[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HT3M8CMD8R2063EYF6H9X":3,"skill-same:01M71HT3M8CMD8R2063EYF6H9X":114},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":30,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":60,"commitSha":61,"skillDirectory":62,"forksCount":63,"repositoryHtmlUrl":64,"repositoryHomepageUrl":65,"ownerHtmlUrl":66,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":67,"install":68,"resources":81},"01M71HT3M8CMD8R2063EYF6H9X","syllabus",null,"Generates a curated supplementary reading list from any course syllabus using Consensus academic search. Grill-me intake (syllabus input format + course audience + year range) plus a grouping forcing-options checkpoint before any search runs — so the reading list matches the course's level and recency need. Parses the syllabus to extract topics and learning outcomes, searches Consensus for recent peer-reviewed papers per topic, and produces a professionally formatted .docx with clickable Consensus links, plain-language summaries calibrated to audience level, and Bloom-higher-order discussion questions tied to course learning goals. Use when the user uploads a syllabus, course outline, or curriculum document and wants supplementary readings (e.g., 'create a reading list from this syllabus', 'find recent papers for my course') — even casual mentions with a syllabus attached should trigger this skill.","marshadgani\u002FArshad.AI","marshadgani","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F275367399?v=4","01M71G2BP4YMZ4AX5YY0QBHAZH","01M71G2BPPHHFRMHQAKJTZPGK4",1,"MIT","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fsyllabus\u002FSKILL.md",[17,22,25],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":26,"categoryName":27,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[5,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"create","my","integrity","list","input","reading","audit","options","grill","me","conversion","when","grill-me","grouping","search","papers","consensus","docx","bloom","2026-11-10 10:12:30",false,"---\nname: syllabus\ndescription: \"Generates a curated supplementary reading list from any course syllabus using Consensus academic search. Grill-me intake (syllabus input format + course audience + year range) plus a grouping forcing-options checkpoint before any search runs — so the reading list matches the course's level and recency need. Parses the syllabus to extract topics and learning outcomes, searches Consensus for recent peer-reviewed papers per topic, and produces a professionally formatted .docx with clickable Consensus links, plain-language summaries calibrated to audience level, and Bloom-higher-order discussion questions tied to course learning goals. Use when the user uploads a syllabus, course outline, or curriculum document and wants supplementary readings (e.g., 'create a reading list from this syllabus', 'find recent papers for my course') — even casual mentions with a syllabus attached should trigger this skill.\"\nlicense: MIT\nmetadata:\n  source_spec: \"megaprompts\u002F10-syllabus-megaprompt.md\"\n  build_pattern: \"Path B (direct conversion)\"\n  research_pack_convention: \"Agent Integrity Rules verbatim per PR #657 audit; bundled-JS-DOCX-generator variant\"\n  version: 1.0.0\n---\n\n# Syllabus — Course Supplementary Reading List\n\n> **Portability:** Requires a Consensus MCP connection, Node.js with `docx` package, and file reading capability for the syllabus. Works in Claude Code CLI natively. In Claude.ai with Consensus MCP + Code Execution + file upload, the workflow is supported.\n\nFor an instructor or student with a course syllabus, produce a professional supplementary reading list as `.docx` containing recent peer-reviewed papers per course section.\n\n## Architectural Pattern: Bundled Script\n\nThis skill uses a **bundled JavaScript helper script** for DOCX generation rather than inlining the 300+ lines of layout code:\n\n- DOCX generation logic is reusable + complex\n- Better separation of concerns: skill = orchestration + intelligence; script = mechanical document assembly\n- Token-efficient: skill doesn't re-derive layout each run\n- Easier to maintain and version\n\nThe bundled script is at `scripts\u002Fgenerate_reading_list.js`. The skill orchestrates the pipeline + invokes the script with JSON input.