deck-creator

deck-creator is an agent for coding agents from ai-analyst-lab/ai-analyst-plus. It costs 0 tokens per session (6,936 once invoked), scanned A, a copy of deck-creator, MIT.

A slide-deck agent turns an analysis narrative and chart files into a complete presentation, including speaker notes. It can produce Gamma-compatible or Marp-ready Markdown.

In plain words
What is it for?
It helps create presentation decks from an executive summary, findings, implications, recommendations, and optional PNG or SVG charts.
Why use it?
It removes the manual work of arranging findings, charts, themes, and notes into a coherent presentation.

Agent

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 agents/ai-analyst-lab/ai-analyst-plus/deck-creator
Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-plus

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 deck-creator

README.md
[![agentmods](https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plus/deck-creator.svg)](https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plus/deck-creator)
Your own site
<a href="https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plus/deck-creator"><img src="https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plus/deck-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,936 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.06936
Opus 5 $0.00000 $0.03468
Sonnet 5 $0.00000 $0.01387
Haiku 4.5 $0.00000 $0.00694

Measured 4d ago against content hash 91a4abcdbbee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deck-creator 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 4d ago.

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.

Origin

This is a copy

100% identical to deck-creator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/deck-creator.md · 630 lines

How it starts

The opening of the file, as written. The whole thing — 630 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Deck Creator

Purpose

Create a complete slide deck from analysis outputs by combining a storytelling narrative with charts, applying a presentation theme, and generating speaker notes for every slide.

Inputs

  • {{NARRATIVE}}: Path to the narrative document produced by the Storytelling Agent. Must contain an executive summary, findings, insight, implication, and recommendations sections.
  • {{CHARTS}}: Path to the directory or list of chart files (PNG/SVG) produced during analysis. Each chart file should have a descriptive filename. If no charts are available, the agent will generate text-only slides and note where charts should be inserted.
  • {{THEME}}: (optional) Presentation theme to apply — one of the named themes from the Presentation Themes skill (e.g., "nyt", "economist", "minimal", "corporate", "analytics", "analytics-dark"). Defaults to "corporate" if not specified.
  • {{FORMAT}}: (optional) Output format — "gamma" for Gamma-compatible markdown (default), or "marp" for Marp PDF-ready markdown. When "marp" is selected with the "analytics" theme, the deck uses themes/analytics-light.css. With "analytics-dark", the deck uses themes/analytics-dark.css. Both can be exported directly to PDF.
  • {{CONTEXT}}: (optional) Presentation context — e.g., "workshop", "talk", "stakeholder readout", "team standup". When context is "workshop" or "talk", the agent adds an optional closing sequence with CTA slides after the main content.
  • {{AUDIENCE}}: (optional) Who will see this deck — e.g., "executive team", "product review", "board meeting", "team standup". Defaults to "senior stakeholders". Controls content density and slide count.
  • {{STORYBOARD}}: (optional) Path to the storyboard from Story Architect (working/storyboard_{{DATASET}}.md). When provided, use the audience journey section for slide framing (who the audience is, what they believe now vs. after, what decision to drive) and the beat sequence for speaker notes transitions.
  • {{DECK_TITLE}}: (optional) Override title for the deck. If not provided, the agent will derive the title from the narrative document's core insight.

Read the full file on GitHub · 630 lines

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. 4d ago First seen · 630 lines · 0 tokens per session scan A 91a4abcdbbee

Subscribe to this mod's changes

deck-creator is an agent published in the GitHub repository ai-analyst-lab/ai-analyst-plus (19 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,936 tokens. A static security scan graded it A with 0 findings. It is 100% identical to deck-creator, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

table-of-contents-generator

Table of Contents Generator. Generate EXACTLY the table of contents slide. REQUIRED inputs: font family, color palette, slide index, slide content (section list with titles). the number of total slides. DO NOT PROVIDE layout specifications.

MiniMax-AI/skills · 0 tokens

doc-to-deck-agent

Converts a Pages or Word document into a Keynote slide deck.

SpillwaveSolutions/automating-mac-apps-plugin · 19 tokens

planner

You are a professional video editor. You will receive a transcription of a raw video recording (with word-level timestamps and an energy map showing audio levels over time) plus context about what the video is about.

gabuldev/auto-edit-video · 0 tokens

briefing-craft-designer

Use this agent when you need to create presentation slides, design PPT for reports, build visual presentations, or produce professional slide decks. Examples: Context: Strategist has completed content strategy for a project presentation user: "根据内容策略,制作汇报PPT" assistant: "我将基于内容策略设计专业的PPT演示文稿,确保视觉效果和内容呈现俱佳。 " Context…

LZMW/briefing-craft-team · 185 tokens

slide-scripter

Generates a Node.js script from the slide plan, executes it to produce a PPTX file, and handles distribution (Phase 2-4 of CLAUDE.md).

groundcobra009/demo-miraichi-company-slide-builder · 0 tokens

ppt_encoder_agent

负责使用 pptx-encoder skill 将 deckspec.json 和 stylespec.json 渲染为可编辑 finaldeck.pptx,并输出编码报告。.

BingHanOfUESTC/open_agent_team · 36 tokens