syllabus — Claude Code plugin: what it does, how to install
Generates curated supplementary reading lists from course syllabi as formatted DOCX files using Consensus academic search.
/plugin marketplace add alirezarezvani/claude-skills
/plugin install syllabus@claude-code-skillsWhat syllabus does
The plugin extracts topics and learning outcomes from syllabi provided as PDF, DOCX, text, or images. Before querying literature, it prompts you to confirm the target audience level and publication year range. Topics are organized into 6 to 12 sections with a checkpoint allowing you to merge or drop sections.
For each section, sequential queries run against Consensus at one request per second. Queries weave applied domains into terms to surface practical papers. Summary difficulty adjusts to the audience: undergraduate summaries define unfamiliar terminology, while graduate summaries retain technical academic language.
Delivery produces a formatted .docx file assembled by a bundled Node.js script. The document includes direct Consensus URLs and discussion prompts aligned with Bloom's taxonomy. Without Consensus MCP, literature retrieval fails. Assembling the document also requires npm install docx.
What it helps with
- Extract topics and learning goals from course outlines
- Retrieve peer-reviewed papers using Consensus academic search
- Generate a structured DOCX reading list with clickable links
- Calibrate study summaries for undergraduate or graduate students
Example prompts for the agent
- Create a supplementary reading list from
syllabus.pdffor undergraduate students - Find recent peer-reviewed papers for the topics in
curriculum.docx - Update my syllabus
course_outline.txtwith recent research from the last 3 years
How to install syllabus
Plugin marketplace
/plugin marketplace add alirezarezvani/claude-skills/plugin install syllabus@claude-code-skillsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about syllabus
How do I install syllabus in Claude Code?
First, register the marketplace source using /plugin marketplace add alirezarezvani/claude-skills. Then install the plugin by running /plugin install syllabus@claude-code-skills.
What does the syllabus plugin do?
It reads course outlines, searches Consensus for peer-reviewed studies per topic, and writes audience-tailored summaries into a formatted .docx document.
What external tools does syllabus require?
You need Consensus MCP for literature searches and Node.js with the docx library installed via npm install docx. Syllabi in PDF or DOCX format also require pandoc or a document parser.
Source text
syllabus · MIT
# syllabus
Course supplementary reading list generator. Takes any course syllabus (PDF / DOCX / text / image) and produces a curated `.docx` of recent peer-reviewed papers via Consensus search, with plain-language summaries calibrated to audience level + Bloom-higher-order discussion questions tied to learning outcomes.
## What this skill does
1. **Phase 0 grill-me** (3 forcing Qs): syllabus input format + course audience + year range
2. **Phase 1**: parse syllabus (PDF/DOCX/text/image) → extract topics + learning outcomes
3. **Phase 2**: group topics into 6-12 sections + grill-me forcing checkpoint (proceed/merge/split/add/remove)
4. **Phase 3**: targeted Consensus searches per section (1-2 queries each, sequential at 1 q/sec, **applied-domain weaving**)
5. **Phase 4**: write summaries (audience-calibrated jargon) + discussion questions (Bloom higher-order)
6. **Phase 5**: generate .docx via **bundled JS script** (`scripts/generate_reading_list.js`)
7. **Phase 6**: deliver file + audit summary
## Architectural pattern: bundled JS
This skill uses a **bundled JavaScript helper script** (`scripts/generate_reading_list.js`) for DOCX generation rather than inlining the 300+ lines of layout code in SKILL.md. Rationale:
- DOCX generation logic is reusable + complex
- Better separation of concerns: skill = orchestration + intelligence; script = mechanical document assembly
- Token-efficient: skill doesn't re-derive layout each run
- Easier to maintain and version
The skill orchestrates the pipeline and invokes the script with JSON input.
## Sibling skill relationship
Part of the **research pack** (sibling of `pulse`, `litreview`, `grants`, `patent`, `dossier`). Shares Agent Integrity Rules. Adds:
- **Audience calibration** — undergrad summaries define every term; grad summaries assume technical fluency
- **Applied-domain weaving** — search "X applications" not just "X" (boosts relevance dramatically)
- **Bundled JS script pattern** — first research-pack skill to use this layout
## Source spec
`megaprompts/10-syllabus-megaprompt.md` (maintainer-local draft spec — gitignored, not in the public repo) (PR #657).
## Plugin layout
```
research/syllabus/
├── .claude-plugin/plugin.json
├── README.md
├── agents/cs-syllabus.md
├── commands/cs-syllabus.md
└── skills/syllabus/
├── SKILL.md
├── references/
│ ├── applied_domain_weaving.md ← search-quality canon (7+ sources)
│ ├── audience_calibration.md ← undergrad vs grad summary jargon (7+ sources)
│ └── bundled_script_pattern.md ← why bundle vs inline (7+ sources)
└── scripts/
├── citation_tracker.py ← stdlib: Consensus three-count + 1s sequential
├── topic_grouper.py ← stdlib: heuristic 6-12 section grouping
├── discussion_question_validator.py ← stdlib: Bloom higher-order quality check
└── generate_reading_list.js ← bundled Node.js: DOCX assembly (~300 lines)
```
## Dependencies
- **Consensus MCP** — Required for literature search
- **Node.js with `docx` package** — Required (`npm install docx`)
- **Bundled script** — `scripts/generate_reading_list.js` (shipped with skill, not external)
- **File reading** — PDF reader / DOCX parser via pandoc / vision for images
## License
MIT.
© Alireza Rezvani · MIT · alirezarezvani/claude-skills
