Copilot Updates

Turn GitHub changelog articles into polished, presentation-ready slides — automatically.

---

Fetch · Summarize · Translate · Present — in under 5 minutes.

Why  ·   How  ·   Demo  ·   Quick Start  ·   Usage  ·   Config  ·   Contribute

🎯 The Opportunity

GitHub ships product updates every single week — across Copilot, Actions, Security, and more.

For any team that tracks these changes, the same recurring challenge surfaces: how do you stay on top of everything, and share what matters with your audience in a meaningful way?

Today, the answer is usually manual:

• 📰 Someone reads through dozens of changelog articles
• 🔍 Picks what's relevant for their team or audience
• ✍️ Writes summaries, formats slides, repeats this every week

That's hours of low-leverage work — done by people who should be doing something harder.

✨ How It Works

This repository is a working AI pipeline powered by a repo-local Copilot skill that orchestrates everything — it calls Python scripts for deterministic work (scraping, validation, indexing, slide generation) and uses AI only for what requires it: writing structured summaries and speaker notes. The result is a polished, multilingual PowerPoint presentation — automatically.

┌──────────────────────────────────────┐ │ Copilot Skill 🤖 │ │ (orchestrator) │ │ │ │ 1. fetch_articles.py │ │ └─ scrape github.blog/changelog │ │ │ │ 2. process_articles.py --prepare │ │ └─ plan batch from raw articles │ │ │ │ 3. AI summarization │ │ └─ generate summaries + notes │ │ │ │ 4. process_articles.py --validate │ │ └─ check output format │ │ │ │ 5. process_articles.py --index │ │ └─ build index.md │ │ │ │ 6. create_pptx.py │ │ └─ assemble final slides │ └──────────────┬───────────────────────┘ ▼ 📊 presentation.pptx

⏱️ Time saved per week Task Before After Read & filter articles ~60 min 0 Write summaries ~5 min × N 0 Translate content ~2 hrs/lang 0 Format slides ~30 min 0 Total 3–4 hrs < 5 min

Note

This repository is the skill. Clone or symlink it to ~/.copilot/skills/copilot-updates/ to use it from any project. The skill supplies workflow knowledge; the Python scripts in scripts/ do the heavy lifting.

Important: generated artifacts are written to the current working directory where you invoke the skill, not to the skill folder itself. That means the skill will create output/ and .pptx files in the project or folder you are currently working in.

📸 Example Output

Every generated presentation uses a dark GitHub-themed design (16:9 widescreen) with four slide types:

Title Slide Date range, active label filters, and source	Section Divider Category header with article count
Article Hero Article title with hero image and date	Summary Structured content with source link & speaker notes

Tip

Summaries and speaker notes can be generated in any language. Article titles and technical terms always stay in English.

⬆ back to top

---

🚀 Getting Started

Prerequisites

Requirement	Notes
Python 3.11+	Core runtime
VS Code + GitHub Copilot	Optional for chat-based usage

Choose how you want to use the skill

You can use copilot-updates in two different ways:

Option 1 — Use it inside the cloned repository

Use this mode when you want to work directly in this repo.

• Clone the repository anywhere you like
• Open Copilot in this repository
• Run the pipeline from this repository root

In this mode, generated files are written inside this repo's working folder:

• .\output\raw\
• .\output\{locale}\...
• generated .pptx files in the repo root

Option 2 — Use it from outside the repository

Use this mode when you want the skill available from any project folder.

• Keep one clone of this repo somewhere on disk
• Register that clone under your user skills folder
• Invoke the skill while working in another folder or project

In this mode, generated files are written to the folder where you invoke the skill, not to the repo that contains the skill:

• C:\work\demo\output\raw\
• C:\work\demo\output\{locale}\...
• generated .pptx files in C:\work\demo\

Configure Option 2 — install as a global Copilot skill

# Clone to your user skills directory
git clone https://github.com/g-mercuri/copilot-updates ~/.copilot/skills/copilot-updates

# Or symlink an existing clone
ln -s /path/to/copilot-updates ~/.copilot/skills/copilot-updates

On Windows (PowerShell):

New-Item -ItemType SymbolicLink -Path "$env:USERPROFILE\.copilot\skills\copilot-updates" -Target "C:\path\to\copilot-updates"

Install Python dependencies

Run this once for the clone that contains the skill scripts:

cd scripts
uv sync

💡 Alternative: plain venv / pip

cd scripts
python -m venv .venv
.venv\Scripts\Activate.ps1   # Windows
source .venv/bin/activate    # macOS / Linux
pip install .