\n\n## Agent Integrity Rules (Research-Pack Convention)\n\nLocked verbatim per PR #657 audit.\n\n- **Only use what Consensus returns.** Every paper title, author, journal, year, URL must come from this session's tool calls. Training-knowledge papers labeled `[Not from Consensus — model knowledge]` and excluded.\n- **Confirm before moving on.** A search isn't complete until response received and inspected.\n- **Track three counts.** Queries sent \u002F papers received \u002F papers cited. Surface in audit summary.\n- **Surface gaps, don't fill them.** Section with one paper + note about limited results > section padded with fabrications.\n\n## Phase 0: Grill-Me Intake (3 forcing questions)\n\n### Q1 (root) — Syllabus input\n\n> **Provide the syllabus — pick one:**\n>\n> 1. File path (PDF, DOCX, text) — I'll read it\n> 2. Pasted content — paste below\n> 3. Image of a printed syllabus — attach the image\n>\n> *Why I'm asking:* Each format needs a different reader (PDF \u002F DOCX parser \u002F vision). Picking upfront prevents wasted attempts.\n\nForcing choice. Refuse to start without a syllabus.\n\n### Q2 (depends on Q1) — Course audience\n\n> **Course audience — pick one:**\n>\n> 1. Undergraduate (intro level)\n> 2. Undergraduate (advanced \u002F upper division)\n> 3. Graduate (Masters \u002F early PhD)\n> 4. Graduate (doctoral \u002F advanced)\n> 5. Professional \u002F continuing education\n> 6. Mixed\n>\n> *Why I'm asking:* Audience dictates summary jargon level and discussion-question complexity. Undergrad summaries define every term; grad summaries assume technical fluency. Discussion questions for undergrads test analysis; for grads test critique and extension.\n\nSee [`references\u002Faudience_calibration.md`](references\u002Faudience_calibration.md) for the canon.\n\n### Q3 (depends on Q1) — Year range\n\n> **Year range for papers — pick one:**\n>\n> 1. Last 1 year (most recent only)\n> 2. Last 2 years (default — recent + a year of context)\n> 3. Last 5 years (broader, includes foundational recent work)\n>\n> *Why I'm asking:* Reading lists go stale fast. 1-year filters keep things fresh; 5-year filters surface foundational recent work that's already standard. Drives the year_min parameter on every Consensus search.\n\nForcing choice with default (last 2 years).\n\n**Stop condition:** 3 questions max before Phase 1. The post-Phase-2 group-and-confirm checkpoint is its own grill-me moment.\n\n## Phase 1: Parse the Syllabus\n\nPer Q1 input format:\n\n- **PDF**: use PDF reader; extract text\n- **DOCX**: use pandoc or DOCX parser; extract text\n- **Text\u002Fpasted**: read directly\n- **Image**: use vision; extract text\n\nFrom extracted text:\n1. Course title + instructor + term\n2. Topic list (lecture titles, week-by-week breakdown, etc.)\n3. Learning outcomes (if explicit; if missing, infer 3-5 from description)\n\nMark inferred learning outcomes as `[inferred]` in the DOCX.\n\n## Phase 2: Group Topics + Confirm with User\n\n### Group via topic_grouper.py\n\nUse `scripts\u002Ftopic_grouper.py` to cluster related topics into 6-12 sections. Heuristic: closely-related topics merge; cross-cutting topics get their own section.\n\n### Group-and-Confirm Checkpoint (Forcing Options)\n\nAfter grouping, present:\n\n> **Proposed sections: [list with item counts]. Pick one:**\n>\n> 1. \"Looks good — proceed with these sections\"\n> 2. \"Merge sections [X] and [Y]\"\n> 3. \"Split section [X] into two\"\n> 4. \"Add a section for [topic]\"\n> 5. \"Remove section [X]\"\n>\n> *Why I'm asking:* Grouping drives search allocation. Wrong grouping wastes the search budget on bad clusters. This is the **last cheap moment** to correct course before searches consume Consensus calls.\n\n**Refuse to start Phase 3 without explicit user choice.**\n\n## Phase 3: Search Consensus per Section\n\nSequential, 1 q\u002Fsec. 1-2 queries per section.