Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add calesthio/generative-media-skills --skill google-lyriagit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/calesthio/generative-media-skills/google-lyria)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/google-lyria"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/google-lyria/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/google-lyria"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/google-lyria.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.04164 |
| Opus 5 | $0.00045 | $0.02082 |
| Sonnet 5 | $0.00018 | $0.00833 |
| Haiku 4.5 | $0.00009 | $0.00416 |
Grade A, and why
google-lyria scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Lyria music generation
Use this skill when a production plan calls for Google Lyria as the music-generation provider. It is for selecting the right Lyria model, writing usable music prompts, deciding when Lyria is inappropriate, and packaging generated music safely for videos, ads, social clips, apps, or internal content.
Facts in this skill were verified against official Google Cloud and Google DeepMind sources on 2026-07-10. Treat model IDs, limits, launch stages, pricing, regions, and policy behavior as volatile; re-check official docs before committing spend, compliance claims, or product launches.
Provider boundary
Documented facts:
- Lyria is Google's music-generation model family. Lyria 3 is documented as synthesizing music from text prompts and outputting audio music plus text lyrics.
- Google Cloud documentation currently appears under Gemini Enterprise Agent Platform and may be reached from Vertex AI / Generative AI on Vertex AI links. Do not assume an older Vertex AI URL means the API contract is unchanged.
- The production-relevant Google Cloud models are:
lyria-3-pro-preview: preview model for full-song music generation.lyria-3-clip-preview: preview model for 30-second clips.lyria-002: Lyria 2, documented as generally available and instrumental-only in the API reference.
- Lyria is not a general audio editor, stem separator, music transcription tool, MIDI renderer, or licensed-catalog search engine. Use another tool if the user needs exact beat matching to an existing song, remixing of copyrighted source music, stem extraction, or guaranteed legal clearance.
Production implication:
Use Lyria for new music creation, not for reproducing existing songs, mimicking named artists, cloning voices, or manufacturing "soundalikes." If the brief references a commercial track, convert it into neutral musical attributes: tempo, instrumentation, energy curve, era, arrangement density, and emotional function.
Model choice
Use lyria-3-pro-preview when the deliverable needs a coherent song or long-form music bed: intros, verses, choruses, bridges, vocal sections, timed lyrics, or scene-by-scene scoring up to roughly three minutes. Official docs list maximum clip length as 184 seconds, one clip per prompt, 44.1 kHz, 192 kbps, MP3 output, global region, preview launch stage, and 2026-03-25 release date for this model.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 259 lines · 90 tokens per session scan A 5588ad487751
google-lyria is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 4,164 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…