CodeArena evaluation skill

Evaluate each project implementation against two independent rubrics — a generic Basic /100 and a per-round, requirement-specific Round /100 (each plus up to +10 dynamic bonus) — and produce a bilingual (EN + CN) report. This skill bundles the full standard, rubrics, report template, and probe scripts.

0. Required resources (all inside this skill)

• references/EVAL_STANDARDS.md — the authoritative standard (workflow, hard rules, baselined-tool table). Read before evaluating.
• references/basic_eval_cases.md — static Basic rubric (B1 Security 30 / B2 Visual 18 / B3 Code Quality 30 / B4 Governance 10 / B5 Test Coverage 12). Reused verbatim every round.
• references/report_template.md — report template (three sections).
• references/scoring_overview.md — scoring breakdown.
• references/example_round_eval_cases.md — a sample round rubric (0→1 requirement) to model new round cases on.
• scripts/ — generic libs lib/ (http/ui/port-detect), per-round templates/ (api/ui/visual skeletons), screenshot tool cap.mjs, readiness check check-tools.sh, installer setup-tools.sh (see §4, §5).

1. Workflow (every round MUST follow these steps, in order)

Paths are relative to the working root (where the projects under review and EvalSets/ live); <round> is the short round id chosen by the user.