Spawn an independent Evaluator agent to score code artifacts across four axes.
npx skills add https://github.com/jh941213/my-cc-harness --skill eval-jh941213
Please help me install this Agent Skill. Skill: eval Source: https://github.com/jh941213/my-cc-harness/tree/main/skills/eval Command: npx skills add https://github.com/jh941213/my-cc-harness --skill eval-jh941213
Manual, biased evaluation of code outputs is often time-consuming and inconsistent. This Skill automates unbiased assessment by spawning an independent Evaluator to score code artifacts across four axes: functionality, code quality, originality, and usability/security.
Trigger an evaluation on the current project to generate EVAL_REPORT.md with four-axis scores.
High-intent search queries and answers about installing and using this skill.
To objectively evaluate code quality, you can trigger an automated assessment that spawns an independent Evaluator agent to score artifacts across four axes: functionality, code quality, originality, and usability/security.
The four-axis scoring system for code evaluation assesses functionality, code quality, originality, and usability/security. It generates an EVAL_REPORT.md file containing the scores and a concise summary for quick decision making.
You can generate an automated code review report by triggering an evaluation event on your current project. This spawns an autonomous Evaluator agent that analyzes the code artifacts and outputs a consolidated EVAL_REPORT.md.
Automated code assessment is designed specifically for autonomous review workflows. It requires no developer intervention during the evaluation process, making it suitable for continuous code submission and project review pipelines.
You can assess code originality and security in a single evaluation. The Evaluator agent simultaneously scores both originality and usability/security, consolidating the results into one comprehensive report.
You should not use an autonomous code evaluator when manual human oversight is required for subjective design preferences. This system provides objective four-axis scoring focused strictly on functionality, quality, originality, and security.
wahabmalikAutomate post-epic reviews to extract lessons and prepare the next iteration.
FuncSmileAutomate verification and quality assurance checks for software projects.
brianwestphalRun automated validation checks and generate prioritized code quality findings.
xiaoniuge36Analyze code for standards compliance, bugs, performance issues, and security vulnerabilities.
