A tool for creating, reviewing, or converting slide presentations in HTML, lecturn.deck/1 JSON, or PowerPoint format. It treats slides as fixed-size pages meant to be read quickly from a distance.

Use it to make pitch decks, keynotes, investor updates, board packs, and other presentations, or to review and convert existing decks.

It helps prevent presentations from becoming documents or web pages squeezed into slides. It keeps the slide format and narrative structure aligned with how people actually view a presentation.

deck-craft — Skill for Claude Code and Codex by fledgeling-co: A tool for creating, reviewing, or converting slide presentations…

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/fledgeling-co/fledgeling-plugins/deck-craft

Any agent

npx skills add fledgeling-co/fledgeling-plugins --skill deck-craft

Clone the repo

git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code, Codex.

Or install deck-craft, 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/fledgeling-co/fledgeling-plugins/deck-craft.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/deck-craft)

Your own site

<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/deck-craft"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/deck-craft.svg" alt="Measured on agentmods" height="20"></a>

Per session 229 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 10,068 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.

Model	Per session	Once invoked
Fable 5.1	$0.00229	$0.10068
Opus 5	$0.00114	$0.05034
Sonnet 5	$0.00046	$0.02014
Haiku 4.5	$0.00023	$0.01007

Measured 5d ago against content hash 4fd0fdbfee6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

deck-craft 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 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (evals/gate/run-evals.sh, scripts/deck-preflight.js, scripts/run-preflight.sh), 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.

plugins/deck-craft/skills/deck-craft/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deck Craft

A deck is not a document with page breaks and not a web page with sections. It is fixed-size content, read at distance, on someone else's clock — the reader can't zoom, can't scroll back mid-sentence, and gives each slide a few seconds before the speaker moves on. Every rule below descends from those three constraints.

You produce decks in three formats. They share the craft and the narrative discipline; they differ only in what you emit. Pick the target first — building an HTML shell when the user needed a .pptx is the expensive mistake, and it isn't recoverable by editing.

Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. §6's slide count as a contract and §7's runner that fails closed are already the right shape for that family; gemini.md extends both — derive the count when the brief omits one, report the per-slide gate as a fraction, paste the runner's blocker line rather than a claim about it, turn §5's accent/hue/type maxima into a bound ledger read back off the built deck, and write the direction's three axes as three chosen values. It also says which deck work to route to another model before starting, and marks which of this skill's rules were measured on that family and which were not. Other models skip it.

1. Route to a target

If the request is empty, ask in one line what the deck is for and who is watching, then stop. Do not open the six-question discovery round on an empty invocation — it is the wrong answer to "no brief at all".

The user wants	Target	Read
A deck to present, share as a link, or open in a browser; "slides", "presentation", "pitch deck", no file format named	HTML — one self-contained file, fixed 16:9 stage	`references/html-deck.md`
A `.pptx`, an editable PowerPoint/Keynote handoff, or a deck that must round-trip through Office; or an existing `.pptx` to read, diff, or edit	lecturn.deck/1 JSON → `.pptx` via the converter	`references/lecturn-json.md`
A deck assembled from the bundled template library — investor artifacts (results, 4C, AGM, board pack, roadshow, capital raising, IPO, investor day, ESG, M&A, site visit) or the business/product/engineering decks the additions cover	lecturn.deck/1 JSON built from `{templateId, slots}`	`references/diolog-templates.md`

Read the full file on GitHub · 259 lines

Files

What ships with it

33 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.

5d ago First seen · 259 lines · 229 tokens per session scan A 4fd0fdbfee6d

Subscribe to this mod's changes

deck-craft is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed today), licensed MIT. It adds 229 tokens to every session and 10,068 once invoked, about $0.0011 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.

Creative and media

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens