{"id":77074,"plugin_id":"plugins_6ab405a6785081918aefad75d5faeef5","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-03T00:12:22.661Z","digest":"fe0ee05a11aa9a04de3f33fcf56939cc7901449d235454f217467054cd32b481","against":null,"payload":{"description":"Evaluate technical or behavioral practice answers fairly with evidence and actionable corrections.","included_files":[],"name":"feedback-and-rubric","skill_md_contents":"---\nname: feedback-and-rubric\ndescription: Evaluate technical or behavioral practice answers fairly with evidence and actionable corrections.\n---\n\n# Feedback And Rubric\n\n\nScore only observable parts of the answer against the task-specific rubric. State what is correct, what is missing or technically wrong, and why. Separate dimensions: correctness, reasoning, trade-offs, test coverage, ownership evidence, communication. For mock coding use `../../references/coding-interview-rubric.md`; for system design `../../references/system-design-rubric.md`; for conversation delivery `../../references/feedback-calibration.md`.\n\nIf a numeric rubric is requested, ratings are coaching heuristics, not predicted job outcomes or company hiring scores. When evidence is absent, mark not assessed rather than zero. Do not run deterministic scripts unless a proper executable environment is available. Do not invent code execution, test outcomes or interviewer intentions.\n\nConclude with a concrete rewrite/repair and 1–3 targeted drills. Prefer fewer high-impact suggestions to generic praise.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}