What is hebrew-md-to-pptx?

A converter that turns slide-formatted Markdown text into a basic PowerPoint presentation, including right-to-left layout for Hebrew and mixed Hebrew-English text.

It is for making .pptx slide decks from Markdown files, with slide titles, body text, speaker notes, and optional templates.

It avoids manually fixing text direction, punctuation placement, and language settings when creating Hebrew slides.

hebrew-md-to-pptx — Skill for Claude Code by AssafTzurEl

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add AssafTzurEl/assaf-agent-skills --skill hebrew-md-to-pptx

Clone the repo

git clone --depth 1 https://github.com/AssafTzurEl/assaf-agent-skills

Made for: Claude Code.

Or install hebrew-md-to-pptx, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/assaftzurel/assaf-agent-skills/hebrew-md-to-pptx/github.svg)](https://agentmods.dev/skills/assaftzurel/assaf-agent-skills/hebrew-md-to-pptx)

Your own site

<a href="https://agentmods.dev/skills/assaftzurel/assaf-agent-skills/hebrew-md-to-pptx"><img src="https://agentmods.dev/badge/skills/assaftzurel/assaf-agent-skills/hebrew-md-to-pptx/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/assaftzurel/assaf-agent-skills/hebrew-md-to-pptx"><img src="https://agentmods.dev/badge/skills/assaftzurel/assaf-agent-skills/hebrew-md-to-pptx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 163 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,853 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00163	$0.01853
Opus 5.5	$0.00065	$0.00741
Sonnet 5.5	$0.00033	$0.00371
Haiku 4.5	$0.00016	$0.00185

Measured 27d ago against content hash bde5e12bbe9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hebrew-md-to-pptx scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 27d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (md_to_pptx_he.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

hebrew-md-to-pptx/skills/hebrew-md-to-pptx/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hebrew slide-Markdown → PPTX

Converts a Markdown deck written in the slide-authoring format into a clean, RTL-aware .pptx skeleton. This is the slide counterpart of the hebrew-md-to-docx skill, and the inverse of pptx-to-slide-md (so a deck can round-trip: PPTX → slide-Markdown → PPTX).

Why this skill exists

Pasting slide-Markdown into PowerPoint forces the user to right-align every Hebrew paragraph by hand, and still leaves bugs: punctuation and brackets around English (ו-CTO., [^]) drift to the wrong side, and every Hebrew word is underlined as a spelling mistake because the runs carry no Hebrew language tag. This skill fixes all of that at the OOXML level and lays out one slide per block with the title, body, and speaker notes in the right places.

How to use

The converter is md_to_pptx_he.py (Python 3; needs python-pptx, mistune, and Pillow):

pip install python-pptx mistune Pillow --break-system-packages   # if needed
python md_to_pptx_he.py INPUT.md -o OUTPUT.pptx

Options:

--template DECK.pptx – build on a template so the output inherits a specific theme, fonts, and slide layouts (see below). Without it, python-pptx's plain default theme is used.
--overrides overrides.json – pin the base direction of ambiguous paragraphs ({ "3": "rtl", "12": "ltr" }, keyed by the index printed to stderr).
--code-font Consolas – monospace font for code spans/blocks. Default Consolas.

Slide size: without a template the deck is 16:9 widescreen (13.33"×7.5"), and the title/body placeholders are widened to fill it. With --template, the template's own slide size and layouts are kept as-is.

By default, run the converter without --template — it uses python-pptx's plain default theme, since the output is meant to be styled afterwards anyway. Only use --template DECK.pptx if the user explicitly asks for a specific template, theme, fonts, or layouts to be applied.

Input format

The document is a sequence of slide blocks. --- on its own line separates slides; === separates a slide's body from its speaker notes.

Read the full file on GitHub · 162 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

27d ago First seen · 162 lines · 163 tokens per session scan A bde5e12bbe9f

Subscribe to this mod's changes

hebrew-md-to-pptx is a skill published in the GitHub repository AssafTzurEl/assaf-agent-skills (2 stars, last pushed 29d ago), licensed MIT. It adds 163 tokens to every session and 1,853 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-10.

Documents Localization

hebrew-md-to-pptx next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hebrew-md-to-pptxAssafTzurEl/assaf-agent-skills	Skill	2	29d ago	MIT	A	163	Claude Code
translate-bookdeusyu/translate-book	Skill	2.3k	8d ago	MIT	A	42	Claude Code
pdf_translatorForceInjection/AI-fundamentals	Skill	3.3k	yesterday	Apache-2.0	A	47	Claude Code, Codex
translate-docsCherryHQ/cherry-studio	Skill	53k	yesterday	AGPL-3.0	A	42	Claude Code, Codex
azure-ai-translation-document-pybenjaminasterA/antigravity-awesome-skills	Skill	461	yesterday	MIT	A	0	Claude Code, Codex
docutranslateznlgis/opengis-skills	Skill	76	10d ago	MIT	A	119	Claude Code, Codex
lov-academic-translatorlovstudio/skills	Skill	72	3d ago	MIT	A	87	Claude Code, Codex