\n\n### Applied-Domain Weaving (Critical)\n\nDon't just search the topic — **search the topic + applied domain**:\n\n| ❌ Generic | ✅ Applied-domain |\n|---|---|\n| \"enzyme kinetics\" | \"enzyme kinetics food processing applications\" |\n| \"machine learning\" | \"machine learning clinical decision support\" |\n| \"thermodynamics\" | \"thermodynamics renewable energy systems\" |\n| \"social network analysis\" | \"social network analysis public health interventions\" |\n\nBoosts paper relevance dramatically. See [`references\u002Fapplied_domain_weaving.md`](references\u002Fapplied_domain_weaving.md) for the canon.\n\n### Per-Section Pattern\n\n```\nFor each section:\n  1. Construct query: \"{topic-keywords} {applied-domain-angle}\" + year_min from Q3\n  2. Submit to Consensus (sequential, 1 q\u002Fsec gap enforced by citation_tracker)\n  3. Receive results\n  4. (If thin) submit one fallback query without applied-domain angle\n  5. Select 1-3 papers per section (15-25 total across all sections)\n```\n\n### Selection Priorities\n\n1. **Relevance** — paper directly addresses the section topic\n2. **Reviews \u002F meta-analyses** — synthesize the field\n3. **Citation count** — established work\n4. **Applied-domain connection** — tied to the course's domain (e.g., engineering vs theory)\n\n## Phase 4: Write Summaries + Discussion Questions\n\n### Summary writing\n\nPer paper:\n- Plain language (calibrated to audience from Q2)\n- 2-3 sentences\n- Define jargon if undergraduate audience; assume fluency if graduate\n\n### Quality bars\n\n| ✅ Good summary | ❌ Bad summary |\n|---|---|\n| \"This review maps how different diets — Mediterranean, Nordic, vegetarian — reshape the types of fat molecules circulating in your blood, with implications for heart disease risk.\" | \"This paper reviews lipidomic profiles across dietary interventions and their cardiometabolic implications.\" |\n\n### Discussion question writing\n\nPer paper:\n- Bloom **higher-order** (apply \u002F analyze \u002F evaluate)\n- Tied to a specific course learning outcome\n- Promotes discussion, not just recall\n\n| ✅ Good question | ❌ Bad question |\n|---|---|\n| \"If dietary fat quality can reshape your lipoprotein lipidome, what does this suggest about the biochemical basis for dietary guidelines recommending unsaturated over saturated fats?\" | \"What did the authors find?\" (Just recall) |\n\nUse `scripts\u002Fdiscussion_question_validator.py` to flag recall-only questions.\n\n## Phase 5: Generate .docx via Bundled Script\n\n```bash\nnode scripts\u002Fgenerate_reading_list.js \\\n  --input \u002Ftmp\u002Fsyllabus_data.json \\\n  --output \u002Fpath\u002Fto\u002Freading_list_\u003Ccourse>_\u003Cdate>.docx\n```\n\nThe script accepts JSON with this schema:\n\n```json\n{\n  \"courseTitle\": \"string\",\n  \"courseSubtitle\": \"string\",\n  \"generatedDate\": \"string\",\n  \"yearRange\": \"string\",\n  \"introText\": \"string\",\n  \"learningOutcomes\": [\"string\", ...],\n  \"sections\": [\n    {\n      \"heading\": \"string\",\n      \"papers\": [\n        {\n          \"title\": \"string\",\n          \"authors\": \"string\",\n          \"journal\": \"string\",\n          \"year\": number,\n          \"url\": \"string\",\n          \"summary\": \"string\",\n          \"question\": \"string\"\n        }\n      ]\n    }\n  ],\n  \"auditLog\": {\n    \"totalQueriesSent\": number,\n    \"totalPapersReceived\": number,\n    \"totalPapersCited\": number,\n    \"toolConstraints\": \"string\",\n    \"searchDetails\": [\n      {\n        \"section\": \"string\",\n        \"query\": \"string\",\n        \"papersReturned\": number,\n        \"papersSelected\": number,\n        \"status\": \"string\"\n      }\n    ],\n    \"failures\": []\n  }\n}\n```\n\nThe script handles:\n- `docx` package require with multi-location fallback\n- Title page, intro with Consensus link, learning outcomes box, numbered papers per section\n- `ExternalHyperlink` with full Consensus URLs (never truncated)\n- `LevelFormat.BULLET` for lists (not unicode bullets)\n- Footer with generation metadata\n- Input validation (missing fields → graceful error)\n\nSee [`references\u002Fbundled_script_pattern.md`](references\u002Fbundled_script_pattern.md) for why bundled vs inline.\n\n## Phase 6: Deliver\n\n- File path\n- Audit summary in chat: \"Saved {file}. {N} sections × {M} papers \u002F {K} cited. Plan tier: {tier}.