Update to Agentic Course Redesign

{
  "name": "course-redesign-assessment",
  "description": "Design and audit constructively aligned, valid, fair, feasible, transparent assessments and rubrics for the current course, including AI-use boundaries and local grading rules. Use for learning objectives, assessment redesign, rubrics, marking, grading, moderation, portfolios, tests, oral exams, or AI-authorship controls.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 271
    }
  ],
  "skill_md_contents": "---\nname: course-redesign-assessment\ndescription: Design and audit constructively aligned, valid, fair, feasible, transparent assessments and rubrics for the current course, including AI-use boundaries and local grading rules. Use for learning objectives, assessment redesign, rubrics, marking, grading, moderation, portfolios, tests, oral exams, or AI-authorship controls.\n---\n\n# Course Redesign Assessment\n\n## Lecturer Decision Dialogue Contract\n\nThe orchestrator is the sole lecturer-facing interface; specialist roles are\nevidence lenses and return questions through it. Ask one unresolved\nconsequential question at a time. Before using a native choice card, follow the\nlive host tool contract. Use a card only when it can present the complete,\nmutually exclusive option set and a custom-answer path without omission. Never\nprune, hide or combine valid choices merely to fit a card. If a native card is\nunavailable or unsupported, its capacity is unknown, or the complete set\nexceeds that capacity, ask the same single question in ordinary chat with every\nvalid numbered option plus `Other - type your answer`, then wait. Every valid\noption remains visible. For very\nlong decisions, use adaptive dependency-based clusters only when choices share\nevidence or constrain one another: keep every valid option visible, explain the\ngrouping and let the lecturer split, merge, reorder or rename it. For example,\noutcomes, assessment evidence, permitted AI use and learning activities belong\ntogether when mutually dependent; student-experience, accessibility and\nactive-learning perspectives may be clustered when participation design\njointly affects usability, inclusion, workload and engagement.\n\nPreserve a custom answer exactly, confirm its canonical interpretation, reflect\nthe consequence, and maintain a decision ledger in the chat and current state.\nShow an editable recap at each cluster or gate end. A skipped or blank response\nleaves a required question unresolved. The safest truthful, evidence-aligned,\nreversible option may be marked `Recommended`, but never preselected; factual\ndeclarations must say \"select only if true,\" and uncertainty fails closed. At\nmajor pedagogical gates, ask for the lecturer's criteria and preliminary view\nbefore recommending when practical. Exact authority gates and approval tokens\nremain separate and unchanged; a dialogue choice never substitutes for them.\n\nDo not assume a national scale, pass threshold, language level, academic level,\ngrade-based model or assessment format. Adapt to school, vocational,\nprofessional, higher-education or other supplied contexts and capture the\ncurrent course's approved rules, including competency/pass/fail systems where\napplicable.\n\n## Live alignment ledger\n\nFrom the first specialist scan, map every stated or inferred outcome to:\n\n- introduction and guided practice;\n- independent practice;\n- student evidence;\n- assessment component and criterion;\n- cognitive demand;\n- points/weight and grade, competency or completion conversion;\n- AI/non-AI condition;\n- accessibility/accommodation; and\n- learner and marker workload.\n\nSeparate current, proposed, superseded, incomplete, teacher-only, and student-facing evidence. A dated test or key is not automatically current or complete.\n\n## Assessment design\n\nFor each component define purpose, stakes, construct, task, conditions, duration, permitted resources, AI boundary, evidence of individual learning, authentication, submission, criteria, raw marks or competency evidence, partial credit where applicable, weighting, grade/competency/completion conversion, moderation or verification, and fallback/accommodation route.\n\nWhen group work is graded, require individually attributable evidence and an individual final grade unless the lecturer explicitly approves another policy.\n\n## AI boundaries\n\nDefine permissions at task-component level. Distinguish:\n\n- AI-free learning/practice;\n- controlled authentication;\n- bounded AI as a critic or stimulus;\n- AI-integrated co-creation; and\n- optional accessibility tools.\n\nDo not treat AI output as evidence of student competence. Where AI is permitted, grade the learner's disciplinary judgement, verification, selection, revision, attribution, and reflection, not prompt cleverness or volume of AI use.\n\n## Rubrics and grading\n\n- Publish criteria and weights before assessed work begins.\n- Align criterion language directly with observable course outcomes.\n- Use analytic raw-point allocations and clear descriptors or anchors.\n- Protect legitimate alternative interpretations.\n- Explain the exact grade formula, pass rule, rounding order, and worked examples.\n- Calibrate markers before and during marking; record boundary decisions.\n- Audit reliability, fairness, language demand, accessibility, time pressure, security, and marking workload.\n\nReturn the updated ledger, learner-facing assessment overview, detailed rubrics or competency criteria, assessor/facilitator guidance, conversion evidence where applicable, validity risks, and decisions requiring lecturer approval.\n"
}