CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lyria

Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage `google_music`, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing exact-duration music for a video.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary instruction-only skill body: concrete commands and verbatim prompt material, a sequenced workflow with real validation and cost-governance checkpoints, and clean deferral of deep detail to a single well-signaled reference. The only blemish is inline volatile facts (prices, current adapter lock) that belong in the dated reference file.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — no explanations of what music generation or ffprobe are, and every section is directive. It falls short of the 5 anchor because time-sensitive details ("currently $0.04/request", "$0.08/request", adapter "currently ... locked to `lyria-3-pro-preview`", current resolver precedence) are stated inline rather than confined to the dated reference, and a few checklist lines restate earlier sections. It is clearly above the 3 anchor, which requires unnecessary explanation or notable slack.

4 / 5

Actionability

Fully executable guidance throughout: a copy-paste `ffprobe` command with exact flags and JSON output, a verbatim instrumental-only constraint block, a fully specified 9-point prompt structure with ordering, concrete vocal/lyric contracts with section labels, and specific auth error codes (`403`, `API_KEY_SERVICE_BLOCKED`) with an explicit credential-precedence rule. The 4 anchor's 'minor gaps' fit worse than the 5 anchor's copy-paste-ready coverage of the common cases (underscore, full song, vocals).

5 / 5

Workflow Clarity

The 8-step Required Workflow is clearly sequenced with explicit validation checkpoints ("Probe the actual file and listen before recording duration, format, or approval metadata"), feedback loops for error recovery (retry treated as a billable regeneration; "Do not spend retries on permission failures. Resolve the credential/project path first"), and a closing Quality Checklist. This matches the 5 anchor's validation + feedback-loop + checklist profile; the destructive/batch cap does not apply since probing and auditioning are mandated.

5 / 5

Progressive Disclosure

The body is a genuine overview that defers API shape, pricing detail, and prompt templates to a single one-level-deep reference, clearly signaled with when-to-read conditions ("Read [references/api-and-prompting.md](references/api-and-prompting.md) when choosing a model, designing vocals or custom lyrics, using image inputs, debugging the response, or checking current limits and pricing"). The reference file exists, is well-organized, and contains no nested .md references (only external links), matching the 5 anchor.

5 / 5

Total

19

/

20

Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description with an explicit what/when pair, third-person voice, and highly specific trigger phrases tied to concrete tools and workflows. The main gap is that the capability list itself is only two verbs deep, and a few natural synonyms (soundtrack, background music) are absent from the triggers.

Suggestions

Broaden the 'what' clause with one or two more capability verbs (e.g., 'structure prompts and verify generated audio'), keeping the description compact.

Add a common natural synonym such as 'background music' or 'soundtrack' to the trigger clause to catch users who don't name Lyria.

DimensionReasoningScore

Specificity

The 'what' is "Generate and validate music with Google Lyria 3 through the Gemini Interactions API" — the domain is named with exactly two concrete actions, matching the anchor for 1-2 concrete actions but not comprehensive coverage (e.g., no mention of prompt design, model selection, or output verification as capabilities). It is below the 4 anchor because the action list is minimal, and above 2 because both actions are specific rather than generic.

3 / 5

Completeness

Explicitly answers both questions: what — "Generate and validate music with Google Lyria 3 through the Gemini Interactions API"; when — "Use before calling OpenMontage `google_music`, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing exact-duration music for a video." This matches the 5 anchor's clear what-and-when with concrete trigger phrases; the 4 anchor ('when could be more explicit') fits less well given six explicit trigger scenarios.

5 / 5

Trigger Term Quality

Strong natural triggers: "OpenMontage `google_music`", "designing Lyria 3 Clip or Pro prompts", "image-to-music", "custom lyrics", "choosing between Lyria 3 and Lyria RealTime", "diagnosing Google music-generation failures", "exact-duration music for a video". A few common phrasings are missing (e.g., "soundtrack", "background music", "underscore", "song"), so it falls short of the comprehensive-synonym coverage of the 5 anchor but is well above the 3 anchor's 'missing common variations'.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Lyria 3 music generation via a specific API and tool) with distinct triggers like `google_music`, Lyria 3 Clip/Pro, and Lyria RealTime; it also actively disambiguates sibling skills ("choosing between Lyria 3 and Lyria RealTime"). Minimal overlap risk with generic music or audio skills, matching the 5 anchor.

5 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

calesthio/OpenMontage

Path

.agents/skills/lyria/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.