stderr**. One stray `console.log` corrupts the stream.
- **FTS is book-level only** (no PDF page / EPUB spine location) and **not enabled** on this library yet.
Calibre has **no OCR**; PDF
widget. Tables come out as plain markdown.
- **B. Standalone deliverable** — a downloadable HTML file, PDF, Excel dashboard: anything that outlives the conversation as a file. Here the whole skill applies
/dev/null -w "%{http_code}" -L `.
- **Beware filename-pattern assumptions.** The `st_ r_<år>.pdf` series ("Statistiske tabeller", 1828–1860, pre-NOS) is documented as a separate convention from
reusable agentic patterns for Copilot Chat. Each issue exists in parallel formats: HTML email, PDF, Viva Amplify content, architecture diagram, and interactive portal page. The `PRODUCTION_PLAYBOOK.md` is the authoritative reference
pattern: `Job_Description-[Company]-[Role].md`
After generating each `.tex` file:
- Compile to PDF using `pdflatex` (run twice for proper cross-references)
- Clean up all auxiliary files
sessions, and a **methodology block** so the report explains itself away from the dashboard. **"PDF" is the browser's own print-to-PDF** (`?print=1` opens the dialog on load
techniques (typography, layout, color, etc.) | When making design decisions |
| `scripts/` | Puppeteer export scripts (PNG, PDF, carousel) | At export time |
| `templates/` | Starter HTML templates for common formats | When starting
Download a bbcswebdav URL directly |
| `blackboard_upload_attempt_file` | Upload a local file (image, PDF, etc.) and get a fileUploadId |
| `blackboard_save_attempt_draft` | Save text/files to an attempt WITHOUT
Universal document converter | De facto standard for markdown-to-anything. Handles EPUB, DOCX, PDF, LaTeX, Typst, HTML. One tool covers most export needs and has a large ecosystem of filters
stored XSS against the staff
sessions that live there. The case that bites is PDF: browsers open it in a
viewer that runs JavaScript. Three things hold it, each with
MatchFastPath`.
**Python is no longer needed on the compression path** (v0.11.3). ADR
0015 moved PDF text extraction to native Go and ADR 0016 ported
`cordon-filter`, closing both
pdf-toolkit-mcp
## 1. Project Overview
**What**: A write-capable, zero-config, TypeScript-native MCP server for PDF manipulation. Provides 22 tools for reading, modifying, creating, and rendering PDFs — including
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.