Gaia Technical Presentation logo

Gaia Technical Presentation

OrganizationPopular
amd
gaia-technical-presentation

Generate a TECHNICAL slide presentation (engineering audience) from a source document as self-contained HTML that prints cleanly to PDF, one slide per page. Use when the user asks for a technical presentation, engineering slides, an architecture or deep-dive deck, or to turn a README/spec/design doc into technical slides. Covers architecture, methodology, request/response contracts, and metrics with their method; code blocks and diagrams allowed. Offline HTML with an @media print profile; no PPTX/Keynote/Google Slides. For a leadership-facing version, use gaia-executive-presentation.

Overview

Publisheramd
Repositorygaia
Skill namegaia-technical-presentation
Stars
1.6K
Forks
176
Bundled files
1
LicenseMIT
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Gaia Technical Presentation 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/amd/gaia/tree/main/.claude/skills/gaia-technical-presentation
  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/amd/gaia.git /tmp/gaia
mkdir -p .claude/skills
cp -r /tmp/gaia/.claude/skills/gaia-technical-presentation .claude/skills/gaia-technical-presentation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gaia Technical Presentation 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 Gaia Technical Presentation 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 Gaia Technical Presentation 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.

GAIA Technical Presentation

Turn one source document into a credible technical slide presentation for an engineering audience — architecture, methodology, contracts, and metrics — as a single self-contained HTML file that exports cleanly to PDF, one slide per printed page.

This skill produces the technical tier only. For a leadership / decision-maker version of the same source, use the gaia-executive-presentation skill.

Invocation

gaia-technical-presentation <source-path>

  • Input: a path to a repo file (.md, .mdx, .json, .html, .txt) — the primary form. Pasted text is accepted as a fallback when no file exists.
  • Output: presentations/<source-path-slug>.technical.html at the repo root, where the slug is the source path with / replaced by - (so hub/agents/chat/python/README.md → presentations/hub-agents-chat-python-README.technical.html). Deterministic; re-runs overwrite in place — never hand-edit the output.
  • Never write next to the source. Decks are local scratch, and many sources live in directories that ship (hub/agents/*/python/, src/). The root presentations/ dir is gitignored; a presentations/ dir dropped next to a package is not, and would land in the published artifact. The path slug keeps two same-named sources (two README.mds) apart.

Shared design system

The look, fonts, slide patterns, and print profile live in the shared assets directory and are inlined verbatim into the output (do not duplicate or hand-edit them per run):

  • .claude/skills/gaia-presentation-assets/assets/fonts.css — base64 brand fonts (offline)
  • .claude/skills/gaia-presentation-assets/assets/deck.css — design system + @media print
  • .claude/skills/gaia-presentation-assets/assets/deck-viewer.js — screen-only viewer
  • .claude/skills/gaia-presentation-assets/assets/slide-blocks.html — slide patterns to compose from

Pipeline (follow in order, every run)

  1. Read the source document in full, and re-read the user's request so you know the goal the presentation must serve.
  2. Build a real-artifact inventory. List every concrete artifact that actually exists in the source: metrics, tables, charts, code/contract snippets, screenshots, version strings, dated milestones — each with its source location (file:line or section). This inventory is the ONLY content source for slide facts.
  3. Ask the user upfront for any known evaluation/benchmark results the source does not contain (accuracy, latency, throughput, cost). One concise prompt; proceed with whatever they give.
  4. Select the technical slides (rules below), drawing values only from the inventory or the user's answers. Any quantitative point with neither becomes a loud, labeled placeholder — never an invented value.
  5. Emit the presentation: inline fonts.css, deck.css, and deck-viewer.js from the shared assets directory into one HTML file, compose slides from slide-blocks.html, populate from the inventory. Write to the output path.
  6. Self-check against the checklist, then report the placeholder list to the user (every ⚠ PLACEHOLDER with what value it needs).

Credibility contract (non-negotiable)

Resolve every slide value in this order: cite-from-source → else ask the user → else insert a loud, labeled placeholder. The one forbidden act is silent fabrication: an invented number presented as if it came from the source. Placeholders are fine because they are visually unmistakable as not-yet-real and are reported back. Where the source supports no real artifact for a slide and the slide is not load-bearing, omit it rather than pad with generic prose.

Technical tier — what belongs here

  • Engineering audience: architecture, methodology, the request/response contract, metrics with their method.
  • Code blocks and inline-SVG diagrams are allowed and encouraged where they carry real source content.
  • Typically 8–14 slides — enough to preserve precision and depth.
  • This is not the executive tier: keep the depth; do not strip methodology to chase brevity. (A leadership-facing cut is the gaia-executive-presentation skill's job.)

Self-contained + print (enforced by the shared assets — do not weaken)

  • Inline everything. No http(s)://, no CDN, no external file refs.
  • deck.css carries the @media print profile: @page { size: landscape; margin:0 }, one slide per page (break-after: page; break-inside: avoid), height:auto; min-height:100vh in print, all chrome hidden. Do not edit these rules per-presentation.
  • The viewer JS is screen-only; it is disabled under @media print.

Worked example

reference/example-technical.html — generated from the GAIA email agent hub package (hub/agents/email/python/): 12 slides covering architecture, the request/response contract, the packaging table, the token-usage schema, and code blocks. Its benchmark slide intentionally shows labeled ⚠ PLACEHOLDER values because no eval results existed in the source at generation time — a demonstration of the credibility contract.

Checklist before reporting done

  • Does the presentation satisfy the user's goal? Re-read the user's request: do the slides cover what they asked to present, at engineering depth, so the audience leaves with what the user intended? If not, revise before reporting done.
  • One self-contained HTML file; no external refs (grep -c 'https\?://' is 0).
  • Every quantitative value is sourced, user-supplied, or a labeled placeholder — no fabricated numbers.
  • Placeholder list reported to the user.
  • (If a browser is available) printed-page count == slide count, nothing clipped.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gaia Technical Presentation AI skill do?

Generate a TECHNICAL slide presentation (engineering audience) from a source document as self-contained HTML that prints cleanly to PDF, one slide per page. Use when the user asks for a technical presentation, engineering slides, an architecture or deep-dive deck, or to turn a README/spec/design doc into technical slides. Covers architecture, methodology, request/response contracts, and metrics with their method; code blocks and diagrams allowed. Offline HTML with an @media print profile; no PPTX/Keynote/Google Slides. For a leadership-facing version, use gaia-executive-presentation.

Why use Gaia Technical Presentation on TypingMind?

Because you install it once and use it with any model. Gaia Technical Presentation 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 Gaia Technical Presentation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/amd/gaia/tree/main/.claude/skills/gaia-technical-presentation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gaia Technical Presentation?

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 Gaia Technical Presentation?

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

Is the Gaia Technical Presentation AI skill free?

Yes. It is published on GitHub by amd under the MIT 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 👇