presets + range math live in
`lib/report.ts`. Every number is real (no fabricated cost/token/SLA metrics).
PDF export is `window.print()` + the `@media print` block in `globals.css`
(isolates `.report-print-area`, reveals
graph structures
- Create flowcharts, mind maps, network diagrams
**3. Ebook MCP (Optional):**
- EPUB and PDF processing
- Extract chapters and content from ebooks
- Useful for literature note creation
**Search Strategy Decision
recipe for each case, plus the commands (`serve-*`, `capture-*`, `video-*`, `variants-*`, `measure-*`, `compare-*`, `terminal`, `pdf`), the scenario table, the document-assembly schema, and how to extend the mocks when
portals.yml` | Query and company config |
| `templates/cv-template.html` | HTML template for CVs |
| `tools/generate-pdf.mjs` | Puppeteer: HTML to PDF |
| `article-digest.md` | Compact proof points from portfolio (optional) |
| `interview-prep/story-bank.md` | Accumulated STAR+R stories across
sanitized human-browser fallback in addition to Exa for dynamic pages, source verification, PDF downloads, ecommerce pages, maps, and tables. Store only distilled source evidence.
## Configuration
**`.claude/settings.local.json`** controls
implementation is done.
Tier 2 in this repo:
- **OCR routing** — what sends a PDF down the Surya path, the silent-`fitz`-failure detection,
`--force-surya`. It only exists
into a shareable one-page summary | ~1 min |
| `/autodecision:publish` | Ship a brief as PDF → Notion, email draft, gist, Slack, Drive, or Local | ~1 min |
| `/autodecision:plan` | Interactive setup wizard
GitHub repositories, remote URLs, and any file format supported by docling — DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, and more) — extracts entities — delegates to `/bedrock:preserve` |
| `/bedrock:preserve` | Single write
prefer Mermaid (renders everywhere). Fallback to ASCII art
- Max line width: 100 characters (for PDF rendering)
### Length Guidelines
- Module total: **800-1500 words** (sweet spot for 20-40 min reading
Project Is
The Curator is a local Node.js web application that ingests text sources (PDF, MD, TXT) and automatically builds an interconnected knowledge wiki. The wiki is stored as plain
citation graphs
- Hugging Face datasets search
- Web search and page crawling
- LaTeX compilation and PDF reading
- LLM-powered document QA and research proposal workflows
**Tech Stack:**
- Python 3.12+ with type
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.