Individual skill
generate_podcast
Not available
Meta/muse-agent/skills/generate_podcast/SKILL.md
Source commit a2d33761e49b98f6ec1b48f12143264eb9b4ff4f
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Network or broad shell
- Last checked
- Nov 10, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
Standard SKILL.md format has not been attested at this commit. No installation command is available; inspect the source.
Repository context
- Repository stars (not skill ratings)
- 71,199
- Repository last updated
- Nov 10, 2026
- License
- CC0-1.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai Repository topic
- anthropic Repository topic
- chatbot Repository topic
- chatgpt Repository topic
- claude Repository topic
- claude-code Repository topic
- codex Repository topic
- gemini Repository topic
- generative-ai Repository topic
- google Repository topic
Declared tags are partial or unavailable.
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 7,550 bytesreferences/podcast_preferred_voices.jsonasset · 3,264 bytesreferences/production.mddoc · 6,108 bytesreferences/publishing.mddoc · 8,065 bytesreferences/save-to-spotify.mddoc · 2,672 bytesreferences/script.mddoc · 3,378 bytessave-to-spotify/vendor/save-to-spotify/README.mddoc · 2,524 bytesskill.yamlasset · 344 bytes
Read excerpt
# Podcast Production
## Plan the episode
- Use [Spoken Audio](/opt/muse/skills/spoken-audio/SKILL.md) for a voice message, narration for an artifact or a word-for-word reading. This skill covers composed episodes, briefings and narrated summaries.
- Settle the topic, the angle and who will listen before writing. Aim for 5 to 15 minutes unless the user asks otherwise. A spoken script runs about 130 words a minute.
- Read the catalog with `/opt/muse/skills/generate_podcast/scripts/podcast-helper manifest read` and look at each recent episode's `topics`. Choose fresh material or a new angle rather than covering the same ground again, which matters most in a recurring series.
- Research facts that change, such as news, scores or prices, when you produce the episode. Build it around one clear idea or progression rather than a list of facts.
## Cast the hosts
- For an existing podcast series, reuse its recorded host names and exact synthesis voice IDs from the schedule or the series' casting record in `~/MEMORY.md`. A fixed cast in a cron body is the series' established cast, not a default to recompute. Do not change it because Muse's name or voice changed, or because this skill was updated; recast only when the user explicitly asks to change the series' hosts. If the established cast cannot be recovered, ask rather than silently choosing new voices.