Presentations

Presentations is a skill for Claude Code, Codex from zm1990s/kb-agent. It costs 12 tokens per session (3,894 once invoked), scanned A, original, MIT.

A set of instructions for creating or editing PowerPoint and Google Slides presentations.

In plain words
What is it for?
Use it to plan presentation structure, write slide content, choose layouts, manage information density, and check visual details such as spacing and overlap.
Why use it?
It helps keep slide content understandable, audience-focused, and visually balanced instead of exposing internal planning notes or overcrowding slides.

Skill for Claude CodeCodex

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/zm1990s/kb-agent/presentations
Any agent
npx skills add zm1990s/kb-agent --skill presentations
Clone the repo
git clone --depth 1 https://github.com/zm1990s/kb-agent

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 Presentations

README.md
[![agentmods](https://agentmods.dev/badge/skills/zm1990s/kb-agent/presentations.svg)](https://agentmods.dev/skills/zm1990s/kb-agent/presentations)
Your own site
<a href="https://agentmods.dev/skills/zm1990s/kb-agent/presentations"><img src="https://agentmods.dev/badge/skills/zm1990s/kb-agent/presentations.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,894 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 $0.00012 $0.03894
Opus 5 $0.00006 $0.01947
Sonnet 5 $0.00002 $0.00779
Haiku 4.5 $0.00001 $0.00389

Measured 3d ago against content hash 2c7a19e3b20c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d ago.

The scan reads SKILL.md. This mod also ships 29 executable files (assets/builtin_templates/codex-grid-layout-library/artifact-tool-compose/index.mjs, assets/builtin_templates/codex-grid-layout-library/artifact-tool-compose/runtime.mjs, assets/builtin_templates/codex-grid-layout-library/artifact-tool-compose/slide-01.mjs, …), 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.

backend/codex_skills/presentations/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slides Skill

Use this skill as reference material when creating or editing presentation slide decks.

Important Instructions

  • [HARD REQUIREMENT] Content quality and storytelling: before planning the deck, read and follow Content Quality and Narrative Rules. Ensure the deck covers everything the user requested and forms a coherent, audience-appropriate narrative rather than a collection of disconnected facts.

  • [HARD REQUIREMENT] Audience-facing copy: visible slide content must be written for the intended audience, not for the person or model producing the deck. Do not expose planning notes, timing scaffolds, talk tracks, content-selection commentary, or other internal process language unless the user explicitly requests it.

  • Info density: avoid cramming low-value details onto a single slide. Prefer lower-density slides with high-value content.

    • Title slide: keep the title slide minimal and simple. Avoid cramming in too much information.
  • Layout: keep things clean and simple. Avoid low-quality visuals, but also avoid excessive white space. By default, use equal left and right margins on each slide.

  • [HARD REQUIREMENT] Overlap: always pay attention to programmatic overlap warnings. Do not assume that overlapping elements in diagrams are intentional, and do not ignore overlap warnings without inspecting them. You MUST fix all unintended overlap errors before delivering the slides. This is critical.

  • [HARD REQUIREMENT] Font size: when a template is provided, match its font sizes. When no template or style guidance is given, you MUST use at least 50pt for deck titles, 35pt for slide titles, 24pt for mid-level text such as subheadings, callout headers, and text-box titles, and 16pt for body text.

  • Text layout: when there is too much text, shorten it before shrinking the font size. Inspect visually for unexpected text wrapping. NEVER allow a title/banner text box intended for one line to wrap to two lines.

  • Narrative copy must fit the chosen layout: shorten it or change layouts rather than adding density or shrinking type.

  • Visual assets:

    • [HARD REQUIREMENT] DO NOT use Python to draw images; DO NOT use programmatic vector shapes for visuals; DO NOT use programmatic drawings of any sort. Use image search or image_gen tool instead!
    • [HARD REQUIREMENT] Minimize the use of diagrams. Add them only when requested or when a single diagram materially improves the clarity of complex concepts. Diagram implementation rules: use native PowerPoint shapes for simple diagrams; use Graphviz for complex relational/topological/network-like diagrams; use image_gen for highly aesthetic, illustrative, or scientific infographic diagrams (e.g. chemical structures, circuit diagrams, etc.). When using native PowerPoint shapes with connectors, create connectors (arrows/edges) before creating entity nodes, so edges appear behind nodes and never cross through node shapes or labels. If this ordering is awkward during early iteration, you may create nodes first in the initial draft, then switch to connectors-first in the revised code.
    • Before sourcing or generating visuals, be mindful of the desired aspect ratio, placement, and cropping options on the slide. For example, if you intend to place text to the left of the image containing a person, you should ask image_gen to put the person on the right side of the image.
    • By default, DO NOT reuse the same image more than once (unless it's a background).
    • Prepare visuals for both the main concept and decorative support.
  • Default styling: use one composition instead of a collection of UI panels. UI-like styling typically includes card grids, pills, badges, button-like text boxes, tab or navigation patterns, repeated modular panels, dense dashboard-style layouts, and other component-library aesthetics that imply interactivity. Use stylized text boxes sparingly, favoring a flat structure on the canvas.

Read the full file on GitHub · 284 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. 3d ago First seen · 284 lines · 12 tokens per session scan A 2c7a19e3b20c

Subscribe to this mod's changes

Presentations is a skill published in the GitHub repository zm1990s/kb-agent (5 stars, last pushed 13d ago), licensed MIT. It adds 12 tokens to every session and 3,894 once invoked, about $0.0001 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

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

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

feishu

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

Hmbown/CodeWhale · 33 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

docx-comment-reply

Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.

foryourhealth111-pixel/Vibe-Skills · 39 tokens