Ppt Html Calibration Editor logo

Ppt Html Calibration Editor

Community
chenxupeng1990-eng
ppt-html-calibration-editor

Use when a fixed 16:9 HTML slide, presentation page, or PNG-rendering template needs browser-based copy editing, text-box adjustment, image replacement, drag/resize calibration, local persistence, JSON handoff, or a clean separation between edit mode and screenshot mode.

Overview

Publisherchenxupeng1990-eng
Repositoryqifei-proposal-skill
Skill nameppt-html-calibration-editor
Stars
74
Forks
4
Bundled files
14
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.

  • 14 bundled files

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

  • Open source

    Published by chenxupeng1990-eng on GitHub. Read the source before you install it.

Installation

Install the Ppt Html Calibration Editor 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/chenxupeng1990-eng/qifei-proposal-skill/tree/codex/qifei-proposal-base/skills/ppt-html-calibration-editor
  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/chenxupeng1990-eng/qifei-proposal-skill.git /tmp/qifei-proposal-skill
mkdir -p .claude/skills
cp -r /tmp/qifei-proposal-skill/skills/ppt-html-calibration-editor .claude/skills/ppt-html-calibration-editor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ppt Html Calibration Editor 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 Ppt Html Calibration Editor 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 Ppt Html Calibration Editor 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.

PPT HTML Calibration Editor

Purpose

Add a lightweight browser calibration layer to fixed 1920×1080 slide HTML. This is for review and precise handoff, not a replacement for Figma or PowerPoint.

Read references/editor-contract.md before modifying an existing renderer. Copy assets/browser-editor/ into the target project when the editor is not already present.

Integration

  1. Keep the logical slide at exactly 1920×1080.
  2. Load editor.css and loader.js from the copied editor package.
  3. Set a stable document ID on body:
html
<body data-document-id="proposal-name">
  1. Opt in only elements the user may change:
html
<h1 data-editable="text" data-edit-id="slide12.title">Title</h1>
<img data-editable="image" data-edit-id="slide12.product" src="product.png" alt="">
  1. Leave backgrounds, decorative layers, page spines, logos, and fixed brand identifiers locked unless the user explicitly requests access.

Modes

  • Preview: open normally; editor does not mount.
  • Edit: ?edit=1&capture=<slide-id>.
  • Full-deck copy edit: ?edit=all; all slides remain visible and opted-in text can be edited in one scrolling document.
  • Screenshot: ?capture=<slide-id>; editor DOM must not exist.
  • Dedicated clickable review entry: create a thin HTML wrapper or set data-editor-auto="true" only on a demo/review page. Never auto-enable editing on a production capture page.

Serve through HTTP rather than file://:

bash
python3 -m http.server 4173

Windows PowerShell 使用:

powershell
py -3 -m http.server 4173

如果没有 Python Launcher,可使用 python -m http.server 4173。

ChatGPT/GPT Work web previews may render HTML without executing local modules or interactive file APIs. For real editing, use Codex desktop/local preview or a normal browser connected to the local server.

Required behavior

  • Single click selects; double click edits text; Escape exits editing.
  • Drag uses 1920×1080 logical coordinates independent of display scale.
  • Text boxes resize freely; images resize proportionally.
  • Text properties include font size, weight, line-height ratio, color, and alignment.
  • Image properties include replacement, opacity, and z-index.
  • Persist after a 300 ms debounce to ppt-editor:<documentId>:<slideId>:v1.
  • Support undo/redo and validated schema-versioned JSON import/export.
  • Make the UI explicit that browser saving does not rewrite source HTML.
  • Keep replacement images below the configured local-storage limit; default to 2.5 MB because data-URL encoding expands the stored payload.
  • Text calibration is plain text only. Imported legacy html values must be stripped to text before application; never inject imported markup into a slide.

Source handoff

Treat exported JSON as a calibration record. Read it, apply copy/geometry/style changes to HTML/CSS, copy replacement image files into project assets, then rerender the slide. Never assume localStorage is the production source of truth.

Verification

Before delivery, use a real browser to verify:

  1. no-query production capture has no .ppt-editor-root;
  2. edit mode mounts and selects opted-in elements;
  3. double-click creates contenteditable="true";
  4. drag, resize, typography, image replacement, undo/redo, reload persistence, JSON exchange, and proportional image sizing work;
  5. the clean render remains 1920×1080 with no new overflow;
  6. a direct review entry actually starts edit mode without requiring the user to type query parameters.

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 Ppt Html Calibration Editor AI skill do?

Use when a fixed 16:9 HTML slide, presentation page, or PNG-rendering template needs browser-based copy editing, text-box adjustment, image replacement, drag/resize calibration, local persistence, JSON handoff, or a clean separation between edit mode and screenshot mode.

Why use Ppt Html Calibration Editor on TypingMind?

Because you install it once and use it with any model. Ppt Html Calibration Editor 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 Ppt Html Calibration Editor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/chenxupeng1990-eng/qifei-proposal-skill/tree/codex/qifei-proposal-base/skills/ppt-html-calibration-editor. 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 Ppt Html Calibration Editor?

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 Ppt Html Calibration Editor?

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

Is the Ppt Html Calibration Editor AI skill free?

It is published on GitHub by chenxupeng1990-eng. Check the repository for licensing terms. 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 👇