\"\n- Validate: check zip integrity with `python3 -c \"import zipfile,sys; zipfile.ZipFile(sys.argv[1]).testzip()\" \u003Cdocx>` (no output = intact), then confirm the required sections are present\n\n## Tooling\n\n| Script | Role |\n|---|---|\n| `scripts\u002Fcitation_tracker.py` | Consensus three-count audit + 1s sequential discipline at `~\u002F.syllabus_sessions\u002F\u003Csession>.json` |\n| `scripts\u002Ftopic_grouper.py` | Heuristic 6-12 section grouping from extracted topics |\n| `scripts\u002Fdiscussion_question_validator.py` | Bloom higher-order quality check; flags recall-only questions |\n| `scripts\u002Fgenerate_reading_list.js` | **Bundled Node.js DOCX generator** — JSON input → .docx output |\n\n## References\n\n- [`references\u002Fapplied_domain_weaving.md`](references\u002Fapplied_domain_weaving.md) — search-quality canon (7+ sources)\n- [`references\u002Faudience_calibration.md`](references\u002Faudience_calibration.md) — undergrad vs grad summary jargon (7+ sources)\n- [`references\u002Fbundled_script_pattern.md`](references\u002Fbundled_script_pattern.md) — why bundle vs inline (7+ sources)\n\n## Error Handling\n\n| Failure | Behavior |\n|---|---|\n| Consensus rate-limit hit | Wait 3s, retry once, log |\n| Search returns 0 for a section | Note section as \"limited results — consider manual supplementation\" |\n| 3 consecutive failures | Stop, alert user, share collected so far |\n| `docx` package not installed | Script attempts `npm install`; if still failing, fail with clear message |\n| DOCX validation fails | Unpack XML, log issue, ask user to retry |\n| Syllabus format unsupported | List supported formats, ask user to convert |\n| Learning outcomes can't be extracted | Infer 3-5 from course description; mark as inferred in document |\n\n## Anti-Patterns To Reject\n\n- Parallelizing Consensus calls (rate limit)\n- Searching topics without applied-domain angle (poor relevance)\n- Padding sections with fabricated entries when Consensus returns thin\n- Generic discussion questions (\"What did the authors find?\")\n- Jargon-heavy summaries unsuitable for the course's audience level\n- Skipping the group-and-confirm step (wastes searches)\n- Truncating Consensus URLs in hyperlinks\n- Inlining 300 lines of docx-generation JavaScript in the skill body (use bundled script)\n\n---\n\n**Version:** 1.0.0\n**Source spec:** `megaprompts\u002F10-syllabus-megaprompt.md` (maintainer-local draft spec — gitignored, not present in the public repository)\n**Build pattern:** Path B (direct conversion). Bundled-JS-DOCX-generator variant.\n","# Syllabus — Course Supplementary Reading List\n\n> **Portability:** Requires a Consensus MCP connection, Node.js with `docx` package, and file reading capability for the syllabus. Works in Claude Code CLI natively. In Claude.ai with Consensus MCP + Code Execution + file upload, the workflow is supported.\n\nFor an instructor or student with a course syllabus, produce a professional supplementary reading list as `.docx` containing recent peer-reviewed papers per course section.\n\n## Architectural Pattern: Bundled Script\n\nThis skill uses a **bundled JavaScript helper script** for DOCX generation rather than inlining the 300+ lines of layout code:\n\n- DOCX generation logic is reusable + complex\n- Better separation of concerns: skill = orchestration + intelligence; script = mechanical document assembly\n- Token-efficient: skill doesn't re-derive layout each run\n- Easier to maintain and version\n\nThe bundled script is at `scripts\u002Fgenerate_reading_list.js`. The skill orchestrates the pipeline + invokes the script with JSON input.\n\n## Agent Integrity Rules (Research-Pack Convention)\n\nLocked verbatim per PR #657 audit.\n\n- **Only use what Consensus returns.** Every paper title, author, journal, year, URL must come from this session's tool calls. Training-knowledge papers labeled `[Not from Consensus — model knowledge]` and excluded.\n- **Confirm before moving on.** A search isn't complete until response received and inspected.\n- **Track three counts.** Queries sent \u002F papers received \u002F papers cited. Surface in audit summary.\n- **Surface gaps, don't fill them.** Section with one paper + note about limited results > section padded with fabrications.