slides

slides is a skill for Claude Code, Codex from agentlas-ai/agentlas-desktop. It costs 36 tokens per session (666 once invoked), scanned A, original, Apache-2.0.

A tool for editing PPTX presentation files in an open document workspace. It can change slide text and formatting, add or remove slides, and save the presentation.

In plain words
What is it for?
Use it to update slide titles and body text, add or delete slides, change text formatting, and save the PPTX file.
Why use it?
It lets you revise slide content without rebuilding the deck. Existing pictures, charts, and tables are kept even though they are not directly editable here.

Skill for Claude CodeCodex

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

Good fit Use it to update slide titles and body text, add or delete slides, change text formatting, and save the PPTX file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentlas-ai/agentlas-desktop/slides
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.

Any agent
npx skills add agentlas-ai/agentlas-desktop --skill slides
Clone the repo
git clone --depth 1 https://github.com/agentlas-ai/agentlas-desktop

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 slides

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/slides/github.svg)](https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/slides)
Your own site
<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/slides"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/slides/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for slides

Your own site · 80×15
<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/slides"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/slides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 666 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00036 $0.00666
Opus 5.5 $0.00014 $0.00266
Sonnet 5.5 $0.00007 $0.00133
Haiku 4.5 $0.00004 $0.00067

Measured 2d ago against content hash 5636ed30605e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

slides 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 2d 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.

plugins/office/skills/slides/SKILL.md · 28 lines

How it starts

The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Steps

  1. harness_call {"operation":"document.list"}: reuse an open session. Otherwise call harness_call {"operation":"document.open","args":{"path":"<absolute path>"}}, or document.create with a new .pptx path (a title slide; then add_slide).
  2. The outline lists # slide N (id s2), then [s2.sh1] title: … and [s2.sh2] body: … lines. {…} shows a shape's text format. A table shows as [id] (table 3x4) with its rows; notes: … is the slide's speaker notes.
  3. Edit with document.apply using sessionId and ops. Edit one slide per call.
  4. Save with document.save.
  5. To check the layout, call harness_call {"operation":"document.render","args":{"sessionId":"…"}}. It returns up to 4 slides as images, as the deck is now (saved or not), and lists the boxes whose text overflows. When the reply has next, call again with its from until every slide has been seen.

Ops

  • {"op":"set_text","target":"s2.sh1","text":"…"} replaces a shape's text. \n starts a new paragraph, which is one bullet in a body. Do not type • or - in a body: the layout draws the bullet.
  • {"op":"insert_text","target":"s2.sh2","text":"…"} appends to a shape's text.
  • {"op":"add_slide","after":"s2","title":"…","body":"line 1\nline 2"} uses the deck's Title and Content layout.
  • {"op":"delete_slide","target":"s3"}
  • {"op":"insert_table","after":"s2","rows":[["지표","3분기","4분기"],["첫 답변 시간","10시간","6시간"]],"widths":[2,1,1]} puts a table on slide s2. The first row is the header. The table takes the slide's empty body; otherwise it goes under the slide's text. For a table slide, use add_slide with only a title, then insert_table.
  • {"op":"set_notes","target":"s2","text":"…"} writes the slide's speaker notes. "" clears them.
  • {"op":"set_format","target":"s2.sh1","format":{"bold":true,"size":40,"color":"#ffffff","align":"center"}}

Notes

  • Pictures and charts on a slide are kept as they are and are not editable here. A table already in the deck is shown with its rows, but its cells are not editable.
  • On revision_conflict, call document.read and apply again.

Read the full file on GitHub · 28 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. 2d ago Changed 5636ed30605e
  2. 3d ago Changed · +3 lines · +5 tokens per session 88e584672704
  3. 4d ago First seen · 25 lines · 31 tokens per session scan A 4866c4c9f98b

Subscribe to this mod's changes

slides is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 666 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-18.

Related

Other skills, from other repositories

cua-volume

Use Cua Volume, the one volume every Space and agent of this user shares. Inside a Space it is mounted as a folder (/volume on Linux, /Cua Volume on macOS), so any program reads and writes it directly. Use it for anything that must outlive this Space - your memory and outputs in your agent home, shared reference in…

trycua/cua · 114 tokens

doc-ingest

Extract readable text from document files — PDF, XLSX/CSV/TSV, DOCX, PPTX, and plain-text formats — so any task that arrives with an attachment can actually consume it.

sonichi/sutando · 0 tokens

md2pdf

Convert a Markdown file to PDF with GitHub-style formatting using the md2pdf tool.

joshukraine/dotfiles · 22 tokens

delive-transcript-analyzer

Analyze, summarize, and extract insights from DeLive transcription sessions. Use when: user mentions DeLive, transcription, meeting transcripts, live captions, audio transcription, AI correction, corrected transcript, or transcript analysis; user wants to search, retrieve, summarize, correct, or process recorded…

XimilalaXiang/DeLive · 98 tokens

hermesoffice-documents

Produce and edit Word documents in HermesOffice Docs — block editing, tracked changes, reports, and the templates/docs library (meeting notes, business plan, PRD, decision memo, and more). Load for any request that creates or restructures a document.

criptogus/HermesOffice · 57 tokens

electron-expert

Expert in Electron framework, desktop app development, IPC, and cross-platform packaging. Use when the user mentions desktop, Node.js, cross platform, Windows, macOS, or Linux, or when the task involves Electron Architecture, Process Types, IPC Communication, or App Lifecycle.

personamanagmentlayer/pcl · 59 tokens