agentleFS
holon-runholon-run/holon/skills/pptx/SKILL.md

pptx

Skill194 starsChanged 4 days agoApache-2.0View on GitHub

Create, inspect, edit, render, and validate PowerPoint presentations with local open-source tools while preserving source files and reporting fidelity limits.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use file-reading, context7-efficient and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SeifBenayedSkill

    file-reading

    Use this skill when a file has been uploaded but its content is NOT in your context — only its path at /mnt/user-data/uploads/ is listed in an uploaded_files block. This skill is a router: it tells you which tool to use for each file type (pdf, docx, xlsx, csv, json, images, archives, ebooks) so you read the right amount the right way instead of blindly running cat on a binary. Triggers: any mention of /mnt/user-data/uploads/, an uploaded_files section, a file_path tag, or a user asking about an uploaded file you have not yet read. Do NOT use this skill if the file content is already visible in your context inside a documents block — you already have it.

    Also in 5 projects that use this

  • hfzarslanSkill

    context7-efficient

    Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.

    Also in 5 projects that use this

  • SeifBenayedSkill

    pdf-reading

    Use this skill when you need to read, inspect, or extract content from PDF files — especially when file content is NOT in your context and you need to read it from disk. Covers content inventory, text extraction, page rasterization for visual inspection, embedded image/attachment/table/form-field extraction, and choosing the right reading strategy for different document types (text-heavy, scanned, slide-decks, forms, data-heavy). Do NOT use this skill for PDF creation, form filling, merging, splitting, watermarking, or encryption — use the pdf skill instead.

    Also in 6 projects that use this

  • amirbironSkill

    import-memory

    Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data.

    Also in 5 projects that use this

  • unicorn-pluginsSkill

    product-self-knowledge

    Anthropic 제품 지식 — Claude Code, Claude API, Claude.ai 관련 정확한 정보 제공

    Also in 8 projects that use this

  • AbdullahMalik17Skill

    configuring-dapr-pubsub

    Configures Dapr pub/sub components for event-driven microservices with Kafka or Redis. Use when wiring agent-to-agent communication, setting up event subscriptions, or integrating Dapr sidecars. Covers component configuration, subscription patterns, publishing events, and Kubernetes deployment. NOT when using direct Kafka clients or non-Dapr messaging patterns.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. 0 are common, 14 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 189 edited versions we read keep these.

  • 14

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill for .pptx presentation work.

    line 10
  2. Very specific:

    Keep the input unchanged and write a new .pptx by default.

    line 27
  3. Distinctive:

    Treat hyperlinks, media, macros, embedded objects, and package metadata as untrusted input.

    line 28
  4. Distinctive:

    Never execute VBA, embedded programs, OLE actions, or linked content.

    line 30
  5. Distinctive:

    Ask before downloading linked assets or uploading deck content.

    line 31
  6. Distinctive:

    Do not claim lossless editing when a deck contains animations, SmartArt, embedded media, custom XML, unsupported charts, signatures, or …

    line 32
  7. Distinctive:

    Prefer PptxGenJS for new presentations requiring explicit placement, reusable layouts, shapes, images, tables, or charts.

    line 41
  8. Distinctive:

    Prefer python-pptx for reading common slide content and small edits whose affected elements are represented by its object model.

    line 43
  9. Distinctive:

    Use LibreOffice headless only when installed and approved as a local renderer or converter.

    line 45
  10. Distinctive:

    Use local image tooling for montage or pixel inspection when available.

    line 47
  11. Distinctive:

    Do not silently install Node, Python packages, LibreOffice, fonts, or other system dependencies.

    line 49
  12. Distinctive:

    Create a content plan before implementation: one message per slide, evidence or data source, visual hierarchy, and speaker-note …

    line 58
  13. Distinctive:

    Keep a consistent grid, margins, typography, and color system.

    line 72
  14. Distinctive:

    Prefer concise slide copy and meaningful visual structure over dense prose.

    line 73
  15. Distinctive:

    Do not fabricate citations, figures, logos, or brand requirements.

    line 74
  16. Distinctive:

    Use fonts known to exist in the target environment, or report substitutions.

    line 77

“Common” is measured: kept by at least 6 in 10 of the 189 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

PPTX

Summary

Use this skill for .pptx presentation work. Prefer PptxGenJS for new, layout-driven decks and python-pptx for inspection or bounded edits. Use an available local LibreOffice or compatible renderer for visual validation.

This is a workflow and safety contract, not a presentation engine. Probe the actual environment before choosing a backend.

When To Use

  • Creating a presentation from an outline, document, data set, or template
  • Inspecting slide text, structure, notes, images, charts, or metadata
  • Making bounded changes to an existing deck
  • Rendering a deck to PDF or images for review
  • Producing charts or tables from operator-provided data

Safety Boundaries

  • Keep the input unchanged and write a new .pptx by default.
  • Treat hyperlinks, media, macros, embedded objects, and package metadata as untrusted input.
  • Never execute VBA, embedded programs, OLE actions, or linked content.
  • Ask before downloading linked assets or uploading deck content.
  • Do not claim lossless editing when a deck contains animations, SmartArt, embedded media, custom XML, unsupported charts, signatures, or unknown parts.

For an existing deck, inventory those features before saving it. If the chosen library cannot preserve important features, use read-only analysis, rebuild a new deck, or request manual Office editing instead.

Backend Selection

  • Prefer PptxGenJS for new presentations requiring explicit placement, reusable layouts, shapes, images, tables, or charts.
  • Prefer python-pptx for reading common slide content and small edits whose affected elements are represented by its object model.
  • Use LibreOffice headless only when installed and approved as a local renderer or converter. Record that it is not Microsoft PowerPoint.
  • Use local image tooling for montage or pixel inspection when available.

Do not silently install Node, Python packages, LibreOffice, fonts, or other system dependencies. Report the missing capability and the safe fallback.

Workflow

  1. Confirm the audience, purpose, slide count, aspect ratio, language, branding, source data, output path, and whether a template must be preserved.
  2. Inspect existing decks before editing. Record slide layouts, masters, fonts, charts, notes, media, links, and unsupported features that affect fidelity.
  3. Create a content plan before implementation: one message per slide, evidence or data source, visual hierarchy, and speaker-note requirements.
  4. Choose a backend and explain any expected limitations.
  5. Generate or edit a new output file. Avoid raw OOXML manipulation unless the exact package contract is understood and no safer API can express the change.
  6. Reopen the package and verify slide count, relationships, media references, and expected text or data.
  7. Render every slide when a renderer is available. Inspect for overflow, clipping, overlap, unreadable charts, missing images, blank slides, and font substitution.
  8. Sample-check numbers, labels, citations, and charts against source material.

Quality Rules

  • Keep a consistent grid, margins, typography, and color system.
  • Prefer concise slide copy and meaningful visual structure over dense prose.
  • Do not fabricate citations, figures, logos, or brand requirements.
  • Preserve aspect ratio when placing images; flag low-resolution assets.
  • Make charts readable without relying only on color.
  • Use fonts known to exist in the target environment, or report substitutions.
  • Separate speaker notes from visible slide content when notes are requested.

Delivery

Report the output path, source preservation, backend and fonts used, rendered pages inspected, structural checks, sampled data checks, and any unsupported or unverified presentation features. If rendering was unavailable, say that visual layout was not verified.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.