⬆ back to top

---

📖 Usage

Option A — Copilot Skill ✨ _{(recommended)}

VS Code If you are using Option 1, open Copilot Chat in this repository and ask Copilot to use the /copilot-updates skill. If you are using Option 2, open Copilot in the project folder where you want the output to be created, and then invoke the skill there.

Copilot CLI This repository is a self-contained Copilot skill (SKILL.md at the root). Option 1: run Copilot from this repo root if you want output written here Option 2: run Copilot from another folder if you want output written there You can ask in natural language, or invoke it explicitly: Run the copilot-updates pipeline for copilot articles from 2026-02-01 to 2026-02-25 in italian Use the /copilot-updates skill to create a weekly GitHub changelog presentation for copilot,actions from 2026-02-01 to 2026-02-25 in italian

In Copilot CLI, use /skills list to confirm the skill is available and /skills reload after editing skill files.

Warning

Check which folder you are currently in before invoking the skill. The pipeline writes output/raw/, output/{locale}/..., and the generated .pptx to your current working directory.

Example: if you run Copilot from C:\work\demo, the skill writes files under C:\work\demo\output\... and creates the presentation there.

You'll be prompted for:

Input	Example	Description
startDate	2026-02-01	Start of the date range
endDate	2026-02-25	End of the date range
labels	copilot,actions or all	Which changelog labels to include
language	italian, english, spanish	Output language for summaries

The skill orchestrates the full pipeline end-to-end:

Fetch → Prepare → Summarize → Validate → Index → PowerPoint

In practice, the important boundary is:

• scripts/fetch_articles.py, scripts/process_articles.py, and scripts/create_pptx.py do the deterministic work
• the skill reads output/batch.json, writes each processed article file under output/{locale}/..., and then resumes the scripted pipeline
• before validation, every target_file in output/batch.json should exist on disk

Tip

Re-running for the same date range is safe — both the scraper and the skill skip articles that already have output files.

Option B — Manual CLI

1️⃣ Fetch raw articles

python scripts/fetch_articles.py --labels copilot --from-date 2026-02-01 --to-date 2026-02-25

More examples & flags

# Multiple labels
python scripts/fetch_articles.py --labels copilot,actions,client-apps --from-date 2026-02-01 --to-date 2026-02-25

# All labels
python scripts/fetch_articles.py --labels all --from-date 2026-02-01 --to-date 2026-02-25

Flag	Default	Description
--labels, -L	copilot	Comma-separated label slugs, or all
--from-date	required	Start date (YYYY-MM-DD)
--to-date	required	End date (YYYY-MM-DD)
--output-dir, -d	output/	Output directory

2️⃣ Process articles

python scripts/process_articles.py --prepare --locale en \
  --from-date 2026-02-01 --to-date 2026-02-25

Between --prepare and --validate, run the Copilot skill (or write summaries manually) to generate the structured article files.

Then verify that every target_file listed in output/batch.json exists, and continue:

python scripts/process_articles.py --validate --locale en
python scripts/process_articles.py --index --locale en

[!TIP] --prepare only builds output/batch.json. It does not generate translated summaries by itself.

[!TIP] If you write summaries manually, assemble the full file: front matter, # title, optional ![hero](...), ---, then the structured body. Validation may pass even if a file is missing from the expected date range, so it is worth checking the batch manifest before generating the deck.

