talksmith:md-to-deck

talksmith:md-to-deck is a skill for Claude Code, Codex from veigap/talksmith. It costs 89 tokens per session (9,402 once invoked), scanned A, original, MIT.

A renderer that turns a Talk's final.md Markdown file into either a PowerPoint presentation or an HTML/Reveal.js deck. Reveal.js is a web format for slide presentations, and the renderer can also create a live view from draft.md.

In plain words
What is it for?
Use it to build and audit native .pptx files, generate HTML slide decks, preview a draft, and classify slides against the project's template catalogue.
Why use it?
It converts cleaned presentation content into viewable slides while applying the selected rendering style and slide templates.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the talksmith plugin — 13 skills, 1 command, 8 agents shipped together

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.

agentmods
npx agentmods add skills/veigap/talksmith/md-to-deck
Any agent
npx skills add veigap/talksmith --skill md-to-deck
Clone the repo
git clone --depth 1 https://github.com/veigap/talksmith

Made for: Claude Code, Codex.

Or install talksmith, the plugin that ships this one along with the rest of its 13 skills, 1 command, 8 agents.

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.

agentmods badge for talksmith:md-to-deck

README.md
[![agentmods](https://agentmods.dev/badge/skills/veigap/talksmith/md-to-deck.svg)](https://agentmods.dev/skills/veigap/talksmith/md-to-deck)
Your own site
<a href="https://agentmods.dev/skills/veigap/talksmith/md-to-deck"><img src="https://agentmods.dev/badge/skills/veigap/talksmith/md-to-deck.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,402 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00089 $0.09402
Opus 5 $0.00044 $0.04701
Sonnet 5 $0.00018 $0.01880
Haiku 4.5 $0.00009 $0.00940

Measured today against content hash 806f7be8872a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

talksmith:md-to-deck 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 today.

The scan reads SKILL.md. This mod also ships 15 executable files (_chrome.py, audits/_model.py, audits/block_coverage.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.

skills/md-to-deck/SKILL.md · 446 lines

How it starts

The opening of the file, as written. The whole thing — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.

md-to-deck — render final.md to a presentation

This skill turns a Talk's cleaned final.md into a presentation. There is one render and two exports measured from it:

  • RENDER — the HTML deck. A styled HTML / Reveal.js deck built by code (build_html.py) from the structured slide-model.json. Needs only Python + jinja2. This is also the live in-progress view (from draft.md, --draft) the orchestrator auto-fires at Step 5.5. It is the deliverable and the source of truth for how a slide looks.
  • EXPORT — PDF and .pptx, on request. Both are derived from the rendered deck, not re-specified: a headless browser lays the deck out and export_pdf.py prints it, while export_pptx.py measures the laid-out page and rebuilds it as native PowerPoint shapes — real, editable text, not pictures of slides. Needs Chrome (or any Chromium); the .pptx also needs python-pptx and Pillow.

Why "measured" and not "rendered again". The .pptx used to be authored by an LLM following a 1143-line prose spec that restated every geometry rule in EMU, checked by five OOXML audits. A card's corner radius had to be changed twice, in two languages, and verified by a third. Now there is one layout engine and the exports cannot disagree with it.

Every slide is classified against the shared catalog slide-templates.md and rendered as the matched template; the universal invariant (labeled enumerations → cards, never plain bullets) always holds.

What a render is asked for — two independent parameters

Neither is mandatory, and neither is written into draft.md or final.md: the same content can be rendered any way at any time.

Parameter Values Default
formats: html (always produced) plus any of pdf, pptx html
style: the deck's visual skin: default, or any file under templates/html/styles/ — currently business, editorial, forest, ocean, sunset, terminal default
theme: light, dark light

Read the full file on GitHub · 446 lines

Files

What ships with it

60 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.

  1. today Changed · +66 lines · -20 tokens per session 806f7be8872a
  2. 5d ago First seen · 380 lines · 109 tokens per session scan A 97bcf6dfc26e

Subscribe to this mod's changes

talksmith:md-to-deck is a skill published in the GitHub repository veigap/talksmith (10 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 9,402 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

baoyu-youtube-transcript

Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…

JimLiu/baoyu-skills · 107 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

gog-slides

Google Slides operations through gog.

openclaw/gogcli · 11 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens