agentleFS
Microsoft AzureKnown publisherAzure/azure-dev/.github/skills/weekly-demo-video/SKILL.md

weekly-demo-video

Skill573 starsChanged 8 months agoMITView on GitHub

**WORKFLOW SKILL** — Generate narrated weekly demo videos for azd features. Pulls latest commits, identifies demo-worthy features, researches PRs, and produces MP4 videos with dark-themed slides and neural TTS narration.

  • Installs packages

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ensure these tools are installed:

    line 25
  2. Distinctive:

    Use the current week window (7 days).

    line 59
  3. Distinctive:

    Look for: new commands, UX improvements, perf gains, new flags, agent features.

    line 64
  4. Distinctive:

    Use explore agents in parallel to research each feature group (give them specific commit SHAs).

    line 66
  5. Distinctive:

    Follow the conventions strictly:

    line 74
  6. Distinctive:

    ffmpeg failure: Check the ffmpeg error output.

    line 85
  7. Very specific:

    All videos go to: <repo-root>/demo-video/

    line 90

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Weekly Demo Video Generator

Generates narrated MP4 demo videos for azd features using Python + Pillow + edge-tts + ffmpeg.

Prerequisites

Ensure these tools are installed:

ToolPurpose
Python 3Script execution
PillowSlide generation (pip install Pillow)
ffmpegVideo/audio stitch
edge-ttsNeural TTS (pip install edge-tts)

Verify prerequisites (bash):

python3 -c "from PIL import Image; print('ok')"
ffmpeg -version
edge-tts --list-voices > /dev/null

Execution Flow

Step 1: Pull latest

cd <repo-root>  # the azure-dev repository root
git checkout main && git pull --rebase

Step 2: Find commits for the week

Replace the dates below with the actual week range:

git log --oneline --since="YYYY-MM-DD" --until="YYYY-MM-DD" --no-merges

Use the current week window (7 days). For sprint demos, use a 2-week window.

Step 3: Identify demo-worthy features

Group related commits. Skip: typos, CI fixes, test-only, deps bumps, docs-only. Look for: new commands, UX improvements, perf gains, new flags, agent features.

Use explore agents in parallel to research each feature group (give them specific commit SHAs).

Step 4: Confirm with user

Present a table of proposed demos. Ask user to confirm or adjust before generating.

Step 5: Generate videos

Follow the conventions strictly:

{{ references/CONVENTIONS.md }}

Step 6: Report

List generated videos with filenames and durations. Offer short descriptions for docs.

Error Handling

  • edge-tts failure: Retry once. If it fails again, log the error and skip that slide's audio — notify the user.
  • ffmpeg failure: Check the ffmpeg error output. Common issues: missing codec, invalid image path. Print the error and stop — don't produce a partial video.
  • Font not found: Falls back to ImageFont.load_default() automatically. Warn the user that slides may look different.

Output

All videos go to: <repo-root>/demo-video/

Note: demo-video/ is listed in .gitignore to prevent accidental commits.

Demo Naming

  • Weekly demos: azd_weekly_demo_{date}_{name}.mp4 (e.g. azd_weekly_demo_may_07_exegraph.mp4)
  • Sprint demos: azd_sprint_demo_{date}_{name}.mp4 (e.g. azd_sprint_demo_apr_28_agent_sessions.mp4)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.