this Skill to grade a new open source package their team is considering adopting, scoring it on correctness, test coverage, and security to make an informed adoption decision.

Quick Start

Ask the AI to assess pull request #412 using the default pull request rubric to generate a structured grade report saved to your project's docs/assessments folder.

Frequently Asked Questions about create-assessment

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I standardize pull request grading to avoid subjective code review assessments?▼

Standardize pull request grading by applying a structured, evidence-based weighted rubric that produces reproducible 0-10 scores. This eliminates subjective code review evaluations by requiring evidence citations for each scored dimension, generating a standardized markdown assessment document with clear grade band classifications.

What is evidence-based scoring for architecture decisions and how does it work?▼

Evidence-based scoring for architecture decisions enforces a weighted rubric system that evaluates project decisions against specific criteria using cited evidence. It assesses architecture decisions by scoring multiple dimensions, generating reproducible 0-10 scores with improvement recommendations and grade band classifications saved as markdown documents.

Can I use a custom rubric to assess source files and project documents?▼

Yes, you can override default rubrics with custom dimensions and weights to assess source files, packages, and project documents. This allows you to tailor the evidence-based scoring criteria to match specific assessment needs while still generating standardized markdown output with scored dimensions and improvement recommendations.

How do I generate a structured grade report for an open source package adoption evaluation?▼

Generate a structured package adoption grade report by assessing the target using built-in or custom weighted rubrics. The assessment produces a markdown document with scored dimensions, evidence citations, improvement recommendations, and grade band classifications, saved directly to the project's docs/assessments directory.

What is the best way to automate reproducible grading for software project artifacts?▼

The best way to automate reproducible grading is enforcing an evidence-backed weighted rubric system that produces standardized 0-10 scores. By applying structured assessment criteria to software artifacts, the process eliminates inconsistent and subjective grading, yielding reproducible markdown documents with cited evidence and actionable improvement recommendations.

Do I need any specific dependencies to run evidence-based weighted assessments on code assets?▼

No specific dependencies are required to run evidence-based weighted assessments on code assets. The grading process operates independently by applying built-in or custom rubrics to evaluate targets, generating standardized markdown assessment documents with scored dimensions and grade bands without relying on external packages.

Related Skills

Explore More Software Engineering Skills→
mleskmlesk
1

dm-loopify

Run rubric-driven iterative optimization loops with explicit success criteria and stop conditions.

Community
Advanced
southlab-aisouthlab-ai
2

council-value

Score a product goal across Value Clarity, Timeline, Perception, and Discovery.

Official
Advanced
peopleforresterpeopleforrester
3

eval-harness

Evaluate code quality across projects using a structured rubric.

Community
Basic
angrysky56angrysky56

peer-reviewer

Evaluate academic manuscripts and technical frameworks for claim-evidence alignment and methodological rigor.

Community
Intermediate