community example · Use or study

convert-pdf-to-md

Prepare PDF text and extracted images for a later reading or analysis task.

github/awesome-copilotskills/convert-pdf-to-md/SKILL.md

Before you use it

Input: An explicitly identified PDF file or PDF folder, plus an agreed output location and the analysis you will do afterward.
Expected output: The source describes a Markdown file and image appendix per PDF. Conversion is separate from answering questions about the document.
Prerequisites: The setup file describes Python 3.10+, MarkItDown and PyMuPDF. Its requirements file uses minimum versions, not exact pins. The script replaces an existing destination directory; review the path and protect existing output before use. No conversion was run here.

Client setup and runtime behavior are not verified here; client installation is not individually established. The use notes below describe source preparation, inputs and limits.

Publisher documentation, static file observations and environment tests are different kinds of evidence. Runtime behavior has not been observed.

Use this method

Source-based preparation, not an installation or a completed run. Nothing is executed here.

Good fit for: Investigating a PDF-to-Markdown workflow for documents with an extractable text layer and separately reviewed image output.
Not for / limits: Not an OCR solution or a layout-preserving converter. The inspected script deletes an existing output directory before writing. Extracted images can be incomplete even when text conversion succeeds; runtime results and dependency safety are untested.
Prepare: Confirm the exact PDF input and a destination containing nothing you need to retain; review the linked setup and script before authorizing execution in your own environment.
Apply: Start with one document under your own approved setup. The source offers batch and recursive modes, but do not treat a mixed-format folder as fully processed by this PDF-only method.
Check: Inspect the Markdown and image appendix against the original, check individual failures, and only then perform the intended summary or analysis.

Sources read for this note

These exact files were read as text at the displayed commit. Other files and external tools were not reviewed. A repository LICENSE observation does not confirm Skill-specific applicability or dependency rights.

skills/convert-pdf-to-md/SKILL.md ↗
Read 2026-09-10T10:33:29.954Z
adadaec52cb7bda8b03254df12eae421d58fd85b6e5c96e57f494ee42216b6a1
skills/convert-pdf-to-md/references/setup.md ↗
Read 2026-09-10T10:33:30.812Z
1870e60e0d5d832cab342c8598c11650c8cd54eb998c98952a8a2626da3d0ed4
skills/convert-pdf-to-md/scripts/requirements.txt ↗
Read 2026-09-10T10:33:31.076Z
622ed8ada047607acd6f41777348fb13a9e751a112a538854a8ace7b3011592f
skills/convert-pdf-to-md/scripts/convert_pdf_to_md.py ↗
Read 2026-09-10T10:33:31.172Z
9ea864b8815e39e5d85e7146d913aad1440a18f587102a4e712d4664c5a07df1
LICENSE ↗
Read 2026-09-10T10:33:31.265Z
e32449d23085399adc1222f7a17408b730550258e51627c153cb108ca9955823

Study the method

Compare the instructions with convert_one and the image-appendix code. Note how text conversion, image extraction and partial-batch failure are separate; an image appendix does not establish reliable inline image placement.

4 files in the observed scope; 2 in scripts/, 1 in references/, 0 in assets/.

Directory evidence checked 2026-09-08T14:47:50.063Z. Filenames and folder counts were observed; in that earlier check, helper file bodies were not read or executed. Later individual reads, when present, are listed in the use notes.

Zero files in scripts/ does not mean no execution, network access or file writes. Markdown and other folders may describe or contain executable behavior.

Source version and requirements

Observed: 2026-09-08T11:55:57.465Z
Source commit: f38fb6cf039b835990d0f49dc161d7c2af99ef69
Content SHA-256: adadaec52cb7bda8b03254df12eae421d58fd85b6e5c96e57f494ee42216b6a1
License: Unknown
Author attribution: Repository owner: github. Individual authorship is not independently established.

This page describes a pinned source snapshot, not the latest repository state. Changes after this commit have not been reconciled here. A repository license does not necessarily cover external models, datasets or services.

Open current repository ↗

Reference note and manual copy

Public reference only

convert-pdf-to-md
Prepare PDF text and extracted images for a later reading or analysis task.
Source owner: github
Repository: github/awesome-copilot
Path: skills/convert-pdf-to-md/SKILL.md
Source commit: f38fb6cf039b835990d0f49dc161d7c2af99ef69
Observed: 2026-09-08T11:55:57.465Z
Source: https://github.com/github/awesome-copilot/blob/f38fb6cf039b835990d0f49dc161d7c2af99ef69/skills/convert-pdf-to-md/SKILL.md
License: Unknown
Requirements: The setup file describes Python 3.10+, MarkItDown and PyMuPDF. Its requirements file uses minimum versions, not exact pins. The script replaces an existing destination directory; review the path and protect existing output before use. No conversion was run here.
Runtime behavior: not observed
Input: An explicitly identified PDF file or PDF folder, plus an agreed output location and the analysis you will do afterward.
Expected output: The source describes a Markdown file and image appendix per PDF. Conversion is separate from answering questions about the document.
Good fit for: Investigating a PDF-to-Markdown workflow for documents with an extractable text layer and separately reviewed image output.
Not for / limits: Not an OCR solution or a layout-preserving converter. The inspected script deletes an existing output directory before writing. Extracted images can be incomplete even when text conversion succeeds; runtime results and dependency safety are untested.
Prepare: Confirm the exact PDF input and a destination containing nothing you need to retain; review the linked setup and script before authorizing execution in your own environment.
Apply: Start with one document under your own approved setup. The source offers batch and recursive modes, but do not treat a mixed-format folder as fully processed by this PDF-only method.
Check: Inspect the Markdown and image appendix against the original, check individual failures, and only then perform the intended summary or analysis.
Study: Compare the instructions with convert_one and the image-appendix code. Note how text conversion, image extraction and partial-batch failure are separate; an image appendix does not establish reliable inline image placement.
Notes summarized: 2026-09-10T10:35:06Z
Source content SHA-256: adadaec52cb7bda8b03254df12eae421d58fd85b6e5c96e57f494ee42216b6a1
Read at this commit: skills/convert-pdf-to-md/SKILL.md | 2026-09-10T10:33:29.954Z | SHA-256 adadaec52cb7bda8b03254df12eae421d58fd85b6e5c96e57f494ee42216b6a1
Read at this commit: skills/convert-pdf-to-md/references/setup.md | 2026-09-10T10:33:30.812Z | SHA-256 1870e60e0d5d832cab342c8598c11650c8cd54eb998c98952a8a2626da3d0ed4
Read at this commit: skills/convert-pdf-to-md/scripts/requirements.txt | 2026-09-10T10:33:31.076Z | SHA-256 622ed8ada047607acd6f41777348fb13a9e751a112a538854a8ace7b3011592f
Read at this commit: skills/convert-pdf-to-md/scripts/convert_pdf_to_md.py | 2026-09-10T10:33:31.172Z | SHA-256 9ea864b8815e39e5d85e7146d913aad1440a18f587102a4e712d4664c5a07df1
Read at this commit: LICENSE | 2026-09-10T10:33:31.265Z | SHA-256 e32449d23085399adc1222f7a17408b730550258e51627c153cb108ca9955823
Read evidence is not execution, compatibility or a Skill-specific license grant.

Repository license evidence

MIT text was read in the nearest repository license file at this commit. Skill-specific applicability has not been confirmed. This is not a redistribution grant for the Skill or its external services.

Read observed license file ↗

License evidence checked: 2026-09-08T14:47:50.063Z
License file SHA-256: e32449d23085399adc1222f7a17408b730550258e51627c153cb108ca9955823