\n\n## Phase 0: Grill-Me Intake (3 forcing questions)\n\n### Q1 (root) — Syllabus input\n\n> **Provide the syllabus — pick one:**\n>\n> 1. File path (PDF, DOCX, text) — I'll read it\n> 2. Pasted content — paste below\n> 3. Image of a printed syllabus — attach the image\n>\n> *Why I'm asking:* Each format needs a different reader (PDF \u002F DOCX parser \u002F vision). Picking upfront prevents wasted attempts.\n\nForcing choice. Refuse to start without a syllabus.\n\n### Q2 (depends on Q1) — Course audience\n\n> **Course audience — pick one:**\n>\n> 1. Undergraduate (intro level)\n> 2. Undergraduate (advanced \u002F upper division)\n> 3. Graduate (Masters \u002F early PhD)\n> 4. Graduate (doctoral \u002F advanced)\n> 5. Professional \u002F continuing education\n> 6. Mixed\n>\n> *Why I'm asking:* Audience dictates summary jargon level and discussion-question complexity. Undergrad summaries define every term; grad summaries assume technical fluency. Discussion questions for undergrads test analysis; for grads test critique and extension.\n\nSee [`references\u002Faudience_calibration.md`](references\u002Faudience_calibration.md) for the canon.\n\n### Q3 (depends on Q1) — Year range\n\n> **Year range for papers — pick one:**\n>\n> 1. Last 1 year (most recent only)\n> 2. Last 2 years (default — recent + a year of context)\n> 3. Last 5 years (broader, includes foundational recent work)\n>\n> *Why I'm asking:* Reading lists go stale fast. 1-year filters keep things fresh; 5-year filters surface foundational recent work that's already standard. Drives the year_min parameter on every Consensus search.\n\nForcing choice with default (last 2 years).\n\n**Stop condition:** 3 questions max before Phase 1. The post-Phase-2 group-and-confirm checkpoint is its own grill-me moment.\n\n## Phase 1: Parse the Syllabus\n\nPer Q1 input format:\n\n- **PDF**: use PDF reader; extract text\n- **DOCX**: use pandoc or DOCX parser; extract text\n- **Text\u002Fpasted**: read directly\n- **Image**: use vision; extract text\n\nFrom extracted text:\n1. Course title + instructor + term\n2. Topic list (lecture titles, week-by-week breakdown, etc.)\n3. Learning outcomes (if explicit; if missing, infer 3-5 from description)\n\nMark inferred learning outcomes as `[inferred]` in the DOCX.\n\n## Phase 2: Group Topics + Confirm with User\n\n### Group via topic_grouper.py\n\nUse `scripts\u002Ftopic_grouper.py` to cluster related topics into 6-12 sections. Heuristic: closely-related topics merge; cross-cutting topics get their own section.\n\n### Group-and-Confirm Checkpoint (Forcing Options)\n\nAfter grouping, present:\n\n> **Proposed sections: [list with item counts]. Pick one:**\n>\n> 1. \"Looks good — proceed with these sections\"\n> 2. \"Merge sections [X] and [Y]\"\n> 3. \"Split section [X] into two\"\n> 4. \"Add a section for [topic]\"\n> 5. \"Remove section [X]\"\n>\n> *Why I'm asking:* Grouping drives search allocation. Wrong grouping wastes the search budget on bad clusters. This is the **last cheap moment** to correct course before searches consume Consensus calls.\n\n**Refuse to start Phase 3 without explicit user choice.**\n\n## Phase 3: Search Consensus per Section\n\nSequential, 1 q\u002Fsec. 1-2 queries per section.\n\n### Applied-Domain Weaving (Critical)\n\nDon't just search the topic — **search the topic + applied domain**:\n\n| ❌ Generic | ✅ Applied-domain |\n|---|---|\n| \"enzyme kinetics\" | \"enzyme kinetics food processing applications\" |\n| \"machine learning\" | \"machine learning clinical decision support\" |\n| \"thermodynamics\" | \"thermodynamics renewable energy systems\" |\n| \"social network analysis\" | \"social network analysis public health interventions\" |\n\nBoosts paper relevance dramatically. See [`references\u002Fapplied_domain_weaving.md`](references\u002Fapplied_domain_weaving.md) for the canon.