portals.yml` | Query and company config |
| `templates/cv-template.html` | HTML template for CVs |
| `generate-pdf.mjs` | Playwright: HTML to PDF |
| `article-digest.md` | Compact proof points from portfolio (optional) |
| `interview-prep/story-bank.md` | Accumulated STAR+R stories across
label":"Model","tone":"warn"}]
```
- **File** Shows an actual file: a PDF through the system's PDF engine, an image as an image, anything that decodes as text as text
DSGVO-Konformität auftreten und wie wir sie mindern können.
```
Falsches Verhalten: Das PDF analysieren und die Frage beantworten.
Richtiges Verhalten: Einen optimierten Prompt erzeugen, der später gegen das PDF gefahren
ingest/ # staging; operator drops material here
original/{slug}.source.md # required — frontmatter sidecar
original/{slug}.{pdf,epub,...} # optional — present only when redistributed
converted/{slug}.md # required — what Pass C reads
references
HTML bodies to Markdown: JSON and plain text inline, plus the `feed`/`image`/`pdf` subpackages (RSS/Atom/JSON feeds, image manifests, PDF text via `third_party/pdf`).
- `internal/reduce` — readability extraction + bluemonday sanitize (`Article
implementation of the same app. Users write LaTeX in a CodeMirror editor, compile to PDF via a cloud compiler, and can ask an AI assistant to create/edit files for them
Form.io REST endpoint and navigates into the relevant reference by scope (platform, project, runtime, pdf).
The library's default "build me an app" entry point is [`plugin/skills/formio-application/`](plugin/skills/formio-application/) — a framework
template-only sync |
### Reading Large PDFs
When agents need to analyze large PDF files (>10 pages), use the `pages` parameter:
```
Read /path/to/doc.pdf
pages: "1-20"
```
Large PDFs (>10 pages) return
TLDraw canvas
6. Executes workflows AUTONOMOUSLY after approval
7. Generates outputs in multiple formats (PDF, PPT, JSON)
### Orchestrator Agent
Location: `.claude/agents/orchestrator.md`
The Orchestrator coordinates all other agents and skills
single `STREAM read_files(...)` via a temp streaming view. Reference: `pipelines/sql/01_bronze.sql` (`raw_pdf_arrivals` view); Auto Loader docs: https://docs.databricks.com/aws/en/ingestion/cloud-object-storage/auto-loader/.
- **Section normalization**: `pipelines/sql/03_gold_classify_extract.sql` POSEXPLODES `parsed:sections[*]` and represents sectionless
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.