القائمة
Generate show metadata (JSON) containing timecoded transcript, title, duration, summary, and date by sending audio and transcript to Gemini.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Guides the agent on how to handle git operations and generate .patch files instead of submitting PRs.
Guides the agent on how to read and search GitHub issues to understand the repository's problems.
Records and appends every user-agent customer support interaction to the memory.md log in the workspace.
Scans a website deeply, converting HTML pages to markdown, respecting robots.txt, and updating the snapshots log.
Exposes a 100% local, offline PDF batch extraction utility (extract_to_markdown.py) that isolates invoices under invoices/ and translates PDFs into clean Markdown files for LLM-native parsing.
Reconcile loaded expenses against the pre-parsed invoice database, flagging discrepancies like amount mismatches, missing invoices, and merchant mismatches locally.
| name | metadata-generation |
| description | Generate show metadata (JSON) containing timecoded transcript, title, duration, summary, and date by sending audio and transcript to Gemini. |
Generate a structured JSON file containing metadata for the radio show. This is done by sending the final mixed audio file and the original transcript back to Gemini.
pip install google-genai
./workspace/data/script.md and the final audio from ./workspace/audio/final/ai_radio.mp3.gemini-3-flash-preview) using the Interactions API, passing the uploaded audio file and the transcript../workspace/data/show_notes.json.The skill is implemented in scripts/generate_metadata.py.
# Example usage
python3 skills/metadata-generation/scripts/generate_metadata.py --workspace ./workspace
The skill produces a JSON file at ./workspace/data/show_notes.json with the following structure:
{
"show_title": "...",
"show_duration": "...",
"two_sentence_summary": "...",
"date_of_generation": "YYYY-MM-DD",
"timecoded_transcript": [
{
"timecode": "MM:SS",
"speaker": "...",
"text": "..."
},
...
]
}