\n\n### Per-Section Pattern\n\n```\nFor each section:\n  1. Construct query: \"{topic-keywords} {applied-domain-angle}\" + year_min from Q3\n  2. Submit to Consensus (sequential, 1 q\u002Fsec gap enforced by citation_tracker)\n  3. Receive results\n  4. (If thin) submit one fallback query without applied-domain angle\n  5. Select 1-3 papers per section (15-25 total across all sections)\n```\n\n### Selection Priorities\n\n1. **Relevance** — paper directly addresses the section topic\n2. **Reviews \u002F meta-analyses** — synthesize the field\n3. **Citation count** — established work\n4. **Applied-domain connection** — tied to the course's domain (e.g., engineering vs theory)\n\n## Phase 4: Write Summaries + Discussion Questions\n\n### Summary writing\n\nPer paper:\n- Plain language (calibrated to audience from Q2)\n- 2-3 sentences\n- Define jargon if undergraduate audience; assume fluency if graduate\n\n### Quality bars\n\n| ✅ Good summary | ❌ Bad summary |\n|---|---|\n| \"This review maps how different diets — Mediterranean, Nordic, vegetarian — reshape the types of fat molecules circulating in your blood, with implications for heart disease risk.\" | \"This paper reviews lipidomic profiles across dietary interventions and their cardiometabolic implications.\" |\n\n### Discussion question writing\n\nPer paper:\n- Bloom **higher-order** (apply \u002F analyze \u002F evaluate)\n- Tied to a specific course learning outcome\n- Promotes discussion, not just recall\n\n| ✅ Good question | ❌ Bad question |\n|---|---|\n| \"If dietary fat quality can reshape your lipoprotein lipidome, what does this suggest about the biochemical basis for dietary guidelines recommending unsaturated over saturated fats?\" | \"What did the authors find?\" (Just recall) |\n\nUse `scripts\u002Fdiscussion_question_validator.py` to flag recall-only questions.\n\n## Phase 5: Generate .docx via Bundled Script\n\n```bash\nnode scripts\u002Fgenerate_reading_list.js \\\n  --input \u002Ftmp\u002Fsyllabus_data.json \\\n  --output \u002Fpath\u002Fto\u002Freading_list_\u003Ccourse>_\u003Cdate>.docx\n```\n\nThe script accepts JSON with this schema:\n\n```json\n{\n  \"courseTitle\": \"string\",\n  \"courseSubtitle\": \"string\",\n  \"generatedDate\": \"string\",\n  \"yearRange\": \"string\",\n  \"introText\": \"string\",\n  \"learningOutcomes\": [\"string\", ...],\n  \"sections\": [\n    {\n      \"heading\": \"string\",\n      \"papers\": [\n        {\n          \"title\": \"string\",\n          \"authors\": \"string\",\n          \"journal\": \"string\",\n          \"year\": number,\n          \"url\": \"string\",\n          \"summary\": \"string\",\n          \"question\": \"string\"\n        }\n      ]\n    }\n  ],\n  \"auditLog\": {\n    \"totalQueriesSent\": number,\n    \"totalPapersReceived\": number,\n    \"totalPapersCited\": number,\n    \"toolConstraints\": \"string\",\n    \"searchDetails\": [\n      {\n        \"section\": \"string\",\n        \"query\": \"string\",\n        \"papersReturned\": number,\n        \"papersSelected\": number,\n        \"status\": \"string\"\n      }\n    ],\n    \"failures\": []\n  }\n}\n```\n\nThe script handles:\n- `docx` package require with multi-location fallback\n- Title page, intro with Consensus link, learning outcomes box, numbered papers per section\n- `ExternalHyperlink` with full Consensus URLs (never truncated)\n- `LevelFormat.BULLET` for lists (not unicode bullets)\n- Footer with generation metadata\n- Input validation (missing fields → graceful error)\n\nSee [`references\u002Fbundled_script_pattern.md`](references\u002Fbundled_script_pattern.md) for why bundled vs inline.\n\n## Phase 6: Deliver\n\n- File path\n- Audit summary in chat: \"Saved {file}. {N} sections × {M} papers \u002F {K} cited. Plan tier: {tier}.\"\n- Validate: check zip integrity with `python3 -c \"import zipfile,sys; zipfile.ZipFile(sys.argv[1]).testzip()\" \u003Cdocx>` (no output = intact), then confirm the required sections are present\n\n## Tooling\n\n| Script | Role |\n|---|---|\n| `scripts\u002Fcitation_tracker.py` | Consensus three-count audit + 1s sequential discipline at `~\u002F.syllabus_sessions\u002F\u003Csession>.json` |\n| `scripts\u002Ftopic_grouper.py` | Heuristic 6-12 section grouping from extracted topics |\n| `scripts\u002Fdiscussion_question_validator.py` | Bloom higher-order quality check; flags recall-only questions |\n| `scripts\u002Fgenerate_reading_list.js` | **Bundled Node.js DOCX generator** — JSON input → .docx output |\n\n## References\n\n- [`references\u002Fapplied_domain_weaving.md`](references\u002Fapplied_domain_weaving.md) — search-quality canon (7+ sources)\n- [`references\u002Faudience_calibration.md`](references\u002Faudience_calibration.md) — undergrad