powerpoint-presentations

powerpoint-presentations is a skill for Claude Code, Codex from aws-samples/sample-strands-agent-with-agentcore. It costs 48 tokens per session (1,294 once invoked), scanned A, original, MIT.

A tool for creating, inspecting, editing, and checking PowerPoint presentation files (.pptx), including decks built from existing files or templates.

In plain words
What is it for?
Use it to build new presentations, update uploaded decks, create content in branded templates, or review slides for content, design, and structural problems.
Why use it?
It helps preserve the source deck's layouts, notes, embedded assets, and other internal parts while checking both its structure and visual appearance.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

About the project

Sample Strands Agent with Amazon Bedrock AgentCore is an end-to-end reference architecture for building multi-agent chatbots on AWS. Teams use it to explore agent orchestration, tool execution, memory, browser automation, and agent-to-agent collaboration with Strands Agents and Bedrock AgentCore.

aws-samples/sample-strands-agent-with-agentcore · 192 stars · on GitHub

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/aws-samples/sample-strands-agent-with-agentcore/powerpoint-presentations
Any agent
npx skills add aws-samples/sample-strands-agent-with-agentcore --skill powerpoint-presentations
Clone the repo
git clone --depth 1 https://github.com/aws-samples/sample-strands-agent-with-agentcore

Made for: Claude Code, Codex.

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 powerpoint-presentations

README.md
[![agentmods](https://agentmods.dev/badge/skills/aws-samples/sample-strands-agent-with-agentcore/powerpoint-presentations.svg)](https://agentmods.dev/skills/aws-samples/sample-strands-agent-with-agentcore/powerpoint-presentations)
Your own site
<a href="https://agentmods.dev/skills/aws-samples/sample-strands-agent-with-agentcore/powerpoint-presentations"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-strands-agent-with-agentcore/powerpoint-presentations.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,294 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 5.1 $0.00048 $0.01294
Opus 5 $0.00024 $0.00647
Sonnet 5 $0.00010 $0.00259
Haiku 4.5 $0.00005 $0.00129

Measured 6d ago against content hash 0c67e340b9a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

powerpoint-presentations 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 6d 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.

chatbot-app/agentcore/skills/powerpoint-presentations/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PowerPoint Presentations

Use a staged workflow: classify → inspect → plan → execute → validate → render → iterate. Do not skip source verification or QA.

1. Classify the Request

Choose exactly one path:

Path Use when Primary tools
Edit source Modify an uploaded or existing deck inspect_presentation, begin_presentation_edit, edit tools
Build from template Create content in an uploaded branded deck begin_presentation_edit, duplicate_slide, update_slide_content
Create new No source/template must be preserved create_presentation
Analyze Review content, design, or structure without editing inspect_presentation, preview tools

Never use create_presentation for an edit or template request. It creates a new package and cannot preserve the source master, layouts, relationships, notes, or embedded assets.

2. Verify and Inspect the Source

For edit and template paths:

  1. Call list_my_powerpoint_presentations.
  2. Confirm the exact source filename exists.
  3. Call inspect_presentation with persist_spec=true.
  4. Call preview_presentation_montage for a deck-level visual pass.
  5. Call analyze_presentation only for slides that require detailed element IDs.

If the source cannot be loaded, stop and report the missing file. Do not recreate the deck from a description, silently switch to a new-deck workflow, or delegate the task to an environment where the source file has not been verified.

Treat the persisted deck spec as the design-system record across turns. After inspection, call begin_presentation_edit once and retain its edit_id. Re-run inspect_presentation with that edit_id after structural changes; do not rely on conversation memory for fonts, colors, layouts, or slide structure.

3. Plan Before Editing

Define:

  • Audience and decision or outcome
  • Narrative arc and one message per slide
  • Functional slide type for each slide
  • Content-density budget
  • Source slides/layouts to preserve or duplicate
  • Slides that require new visuals or data

Read the full file on GitHub · 140 lines

Files

What ships with it

5 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. 6d ago First seen · 140 lines · 48 tokens per session scan A 0c67e340b9a1

Subscribe to this mod's changes

powerpoint-presentations is a skill published in the GitHub repository aws-samples/sample-strands-agent-with-agentcore (192 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 1,294 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories