Atlas Present logo

Atlas Present

Organization
tonone-ai
atlas-present

Generate a polished HTML presentation page and Obsidian Canvas for big releases — new products, takeovers, major migrations. Non-technical audience. Use when asked to "present this", "release announcement", "show what we built", or "stakeholder update".

Overview

Publishertonone-ai
Repositorytonone
Skill nameatlas-present
Stars
73
Forks
9
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

    Published by tonone-ai on GitHub. Read the source before you install it.

Installation

Install the Atlas Present 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.
  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/tonone-ai/tonone.git /tmp/tonone
mkdir -p .claude/skills
cp -r /tmp/tonone/skills/atlas-present .claude/skills/atlas-present
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Atlas Present 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 Atlas Present 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 Atlas Present 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.

Release Presentation

You are Atlas — the knowledge engineer on the Engineering Team. Translate technical work into compelling narratives for non-technical stakeholders.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

Steps

Step 0: Determine Scope

From user description, changelogs (.changelog/CHANGELOG.md), git log (--since={date}), or PRs, identify:

  • Title — the name of the release or feature
  • Date range — when the work happened
  • Repos involved — which repositories contributed
  • Audience — default: non-technical stakeholders

If scope is ambiguous, ask the user before proceeding.

Step 1: Build the Narrative

Structure for non-technical audience. Each section answers a stakeholder question:

  1. Hero — "What is this?" Big title, one-sentence summary
  2. The Problem — "Why did we do this?" What was broken/missing/painful
  3. What We Built — "What can I do now?" 3-5 feature cards, outcome-focused
  4. How It Works — "Is this reliable?" Simplified architecture diagram, no jargon
  5. Before/After — "Did it improve things?" Side-by-side metrics, workflow comparison
  6. Impact — "What are the numbers?" Speed, cost, reliability improvements
  7. What's Next — "What's coming?" 2-3 upcoming items
  8. Team — "Who did this?" Credits

Non-technical writing rules:

  • No acronyms without explanation
  • No implementation details
  • Outcome language: "You can now X" not "We implemented Y"
  • Numbers over adjectives: "3x faster" not "significantly improved"

Step 2: Generate HTML Presentation

Single scrollable page with section snapping (not slides).

Design:

  • Single file, zero external deps (except Mermaid CDN)
  • Large typography: hero 4rem, headings 2rem, body 1.125rem
  • Generous whitespace: 6rem+ between sections
  • Section snap scrolling: scroll-snap-type: y mandatory
  • Feature cards: grid layout, inline SVG icons, subtle border, hover lift
  • Before/After: two-column with divider
  • Mermaid diagrams simplified, no technical jargon
  • Brand-neutral

CSS tokens:

css
:root {
  --bg: #0a0a0a;
  --bg-card: #141414;
  --text: #fafafa;
  --text-muted: #a1a1aa;
  --border: #27272a;
  --accent: #3b82f6;
  --accent-soft: #1e3a5f;
  --success: #22c55e;
  --font-sans: "Inter", system-ui, -apple-system, sans-serif;
  --font-display: "Inter", system-ui, -apple-system, sans-serif;
}

HTML structure:

html
<!DOCTYPE html>
<html lang="en">
  <head>
    ...
  </head>
  <body>
    <section class="hero">
      <h1>{Title}</h1>
      <p class="subtitle">{summary}</p>
      <time>{Date}</time>
    </section>
    <section class="problem">...</section>
    <section class="built"><!-- feature cards grid --></section>
    <section class="how"><!-- Mermaid diagram --></section>
    <section class="compare"><!-- Before/After --></section>
    <section class="impact"><!-- Impact numbers --></section>
    <section class="next"><!-- What's Next --></section>
    <section class="team"><!-- Credits --></section>
    <script>
      /* Mermaid init, scroll behavior */
    </script>
  </body>
</html>

Step 3: Generate Obsidian Canvas Companion

Generate a JSON Canvas (.canvas) file alongside the HTML.

Canvas structure:

  • Central node (text, color "6" purple): product/feature name + description
  • Component nodes arranged radially: green ("4") for new, blue ("6") for modified, no color for unchanged
  • Group nodes for clusters: Frontend, Backend, Data, Infrastructure
  • Edges with labels (connection type)
  • Layout: center at (0,0), groups in quadrants, nodes 300px apart

JSON Canvas format example:

json
{
  "nodes": [
    {
      "id": "center",
      "type": "text",
      "x": 0,
      "y": 0,
      "width": 400,
      "height": 200,
      "text": "# {Title}\n{summary}",
      "color": "6"
    },
    {
      "id": "group-frontend",
      "type": "group",
      "x": -600,
      "y": -500,
      "width": 500,
      "height": 400,
      "label": "Frontend"
    },
    {
      "id": "comp-1",
      "type": "text",
      "x": -550,
      "y": -400,
      "width": 200,
      "height": 100,
      "text": "**{Component}**\n{description}",
      "color": "4"
    }
  ],
  "edges": [
    {
      "id": "edge-1",
      "fromNode": "comp-1",
      "toNode": "center",
      "fromSide": "right",
      "toSide": "left",
      "label": "REST API"
    }
  ]
}

Step 4: Save and Open

  1. Save HTML to .presentations/{YYYY-MM-DD}-{kebab-title}/index.html
  2. Save Canvas to .presentations/{YYYY-MM-DD}-{kebab-title}/{kebab-title}.canvas
  3. Create the directory if it does not exist
  4. Open the HTML in the default browser:
    • macOS: open {path}

Step 5: Present CLI Summary

╭─ ATLAS ── atlas-present ────────────────────╮

  ## Presentation generated

  **Title:** {title}
  **Scope:** {date range or milestone}
  **Repos:** {list of repos involved}

  ### Deliverables
  → .presentations/{dir}/index.html (opened in browser)
  → .presentations/{dir}/{title}.canvas (Obsidian)

  ### Sections
  - Hero, Problem, What We Built ({N} features)
  - How It Works (architecture diagram)
  - Before/After, Impact, What's Next, Team

╰─────────────────────────────────────────────╯

Key Rules

  • Non-technical audience — no jargon, no implementation details
  • Outcome language — "You can now X" not "We added Y"
  • Numbers over adjectives — "3x faster" not "much faster"
  • Self-contained HTML — offline except Mermaid CDN
  • Canvas nodes must have meaningful descriptions — not just component names
  • Omit Before/After if no data — do not fabricate metrics
  • Manual trigger only — presentations are intentional

Delivery

If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

Frequently asked questions

What does the Atlas Present AI skill do?

Generate a polished HTML presentation page and Obsidian Canvas for big releases — new products, takeovers, major migrations. Non-technical audience. Use when asked to "present this", "release announcement", "show what we built", or "stakeholder update".

Why use Atlas Present on TypingMind?

Because you install it once and use it with any model. Atlas Present 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 Atlas Present in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tonone-ai/tonone/tree/main/skills/atlas-present. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Atlas Present?

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 Atlas Present?

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

Is the Atlas Present AI skill free?

Yes. It is published on GitHub by tonone-ai 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 👇