vs grad summary jargon (7+ sources)\n- [`references\u002Fbundled_script_pattern.md`](references\u002Fbundled_script_pattern.md) — why bundle vs inline (7+ sources)\n\n## Error Handling\n\n| Failure | Behavior |\n|---|---|\n| Consensus rate-limit hit | Wait 3s, retry once, log |\n| Search returns 0 for a section | Note section as \"limited results — consider manual supplementation\" |\n| 3 consecutive failures | Stop, alert user, share collected so far |\n| `docx` package not installed | Script attempts `npm install`; if still failing, fail with clear message |\n| DOCX validation fails | Unpack XML, log issue, ask user to retry |\n| Syllabus format unsupported | List supported formats, ask user to convert |\n| Learning outcomes can't be extracted | Infer 3-5 from course description; mark as inferred in document |\n\n## Anti-Patterns To Reject\n\n- Parallelizing Consensus calls (rate limit)\n- Searching topics without applied-domain angle (poor relevance)\n- Padding sections with fabricated entries when Consensus returns thin\n- Generic discussion questions (\"What did the authors find?\")\n- Jargon-heavy summaries unsuitable for the course's audience level\n- Skipping the group-and-confirm step (wastes searches)\n- Truncating Consensus URLs in hyperlinks\n- Inlining 300 lines of docx-generation JavaScript in the skill body (use bundled script)\n\n---\n\n**Version:** 1.0.0\n**Source spec:** `megaprompts\u002F10-syllabus-megaprompt.md` (maintainer-local draft spec — gitignored, not present in the public repository)\n**Build pattern:** Path B (direct conversion). Bundled-JS-DOCX-generator variant.\n",{"name":5,"license":14,"metadata":55,"description":7},{"version":56,"source_spec":57,"build_pattern":58,"research_pack_convention":59},"1.0.0","megaprompts\u002F10-syllabus-megaprompt.md","Path B (direct conversion)","Agent Integrity Rules verbatim per PR #657 audit; bundled-JS-DOCX-generator variant","claude\u002Fai-personal-assistant-main","fb33f7f5b3a206eb019c788e3c48e91c02ccb1f9",".claude\u002Fskills\u002Fclaude-skills\u002Fsyllabus",0,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI","https:\u002F\u002Farshad-ai-seven.vercel.app","https:\u002F\u002Fgithub.com\u002Fmarshadgani","2026-11-02 00:51:35",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":80},[70,73,76],{"tool":71,"command":72},"npx","npx skills add marshadgani\u002FArshad.AI --skill syllabus",{"tool":74,"command":75},"bunx","bunx skills add marshadgani\u002FArshad.AI --skill syllabus",{"tool":77,"command":78},"pnpm","pnpm dlx skills add marshadgani\u002FArshad.AI --skill syllabus","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fsyllabus\u002FSKILL.md",true,[82,88,92,96,102,106,110],{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fapplied_domain_weaving.md","REFERENCE","参考文档",8232,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fsyllabus\u002Freferences\u002Fapplied_domain_weaving.md",{"path":89,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Faudience_calibration.md",10240,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fsyllabus\u002Freferences\u002Faudience_calibration.md",{"path":93,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fbundled_script_pattern.md",7280,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fsyllabus\u002Freferences\u002Fbundled_script_pattern.md",{"path":97,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Fcitation_tracker.py","SCRIPT","脚本",8343,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fsyllabus\u002Fscripts\u002Fcitation_tracker.py",{"path":103,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fdiscussion_question_validator.py",8866,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fsyllabus\u002Fscripts\u002Fdiscussion_question_validator.py",{"path":107,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Fgenerate_reading_list.js",13810,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fsyllabus\u002Fscripts\u002Fgenerate_reading_list.js",{"path":111,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Ftopic_grouper.py",7125,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fsyllabus\u002Fscripts\u002Ftopic_grouper.py",[115,148,174,202,230,254],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":119,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":129,"publishedAt":147},"01M71MVWH15PQRS9KT3J24D7WV","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[123,126],{"categoryNo":124,"categoryName":125,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":127,"categoryName":128,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146],"webapp","testing","webapp