skills.rest
Ankh-Studio
Ankh-StudioOFFICIAL
Explore all skills by this author →
GitHub

artifact

Evaluate Copilot artifacts against a structured rubric with self-critique and scoring.

Updated Mar 10, 2026
Search Tags:#code quality#prompt engineering#verification#rubric#copilot#artifact evaluation
One-click install
npx skills add https://github.com/Ankh-Studio/copilot-enterprise-eval-plugin --skill artifact-ankh-studio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: artifact
Source: https://github.com/Ankh-Studio/copilot-enterprise-eval-plugin/tree/main/skills/artifact
Command: npx skills add https://github.com/Ankh-Studio/copilot-enterprise-eval-plugin --skill artifact-ankh-studio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the evaluation of Copilot-generated artifacts against a defined rubric, ensuring quality and consistency.

Core Features & Use Cases

  • Rubric-Based Evaluation: Applies structured criteria to assess artifacts.
  • Self-Critique: Includes a verification step where the artifact is critiqued for potential issues.
  • Revision and Scoring: Facilitates incorporating feedback and calculating weighted scores.
  • Use Case: Automatically evaluate a Copilot-generated code review prompt (.github/prompts/code-review.prompt.md) against a predefined quality rubric, identify potential flaws, and suggest improvements.

Quick Start

Evaluate the artifact located at .github/prompts/code-review.prompt.md.

Frequently Asked Questions about artifact

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

FAQPage Schema
How do I evaluate Copilot artifacts against a rubric automatically?▼

To evaluate Copilot artifacts automatically, you apply a structured rubric to assess the generated content, perform self-critique for potential issues, and calculate weighted scores. This process requires a defined rubric and a verification stage for accurate assessment.

What is the best way to run a self-critique and revision loop for prompt engineering?▼

Running a self-critique and revision loop for prompt engineering involves applying structured criteria to identify potential flaws in a code review prompt, facilitating feedback incorporation, and calculating weighted scores to ensure quality and consistency.

Can I use rubric-based evaluation to check SKILL.md and WORKFLOW.md files within GitHub?▼

Yes, rubric-based evaluation applies to various artifact types including SKILL.md and WORKFLOW.md files within GitHub. It applies structured criteria to assess these artifacts and performs self-critique for potential issues.

Does artifact evaluation require a predefined quality rubric to work?▼

Yes, artifact evaluation requires a defined rubric and verification stage for accurate assessment. Without a predefined quality rubric, the structured criteria cannot be applied to score or critique the Copilot-generated content.

How do I automate scoring for Copilot-generated code review prompts?▼

Automating scoring for Copilot-generated code review prompts involves evaluating the artifact located at .github/prompts/code-review.prompt.md against a predefined quality rubric, identifying flaws through self-critique, and calculating weighted scores.

Related Skills

Explore More Software Engineering Skills→
yu13130122297yu13130122297

scout

Identify uncertainties in research framing, datasets, metrics, and baselines.

Community
Intermediate
Ankh-StudioAnkh-Studio

artifact-evaluation

Evaluate Copilot artifacts against structured rubrics using Chain-of-Verification.

Official
Intermediate
coreyjacoreyja
12

skill-writer

Draft SKILL.md frontmatter and structure guidance for Claude Code skills.

Community
Basic
HerxinsasaHerxinsasa
1

darwin-skill

Evaluate and optimize agent skill files using an 8-dimension rubric.

Community
Advanced