devlyn:evaluate

Assemble an evaluator team to audit code changes with file:line references.

4|Updated Feb 23, 2026

Search Tags:#evaluation #reporting #evidence #quality-assurance #code-review #team-eval

Ready to run

npx skills add https://github.com/fysoul17/one-query-v1 --skill devlyn-evaluate

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: devlyn:evaluate
Source: https://github.com/fysoul17/one-query-v1/tree/main/onequery/.claude/skills/devlyn%3Aevaluate
Command: npx skills add https://github.com/fysoul17/one-query-v1 --skill devlyn-evaluate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Independent evaluation of work quality by assembling a specialized evaluator team. It enables grading work produced by another session, PR, branch, or changeset, with evaluations that cover correctness, architecture, security, frontend quality, spec compliance, and test coverage. It provides evidence-based findings with file:line references.

Core Features & Use Cases

Assemble a focused evaluator team to audit multiple quality dimensions across code changes.
Produce evidence-backed findings with file:line references for each issue.
Use when someone asks to evaluate, grade, or review changes or wants an independent assessment of recent implementation work.

Quick Start

Assemble the evaluation team and generate a structured report detailing findings and remediation steps.

Frequently Asked Questions about devlyn:evaluate

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

FAQPage Schema

How do I perform an independent code review on a pull request?▼

Independent code review on a pull request is performed by assembling a specialized evaluator team to audit changes and produce evidence-based findings. The evaluation covers correctness, architecture, security, frontend quality, spec compliance, and test coverage.

What is evidence-based work evaluation for software changes?▼

Evidence-based work evaluation is an independent assessment of recent implementation work that produces structured findings with file:line references. It grades code changes across multiple quality dimensions and delivers an outcome-focused report suitable for DevOps workflows.

How do I audit code quality across multiple dimensions like security and architecture?▼

Auditing code quality across security and architecture is done by applying a focused evaluator team to the changeset. This team audits correctness, frontend quality, spec compliance, and test coverage, generating evidence-backed findings with specific file:line references.

Can I generate a structured report for grading a branch or changeset?▼

You can generate a structured report for grading a branch or changeset by assembling an evaluator team to audit the work. The resulting report details findings and remediation steps, making it suitable for integration into DevOps workflows.

Does independent work evaluation require any specific dependencies or setup?▼

Independent work evaluation requires no specific dependencies or setup to function. It operates as a standalone process to audit work produced by another session, PR, branch, or changeset and deliver structured, outcome-focused reports.