ワンクリックでManusで任意のスキルを実行

始める

docling

スター2

フォーク1

更新日2026年2月2日 21:42

Expert guidance on document processing with Docling and audio transcription with Whisper.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

FullFran

FullFran/Hybrid-RAG-example

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Docling & Ingestion Expert Skill

This skill provides patterns for processing diverse document formats and audio files.

📝 Document Processing

Multi-format support: Use docling for converting PDF, DOCX, PPTX, XLSX, HTML, and Markdown to a clean Markdown representation.
HybridChunker: Always use Docling's HybridChunker to preserve document structure (headings, lists, tables).
Token Awareness: Configure chunker with max_tokens=512 to align with embedding models (e.g., text-embedding-3-small).

🔊 Audio Transcription

Whisper ASR: Use docling's integration with Whisper Turbo for transcribing audio files (.mp3, .wav, .m4a, .flac).
Path Handling: Pass pathlib.Path objects to DocumentConverter for audio files.

🏗️ Pipeline Architecture

Ingestion Pipeline: Centralize logic in src/ingestion/ingest.py.
Metadata Extraction: Extract YAML frontmatter and standard document properties.
Batching: Use batch embedding generation and insert_many for chunks to optimize performance.

このリポジトリの他の Skills

同じリポジトリ

architecture-decision-record

FullFran/Hybrid-RAG-example

Help the team document and maintain Architecture Decision Records (ADRs).

2026-02-022

docs-standard

FullFran/Hybrid-RAG-example

Standard for creating technical documentation in this repository. Use this when writing new documentation in docs/ to ensure consistent hierarchy and formatting.

2026-02-022

mermaid-diagrams

FullFran/Hybrid-RAG-example

Expert guidance on creating accurate, visually polished Mermaid diagrams for architecture documentation.

2026-02-022

mongodb

FullFran/Hybrid-RAG-example

Expert guidance on MongoDB implementation for RAG, including aggregation pipelines and search patterns.

2026-02-022

pydantic-ai

FullFran/Hybrid-RAG-example

Expert guidance on building agents and tools with Pydantic AI.

2026-02-022

python-async-patterns

FullFran/Hybrid-RAG-example

Best practices for async Python code, avoiding common pitfalls like await precedence bugs and sync-in-async anti-patterns.

2026-02-022

name	docling
description	Expert guidance on document processing with Docling and audio transcription with Whisper.

Docling & Ingestion Expert Skill

This skill provides patterns for processing diverse document formats and audio files.

📝 Document Processing

Multi-format support: Use docling for converting PDF, DOCX, PPTX, XLSX, HTML, and Markdown to a clean Markdown representation.
HybridChunker: Always use Docling's HybridChunker to preserve document structure (headings, lists, tables).
Token Awareness: Configure chunker with max_tokens=512 to align with embedding models (e.g., text-embedding-3-small).

🔊 Audio Transcription

Whisper ASR: Use docling's integration with Whisper Turbo for transcribing audio files (.mp3, .wav, .m4a, .flac).
Path Handling: Pass pathlib.Path objects to DocumentConverter for audio files.

🏗️ Pipeline Architecture

Ingestion Pipeline: Centralize logic in src/ingestion/ingest.py.
Metadata Extraction: Extract YAML frontmatter and standard document properties.
Batching: Use batch embedding generation and insert_many for chunks to optimize performance.