dw-skill-eval-analyze

Analyze a Skill's SKILL.md and output skill-analysis.yaml for evaluation.

1|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/xurik/dataworks-skill-evaluator --skill dw-skill-eval-analyze
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dw-skill-eval-analyze
Source: https://github.com/xurik/dataworks-skill-evaluator/tree/main/eval/skills/dw-skill-eval-analyze
Command: npx skills add https://github.com/xurik/dataworks-skill-evaluator --skill dw-skill-eval-analyze

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyzes a tested Skill's SKILL.md to perform static analysis, extract structure and references, and conduct semantic evaluation across five dimensions; it also gathers evaluation context from the user and outputs skill-analysis.yaml for downstream steps.

Core Features & Use Cases

  • Static analysis: extract structure, token counts, API references, API coverage, and reference integrity.
  • Semantic analysis: assess intent clarity, instruction ambiguity, scenario coverage, API chain logic, and edge case gaps.
  • Context collection: prompt the user to fill in target_user, known_failures, success_criteria, and forbidden_behaviors, feeding the resulting user_context.
  • Output: generates eval/evaluations/{skill-name}/skill-analysis.yaml to guide the rest of the evaluation pipeline.
  • Use case: serves as the first phase in the end-to-end skill evaluation workflow, ensuring the tested skill is well-defined before test generation.

Quick Start

Run the analyze command on your skill directory to generate eval/evaluations/{skill-name}/skill-analysis.yaml.

Frequently Asked Questions about dw-skill-eval-analyze

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

FAQPage Schema
What is semantic analysis for skill evaluation?

To analyze a SKILL.md for static structure, the tool extracts token counts, API references, API coverage, and reference integrity. It validates required frontmatter and outputs a structured skill-analysis.yaml evaluation artifact.

How do I generate a skill-analysis.yaml file for my evaluation pipeline?

You generate a skill-analysis.yaml file by running the analyze command on your skill directory. The tool performs static and semantic analysis on your SKILL.md and outputs the artifact to eval/evaluations/{skill-name}/skill-analysis.yaml.

Does skill evaluation require specific context before analyzing a SKILL.md?

Skill evaluation requires specific context before analyzing a SKILL.md. The tool prompts you to provide target_user, known_failures, success_criteria, and forbidden_behaviors, feeding this data into the resulting user_context for accurate semantic analysis.

What are the limitations of static analysis for evaluating skill definitions?

The limitations of static analysis for evaluating skill definitions involve its inability to understand meaning without semantic evaluation. Static analysis only extracts structure, token counts, API references, and reference integrity, requiring semantic analysis to assess intent and ambiguity.