Update to Agentic Course Redesign

{
  "name": "course-redesign-materials",
  "description": "Produce and independently validate approved editable course materials in formats required by the supplied context, including documents, slides, PDFs, worksheets, assessment files and facilitator guides. Use after exact-target approval for design, citations, media, accessibility, formatting, rendering or package QA.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 254
    }
  ],
  "skill_md_contents": "---\nname: course-redesign-materials\ndescription: Produce and independently validate approved editable course materials in formats required by the supplied context, including documents, slides, PDFs, worksheets, assessment files and facilitator guides. Use after exact-target approval for design, citations, media, accessibility, formatting, rendering or package QA.\n---\n\n# Course Redesign Materials\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\nStart only after Gate 3 has approved the exact typed material targets: working\ncopies under `04_Working_Copies/` and accepted releases under `05_Approved/`.\nGate 2B research-target approval is not production authority. Verify the\nrecorded plan and targets, then enter the named gate for the first artefact; do\nnot add an unlabeled second approval pause. Never edit protected sources; work\nfrom copies into the approved dated output root.\nUse the terminology, format, accessibility standard, device/print conditions\nand facilitator role supplied by the current school, vocational, professional,\nhigher-education or other course. Do not assume a literary subject, academic\nsemester, university classroom or teacher/student naming convention.\n\n## Preserve and improve\n\n- Preserve worthwhile pedagogy, lecturer voice, period/discipline structure, authentic examples, media, links, and style cues.\n- Use an explicit image-retention/omission register rather than blindly dropping or reinserting assets.\n- Preserve aspect ratios; crop intentionally and document derived assets.\n- Do not show production notes such as \"retained from source\", donor-slide IDs, prompts, or internal QA language to students.\n- Preserve exact source artefacts where fidelity matters; add only approved,\n  context-appropriate explanation, scaffolding or alternatives without silently\n  changing the source.\n\n## Human-centred design\n\n- Design for the actual learners, setting, devices, print use, and teacher workflow.\n- Give handwriting/stylus fields enough physical space; test at 100% scale.\n- Keep one clear task and purpose at a time, realistic lesson timing, and visible assessment status.\n- Use semantic headings, logical reading order, descriptive links, meaningful alt text, sufficient contrast, and non-colour cues.\n- Avoid cramped tables, arbitrary mid-word wrapping, tiny text, distorted media, and inaccessible image-only instructions.\n\n## Citations and rights\n\n- Use the approved citation style consistently.\n- In Word, use real superscript footnote references and the approved footnote size; make DOI/URL targets live.\n- In PowerPoint, use readable markers/short source text where appropriate, full notes/reference slides, and real hyperlink relationships.\n- Keep factual verification and rights/redistribution status separate.\n\n## Assessment security\n\nUse separate student and teacher targets. Scan visible text, editable layers, text boxes, comments, notes, metadata, alt text, hidden objects, model responses, and derived PDFs for key leakage. Accessible assessment derivatives must expose only the assigned item, never an entire secure bank.\n\n## QA gate\n\nFor every deliverable:\n\n1. reopen it in the intended application;\n2. verify it is editable;\n3. export the intended PDF/derivative;\n4. render and inspect every page or slide;\n5. test links, notes/footnotes, headings, language, contrast, alt text, reading order, response space, tables, media, citations, and metadata;\n6. compare points/criteria/weights/timings/AI states across all files;\n7. verify source hashes unchanged and no unapproved extras/caches in release folders; and\n8. commission independent, read-only pedagogical/factual/accessibility/visual/package audits.\n\nCorrect direct defects, rerender, rerun targeted and regression checks, and report hashes, counts, limitations, and unresolved lecturer decisions. Do not promote a failing candidate.\n"
}