Flags

Flag	Default	Description
--prepare	—	Scan raw files and produce output/batch.json
--validate	—	Validate processed article files
--index	—	Generate/update index.md
--locale, -l	en	Locale code
--from-date	(none)	Start date filter (YYYY-MM-DD)
--to-date	(none)	End date filter (YYYY-MM-DD)
--labels, -L	(all)	Comma-separated label slugs to filter
--output-dir, -d	output/	Output directory

3️⃣ Generate the PowerPoint

python scripts/create_pptx.py --locale it --from-date 2026-02-01 --to-date 2026-02-25

More examples & flags

python scripts/create_pptx.py --label copilot
python scripts/create_pptx.py --label copilot,actions --categories new-release,improvement

Flag	Default	Description
--output-dir, -d	output/	Root directory containing locale subfolders
--locale, -l	en	Locale subfolder to read from
--output, -o	auto-generated	Output .pptx filename
--from-date	auto-detected	Start date filter
--to-date	auto-detected	End date filter
--label, -L	(all)	Comma-separated label slugs to filter by
--categories, -c	(all)	Comma-separated categories: new-releases, improvements, deprecations

⬆ back to top

---

⚙️ Configuration

All labels, categories, colors, and defaults live in scripts/config.yaml.

📋 Supported labels _{(13 labels)}

Slug	Display Name
account-management	Account Management
actions	Actions
application-security	Application Security
client-apps	Client Apps
collaboration-tools	Collaboration Tools
community-engagement	Community Engagement
copilot	Copilot
ecosystem-and-accessibility	Ecosystem & Accessibility
enterprise-management-tools	Enterprise Management Tools
platform-governance	Platform Governance
projects-and-issues	Projects & Issues
supply-chain-security	Supply Chain Security
universe25	Universe '25

📄 Article format

Each processed article follows this markdown structure:

---
title: "Article Title"
date: "2026-02-15"
type: "new-releases"
labels: ["copilot", "client-apps"]
image_url: "https://github.blog/wp-content/uploads/..."
article_url: "https://github.blog/changelog/2026-02-15-slug"
---

# Article Title

![hero](https://github.blog/wp-content/uploads/...)

---

## What's new

One-liner with **key product/feature** and **status**.

### Why it matters
- **Key benefit 1** — short explanation
- **Key benefit 2** — short explanation

### Where you can use it
- **Platform 1** — details

### Who gets it
- Plans, rollout info

<!-- speaker_notes: Speaker notes in the target language (5–8 sentences). -->

The ## heading varies by type: What's new (new-releases), What changed (improvements), What's deprecated (deprecations).

⬆ back to top

---

📂 Project Structure

copilot-updates/                          # Root IS the skill folder
├── SKILL.md                              # Skill definition (entry point)
├── scripts/
│   ├── fetch_articles.py                 # Stage 1 — Web scraper
│   ├── process_articles.py               # Stage 2 — Batch planning, validation, indexing
│   ├── create_pptx.py                    # Stage 3 — PowerPoint generator
│   ├── config.yaml                       # Centralized configuration
│   ├── pyproject.toml                    # Python dependencies
│   └── imgs/                             # Fallback hero images
├── references/                           # Summary format guides (loaded by SKILL.md)
│   ├── summarize-new-releases.md
│   ├── summarize-improvements.md
│   ├── summarize-deprecations.md
│   └── translate-content.md
├── docs/imgs/                            # README screenshots
├── output/                               # Generated artifacts (git-ignored)
│   ├── raw/                              # Scraped raw articles
│   └── {locale}/                         # Processed articles per language
├── README.md
├── LICENSE
└── .github/
    ├── copilot-instructions.md           # Repo-wide Copilot rules
    └── skills/
        └── make-skill-template/          # Skill scaffolding utility

---

🤝 Contributing

Contributions are welcome! Here's how to get started:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes
4. Open a Pull Request

Important

When adding new categories or labels, update scripts/config.yaml — all scripts read it at startup.

⬆ back to top

---

🙏 Credits

Special thanks to @congiuluc for conceiving and inspiring this solution.

Built entirely with GitHub Copilot.

---

MIT License · Made with ❤️ and 🤖