HarryoungHarryoung/efka/skills/document-conversion/SKILL.md

document-conversion

Skill104 starsChanged 10 months agoApache-2.0View on GitHub

Convert DOC/DOCX/PDF/PPT/PPTX documents to Markdown format. Automatically detect PDF type (electronic/scanned), extract images to separate directory. Use this Skill when administrator onboards non-Markdown documents. Trigger condition: Onboard DOC/DOCX/PDF/PPT/PPTX format files.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
If success: false, report error and end
line 51
Very specific:
If success: true, record generated file path and image directory
line 52
Very specific:
Not passing --original-name will cause incorrect image reference paths
line 57

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Document Format Conversion

Convert various document formats to Markdown for knowledge base onboarding.

Supported Formats

Format	Processing Method
DOCX	Pandoc conversion, preserve formatting and images
DOC	LibreOffice → DOCX → Pandoc
PDF Electronic	PyMuPDF4LLM fast conversion
PDF Scanned	PaddleOCR-VL online OCR
PPTX	pptx2md professional conversion
PPT	LibreOffice → PPTX → pptx2md

Usage

python .claude/skills/document-conversion/scripts/smart_convert.py \
    <temp_path> \
    --original-name "<original_filename>" \
    --json-output

Parameters:

<temp_path>: Temporary file path (e.g. /tmp/kb_upload_xxx.pptx)
--original-name: Must pass original filename, used to generate correct image directory name
--json-output: Output JSON format result

Output Format

{
  "success": true,
  "markdown_file": "/path/to/output.md",
  "images_dir": "original_filename_images",
  "image_count": 5,
  "input_file": "/path/to/input.pptx"
}

Processing Flow

Execute conversion command (must use --original-name and --json-output)
Parse JSON output, check success field
If success: false, report error and end
If success: true, record generated file path and image directory

Important Notes

Image directory uses original filename naming (e.g. 培训资料_images/)
Not passing --original-name will cause incorrect image reference paths
PDF type is automatically detected, scanned version processing is slower (tens of seconds to minutes)

Format Details

Detailed processing instructions for each format, see FORMATS.md

Download now (ZIP)

Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
nimadorostkar/Claude-Skills-collection★ 33same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- backend/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- frontend/CLAUDE.mdCLAUDE.md
- skills/CLAUDE.mdCLAUDE.md
- batch-notificationSkill
- excel-parserSkill
- expert-routingSkill
- large-file-tocSkill
- satisfaction-feedbackSkill

Does it work?

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

Reviews can't be read right now.

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.

Check your setup, free