skills.rest
ShaheerKhawaja
ShaheerKhawajaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agentic-eval

Evaluate plans, code, or research with the CLEAR v2.0 framework.

8|Updated Mar 17, 2026
Search Tags:#evaluation#evidence#quality-assurance#code-review#evaluate#clear
One-click install
npx skills add https://github.com/ShaheerKhawaja/ProductionOS --skill agentic-eval-shaheerkhawaja
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agentic-eval
Source: https://github.com/ShaheerKhawaja/ProductionOS/tree/main/skills/agentic-eval
Command: npx skills add https://github.com/ShaheerKhawaja/ProductionOS --skill agentic-eval-shaheerkhawaja

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a rigorous CLEAR v2.0 evaluation framework to assess plans, codebases, and research outputs, surfacing gaps and improvement opportunities.

Core Features & Use Cases

  • End-to-end evaluation across Foundations, Psychology & UX, Segmentation, Maturity Pathway, Methodology, and Validation using a unified scoring approach.
  • Automatic generation of a structured CLEAR report with actionable recommendations that can feed orchestration workflows like /omni-plan and /production-upgrade.
  • Suitable for software engineering, product planning, and research analyses to improve quality and alignment with goals.

Quick Start

Provide the target artifact and run the evaluation to generate the CLEAR report.

Frequently Asked Questions about agentic-eval

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

FAQPage Schema
What is CLEAR evaluation for code review and research reports?▼

CLEAR evaluation assesses plans, codebases, and research reports across foundations, UX, segmentation, maturity, methodology, and validation dimensions. It scores the target artifact and outputs a structured report with evidence and recommendations.

How do I evaluate a codebase or design document using the CLEAR framework?▼

Provide the target artifact to run the CLEAR evaluation. The system auto-detects the domain, evaluates the artifact across six evidence dimensions, and outputs a structured report to .productionos/EVAL-CLEAR.md.

Can I use CLEAR evaluation for research reports and product planning?▼

Yes, CLEAR evaluation is suitable for software engineering, product planning, and research analyses. It evaluates research reports and design documents by assessing methodology and validation pathways to improve quality and goal alignment.

What is the best way to generate an actionable evaluation report for a software artifact?▼

Run the CLEAR evaluation on your target artifact to generate a structured report. This report includes scores across six dimensions, surfaces gaps, and provides actionable recommendations that can feed orchestration workflows.

Do I need any dependencies to run an end-to-end evaluation on a design document?▼

No dependencies are required. You only need to provide the target artifact for evaluation. The system handles domain auto-detection and outputs the CLEAR report with scores and improvement recommendations automatically.

What output format does the CLEAR evaluation report generate?▼

The CLEAR evaluation outputs a structured markdown report to .productionos/EVAL-CLEAR.md. This report includes scores, evidence, and actionable recommendations for improving the evaluated artifact.

Related Skills

Explore More Software Engineering Skills→
wade56754wade56754

ai-ad-test-gen

Generate pytest test cases from SoT documents and target source code.

Community
Advanced
JeremyDev87JeremyDev87
31

retrospective

Analyze archived session data to generate structured retrospective reports.

Community
Advanced
gesmith0606gesmith0606

gsd-plan-milestone-gaps

Convert milestone audit gaps into prioritized ROADMAP.md phases.

Community
Intermediate
christopherlouetchristopherlouet
5

dev-refactor

Detect code smells and generate refactoring suggestions for JavaScript files.

Community
Intermediate