baem1n/langchain-langgraph-deepagents-notebooks/multimodal-rag

Claude Code and agent skill by baem1n/langchain-langgraph-deepagents-notebooks

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Multimodal PDF RAG guide for slide-level indexing with extracted text, images, tables, and grounded slide citations.

Install

npx vskill@latest install baem1n/langchain-langgraph-deepagents-notebooks/multimodal-rag

SKILL.md

Skill tools note: metadata.include_tools is a space-separated Deep Agents field. The tools become visible only after this skill is read or pinned, and the agent or SkillsMiddleware must provide matching tool implementations.

Multimodal PDF RAG Skill

공개 강의 PDF/PPTX-export PDF를 슬라이드 단위로 인덱싱하는 예제용 규칙.

워크플로

  1. PDF 확보: 공개 URL을 캐시에 다운로드하고 PDF 헤더를 검증한다.
  2. 슬라이드 단위 추출: PyMuPDF4LLM to_markdown(page_chunks=True)로 1페이지 = 1 Document를 만든다.
  3. 이미지 보강: write_images=True로 추출 이미지를 저장하고, PyMuPDF 렌더링으로 슬라이드 대표 이미지를 만든다.
  4. 표 보강: Markdown 표 블록을 분리해 metadata.table_count와 본문 섹션에 넣는다.
  5. LLM 이미지 설명: 비전 지원 ChatOpenAI로 슬라이드/이미지를 한국어 설명으로 변환해 검색 텍스트에 합친다.
  6. LangChain v1 RAG: InMemoryVectorStore + @tool(response_format="content_and_artifact") + create_agent()를 사용한다.

안전 규칙

  • 원본 공개 PDF는 저장소에 커밋하지 않고 .cache/ 아래에 런타임 캐시로 둔다.
  • 이미지 설명은 슬라이드 텍스트와 이미지를 근거로 작성하고, 보이지 않는 정보는 추측하지 않는다.
  • 검색 답변에는 슬라이드 번호를 반드시 포함한다.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
69
Repository forks
15
7-day trend score
20

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/baem1n/langchain-langgraph-deepagents-notebooks/multimodal-rag/badge)](https://verified-skill.com/skills/baem1n/langchain-langgraph-deepagents-notebooks/multimodal-rag)

Something wrong with this skill or its page? Tell us.