testing","for","applications","local","frontend","debugging","toolkit","logs","browser","with","playwright","web","behavior","ui","screenshots","2026-11-10 10:56:23",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":119,"licenseFileUrl":152,"sourceHtmlUrl":153,"categories":154,"keywords":156,"publishedAt":147},"01M71MVMAZ1J606SGA4JPHRDAZ","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[155],{"categoryNo":127,"categoryName":128,"taxonomyType":20,"taxonomyTypeDesc":21},[157,158,159,143,160,161,162,133,163,164,136,165,166,167,168,169,170,171,172,173],"builder","artifacts builder","artifacts","web artifacts builder","single-file","css","Tailwind","ui components","single","use","file","components","react","multi","state","routing","state management",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":178,"sourceHtmlUrl":179,"categories":180,"keywords":187,"publishedAt":147},"01M71MSTFAEYT9J9GA587SP3RB","ui-styling","Create beautiful, accessible user interfaces with shadcn\u002Fui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fui-styling\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fui-styling\u002FSKILL.md",[181,184],{"categoryNo":182,"categoryName":183,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":185,"categoryName":186,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000032","设计师",[188,189,145,162,163,190,191,192,193,194,195,196,42,168,197,31,198,199,200,201],"ui styling","styling","mode","canvas","implementing","design","themes","utility","design systems","across","component","layout","forms","patterns",{"skillNo":203,"name":193,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":213,"publishedAt":147},"01M71MSM72HXKQRCY5D45WYPNP","Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social\u002Fads\u002Fweb\u002Fprint), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fdesign\u002FSKILL.md",[207,210,211,212],{"categoryNo":208,"categoryName":209,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":182,"categoryName":183,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":185,"categoryName":186,"taxonomyType":28,"taxonomyTypeDesc":29},[193,214,215,216,188,217,218,219,220,31,221,222,223,224,225,226,227,228,145,229],"Media","tiktok","actions","logo","logo generation","chart","multi-platform","ads","youtube","generate","presentations","google","atlas cloud","screenshot","muapi","identity",{"skillNo":231,"name":232,"nameZh":6,"description":233,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":234,"categories":235,"keywords":238,"publishedAt":147},"01M71MSH9T7S227MN2YSYB2EP5","design-system","Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing\u002Ftypography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fdesign-system\u002FSKILL.md",[236,237],{"categoryNo":182,"categoryName":183,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":185,"categoryName":186,"taxonomyType":28,"taxonomyTypeDesc":29},[193,239,240,162,241,242,243,244,198,224,245,246,247,248,249,250,251,133,252,253],"design system","system","css variables","creation","Variables","architecture","systematic","token","spacing","layer","typography","brand","three","tokens","slide generation",{"skillNo":255,"name":256,"nameZh":6,"description":257,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":258,"categories":259,"keywords":262,"publishedAt":147},"01M71MSCFZ1HFMNBDMAFXDZV92","banner-design","Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter\u002FX, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fbanner-design\u002FSKILL.md",[260,261],{"categoryNo":182,"categoryName":183,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":185,"categoryName":186,"taxonomyType":28,"taxonomyTypeDesc":29},[193,263,264,214,265,266,267,216,268,269,270,271,272,273,31,221,222,223,38,274],"banner","banner design","3D","direction","neon","Art","social","generated","hero","dimensions","display","website"]