from my-cc-harness122
Spawns an independent evaluator agent to score code outputs on functionality, code quality, originality, and usability/security, producing a structured EVAL_REP
This skill provides an evaluation harness that spawns a separate evaluator agent to independently assess code artifacts across four axes: functional accuracy, code quality, originality, and usability & security. The evaluator produces a numeric score and a written report (EVAL_REPORT.md), with recommendations and a pass/conditional/fail verdict.
Use when you need an automated, repeatable assessment of generated or submitted code — for grading, CI checks, or quality gates. Trigger on keywords like eval, quality score, code evaluation, or when a project requires an impartial scoring pass before merge or release.
Designed for multi-agent or subagent-capable systems (agents that can spawn evaluator subagents), and helpful for developer-assistants and CI-integrated bots (Claude-style agents, acp harnesses, other orchestrators).
A Korean-language skill that spawns an evaluator subagent to score code outputs across 4 axes (functionality, quality, originality, usability/security). No bundled scripts to test. The SKILL.md is self-contained with clear steps but lacks error handling guidance and has loose output contracts. Niche audience due to language and toolchain specificity.
Clean skill with no security concerns. Limited by Korean-only documentation and reliance on external evaluator agent config. Architecture is basic — single file, no scripts or references directories.
