agentleFS
FullFranFullFran/Agent-skills-POC/.agents/skills/docling/SKILL.md

docling

Skill1 starsChanged 10 months agoMITView on GitHub

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

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Multi-format support: Use docling for converting PDF, DOCX, PPTX, XLSX, HTML, and Markdown to a clean Markdown representation.

    line 12
  2. Very specific:

    HybridChunker: Always use Docling's HybridChunker to preserve document structure (headings, lists, tables).

    line 13
  3. Very specific:

    Whisper ASR: Use docling's integration with Whisper Turbo for transcribing audio files (.mp3, .wav, .m4a, .flac).

    line 18
  4. Very specific:

    Batching: Use batch embedding generation and insert_many for chunks to optimize performance.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.