Reframe README as the AI-assisted research center

Document the project as a git-backed research workspace: collect sources by
topic, convert to markdown, synthesize with Claude over whole files, commit
everything. Topics open-ended; demonology is the primary one today.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

README.md

@@ -1,29 +1,54 @@
-# Research library: PDF → markdown for Claude-assisted synthesis
+# My AI-Assisted Research Center
 
-Local, git-tracked workflow. Drop text PDFs into topic folders, convert them to
+A local, **git-backed** research workspace where I collect source material by
-markdown, then have Claude Code **read whole files** to cross-reference and
+topic, convert it to clean markdown, and have **Claude Code read whole files** to
-synthesize across a topic — instead of chunked RAG, which gave shallow results.
+cross-reference and synthesize across a subject — instead of chunked RAG, which
+gave shallow results.
+
+Everything that matters is versioned in git: the converted markdown, the
+conversion tooling, and any syntheses Claude produces. Source PDFs stay local
+(see below). The repo is the durable record; Claude is the analyst working over
+it.
+
+**Topics:** TBD and growing. The primary one today is **demonology**. The layout
+is topic-per-folder so the same workflow scales to any subject — add a folder,
+drop in sources, convert, ask.
+
+## How it works
+
+1. **Collect** — drop text PDFs into `pdfs/<topic>/`.
+2. **Convert** — `python convert.py` mirrors them into `md/<topic>/` as markdown
+   (headings, lists, tables, and `-----` page boundaries preserved).
+3. **Synthesize** — point Claude Code at `md/<topic>/` and ask it to read the
+   whole topic and produce something. It saves the result back into the folder.
+4. **Commit** — markdown sources and syntheses go into git.
 
 ## Layout
 
 ```
-demonology/
+research-center/
   pdfs/<topic>/*.pdf     # source PDFs (gitignored — kept local, not committed)
-  md/<topic>/*.md        # converted markdown — the files Claude reads
+  md/<topic>/*.md        # converted markdown + saved syntheses — what Claude reads
-  convert.py             # batch converter
+  convert.py             # batch PDF→markdown converter
-  requirements.txt       # pins pymupdf4llm
+  requirements.txt       # pins the converter (pymupdf4llm)
   needs-ocr.txt          # generated: PDFs with no text layer (gitignored)
   README.md
 ```
 
-Group PDFs into topic subfolders under `pdfs/` (e.g. `pdfs/angelology/`). The
+Group sources into topic subfolders under `pdfs/` (e.g. `pdfs/demonology/`,
-converter mirrors that structure into `md/`. A flat `pdfs/` (no subfolders) works
+`pdfs/alchemy/`). The converter mirrors that structure into `md/`. A flat
-too — it just produces a flat `md/`. Current topics: `demonology/`. Add more by
+`pdfs/` (no subfolders) works too — it just produces a flat `md/`.
-creating a new `pdfs/<topic>/` and dropping PDFs in.
 
-> **PDFs are gitignored.** They are large and copyrighted, so only the generated
+**Add a new topic:**
-> markdown is committed. Keep your PDFs backed up outside git. To version the
+
-> PDFs too, remove `pdfs/` from `.gitignore` (consider git-lfs first).
+```bash
+mkdir pdfs/<topic>     # drop PDFs in
+python convert.py      # converts only the new files into md/<topic>/
+```
+
+> **PDFs are gitignored.** They are large and often copyrighted, so only the
+> generated markdown is committed. Keep your PDFs backed up outside git. To
+> version the PDFs too, remove `pdfs/` from `.gitignore` (consider git-lfs first).
 
 ## Setup
 
@@ -63,7 +88,9 @@ Per topic, ask things like:
 > folder."
 
 The markdown keeps headings, lists, tables, and page boundaries (`-----`
-separators) so Claude can cite locations while reading entire files.
+separators) so Claude can cite locations while reading entire files. Syntheses
+Claude writes land alongside the sources in `md/<topic>/` and get committed too —
+so the research center accumulates both raw material and worked analysis.
 
 ## Fallbacks