github-featured/wanshuiyin--auto-claude-code-research-in-sleep

Files

T

Ruofeng Yang 966d45109a docs: hoist 4 optional integrations out of README to docs/integrations/

Move Vast.ai, Zotero, Obsidian (+arXiv), and Feishu/Lark setup details
out of the main README into per-integration guides under
docs/integrations/. Each section in README is now a 8-12 line teaser
that explains the value prop and lists what's covered at the
destination, so users can decide whether to click through before being
buried in setup steps.

Both READMEs:
- README.md Setup section: 558 → 315 lines
- README_CN.md 安装 section: 444 → 254 lines
- Net diff: +92 / −525 across both READMEs

New docs (EN + CN parity):
- docs/integrations/VAST_GPU_GUIDE.md / _CN.md (also new to CN, which
  previously had no Vast.ai content)
- docs/integrations/ZOTERO.md / _CN.md
- docs/integrations/OBSIDIAN.md / _CN.md (includes arXiv built-in section)
- docs/integrations/FEISHU.md / _CN.md

All in-page anchor links (News, Features, Awesome Community Skills)
re-pointed from #-zotero-integration-optional style anchors to direct
doc URLs.

No functional change: same MCP install commands, same CLAUDE.md
snippets, same fallback behavior. Move-only refactor.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-17 13:05:45 +08:00

2.9 KiB

Raw Permalink Blame History

Obsidian + arXiv Integration (Optional)

🇨🇳 中文版：OBSIDIAN_CN.md Plugs into /research-lit and the upstream skills that call it. Pairs naturally with the Zotero integration.

If you use Obsidian for research notes, /research-lit can search your vault for paper summaries, tagged references, and your own insights. These are usually more valuable than raw papers because they already encode your judgments.

Recommended MCP server

mcpvault (760⭐, no Obsidian app needed, 14 tools, BM25 search)

# Add to Claude Code (point to your vault path)
claude mcp add obsidian-vault -s user -- npx @bitbonsai/mcpvault@latest /path/to/your/vault

Optional complement: obsidian-skills

obsidian-skills (13.6k⭐, by Obsidian CEO) — teaches Claude to understand Obsidian-specific Markdown (wikilinks, callouts, properties). Copy to your vault:

git clone https://github.com/kepano/obsidian-skills.git
cp -r obsidian-skills/.claude /path/to/your/vault/

What it enables in `/research-lit`

🔍 Search your vault for notes on the research topic
🏷️ Find notes by tags (e.g., #paper-review, #diffusion-models)
📝 Read your processed summaries and insights (more valuable than raw papers)
🔗 Follow wikilinks to discover related notes

Fallback: no Obsidian

Without Obsidian configured, /research-lit automatically skips it and works as before. No errors, no warnings.

Combined Zotero + Obsidian workflow

Many researchers use Zotero for paper storage and Obsidian for notes. Both integrations work simultaneously — /research-lit checks Zotero first (raw papers + annotations), then Obsidian (your processed notes), then local PDFs, then web search. See ZOTERO.md for the Zotero half.

arXiv (built-in, no setup)

/research-lit automatically queries the arXiv API for structured metadata (title, abstract, full author list, categories) — richer than web search snippets. No setup required.

By default, only metadata is fetched (no files downloaded). To also download the most relevant PDFs:

/research-lit "topic" — arxiv download: true                    # download top 5 PDFs
/research-lit "topic" — arxiv download: true, max download: 10  # download up to 10

For standalone arXiv access, use the dedicated /arxiv skill:

/arxiv "attention mechanism"           # search
/arxiv "2301.07041" — download         # download specific paper

/research-lit — primary consumer
/arxiv — standalone arXiv search/download
/idea-discovery — uses /research-lit internally

2.9 KiB Raw Permalink Blame History