Pptx Author logo

Pptx Author

OrganizationPopular
NousResearch
pptx-author

Build PowerPoint decks headless with python-pptx.

Overview

PublisherNousResearch
Repositoryhermes-agent
Skill namepptx-author
Stars
250.4K
Forks
53.5K
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by NousResearch on GitHub. Read the source before you install it.

Installation

Install the Pptx Author AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/NousResearch/hermes-agent/tree/main/optional-skills/finance/pptx-author
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/NousResearch/hermes-agent.git /tmp/hermes-agent
mkdir -p .claude/skills
cp -r /tmp/hermes-agent/optional-skills/finance/pptx-author .claude/skills/pptx-author
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pptx Author in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pptx Author on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pptx Author is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

pptx-author

Produce a .pptx file on disk using python-pptx. Use when you need to deliver a deck as a file artifact, not drive a live PowerPoint session.

Adapted from Anthropic's pptx-author and pitch-deck skills in anthropics/financial-services. The MCP / Office-JS branches of the originals are dropped — this assumes headless Python.

For the broader, already-shipped PowerPoint authoring skill (slides, speaker notes, embeds, media), see the built-in powerpoint skill. This skill is a lighter-weight pattern tuned for model-backed decks (pitch decks, IC memos, earnings notes) where every number must trace to a source workbook.

Output contract

  • Write to ./out/<name>.pptx. Create ./out/ if it does not exist.
  • Return the relative path in your final message.

Setup

bash
pip install "python-pptx>=0.6"

Core conventions

One idea per slide

Title states the takeaway; body supports it. A slide titled "Q3 Revenue" is weak; "Revenue growth accelerated to 14% Y/Y in Q3" is strong.

Every number traces to the model

If a figure on a slide came from ./out/model.xlsx, footnote the sheet and cell.

Revenue: $1,250M  (Source: model.xlsx, Inputs!C3)

Never transcribe numbers from memory or from a summary — open the workbook, read the named range, and bind the deck value to it programmatically when you can.

Use the firm template when one is mounted

If ./templates/firm-template.pptx exists, load it so the deck inherits branded colors, fonts, and master layouts.

python
from pptx import Presentation
from pathlib import Path

template = Path("./templates/firm-template.pptx")
prs = Presentation(str(template)) if template.exists() else Presentation()

Charts: PNG-from-model beats native pptx charts

When fidelity matters (the model's chart styling must match the deck exactly), render the chart to PNG from the source workbook and embed the image. Native pptx.chart charts are fragile and often don't match firm conventions.

python
from pptx.util import Inches
slide.shapes.add_picture("./out/charts/football_field.png",
                         Inches(1), Inches(2),
                         width=Inches(8))

No external sends

This skill writes a file. It never emails, uploads, or posts. Orchestration layers handle delivery.

Skeleton

python
from pptx import Presentation
from pptx.util import Inches, Pt
from pptx.dml.color import RGBColor
from pathlib import Path

template = Path("./templates/firm-template.pptx")
prs = Presentation(str(template)) if template.exists() else Presentation()

# Title slide
slide = prs.slides.add_slide(prs.slide_layouts[0])
slide.shapes.title.text = "Project Aurora — Strategic Alternatives"
slide.placeholders[1].text = "Preliminary Discussion Materials"

# Valuation summary slide (title-only layout)
slide = prs.slides.add_slide(prs.slide_layouts[5])
slide.shapes.title.text = "Valuation implies $38–$52 per share across methodologies"

# Add a table bound to model outputs
rows, cols = 5, 4
tbl_shape = slide.shapes.add_table(rows, cols,
                                   Inches(0.5), Inches(1.5),
                                   Inches(9), Inches(3))
tbl = tbl_shape.table
headers = ["Methodology", "Low ($)", "Mid ($)", "High ($)"]
for c, h in enumerate(headers):
    tbl.cell(0, c).text = h

# In a real deck, read these from the model workbook with openpyxl
data = [
    ("Trading comps",     "35", "41", "48"),
    ("Precedent M&A",     "39", "45", "52"),
    ("DCF (base)",        "36", "43", "51"),
    ("LBO (10% IRR)",     "33", "38", "44"),
]
for r, row in enumerate(data, start=1):
    for c, val in enumerate(row):
        tbl.cell(r, c).text = val

# Embed a chart rendered from the model
slide = prs.slides.add_slide(prs.slide_layouts[5])
slide.shapes.title.text = "Football field — current price $42"
slide.shapes.add_picture("./out/charts/football_field.png",
                         Inches(1), Inches(1.8), width=Inches(8))

Path("./out").mkdir(exist_ok=True)
prs.save("./out/pitch-aurora.pptx")

Binding deck numbers to the source workbook

Read named ranges or specific cells from your Excel model so deck numbers never drift.

python
from openpyxl import load_workbook

wb = load_workbook("./out/model.xlsx", data_only=True)
def nr(name):
    """Resolve a named range to its current computed value."""
    rng = wb.defined_names[name]
    sheet, coord = next(rng.destinations)
    return wb[sheet][coord].value

revenue_fy24 = nr("RevenueFY24")
implied_mid  = nr("ImpliedSharePriceBase")

Then build deck content using those values:

python
slide.shapes.title.text = f"Implied share price of ${implied_mid:.2f} (base case)"

Remember to recalculate the workbook before reading it — openpyxl only sees computed values if something has already calculated the sheet. Run the recalc helper in the excel-author skill first, or open/save through a real Excel session.

Slide-type checklist for pitch decks

A typical banking pitch deck follows this structure. Not prescriptive, but useful as a starting skeleton:

  1. Cover / title
  2. Disclaimer
  3. Table of contents
  4. Situation overview
  5. Company snapshot (the target)
  6. Market / sector context
  7. Valuation summary (football field) — the money slide
  8. Trading comps detail
  9. Precedent transactions detail
  10. DCF summary
  11. Illustrative LBO / sponsor case
  12. Process considerations
  13. Appendix

When NOT to use this skill

  • Users in a live PowerPoint session with an Office MCP available — drive their live doc instead.
  • Non-financial slideware (quarterly all-hands, marketing decks) — use the broader powerpoint skill.
  • Decks with heavy animation, transitions, or speaker notes — use the broader powerpoint skill.

Attribution

Conventions adapted from Anthropic's Claude for Financial Services plugin suite, Apache-2.0 licensed. Original: https://github.com/anthropics/financial-services/tree/main/plugins/agent-plugins/pitch-agent/skills/pptx-author

Frequently asked questions

What does the Pptx Author AI skill do?

Build PowerPoint decks headless with python-pptx.

Why use Pptx Author on TypingMind?

Because you install it once and use it with any model. Pptx Author is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pptx Author in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NousResearch/hermes-agent/tree/main/optional-skills/finance/pptx-author. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pptx Author?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pptx Author?

As many as you like. As long as a model supports skills, you can use Pptx Author with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pptx Author AI skill free?

Yes. It is published on GitHub by NousResearch under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