muapi-music-video

Build a short music video from a song theme — N keyframes, animate each, generate matching music.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./library/motion/music-video/SKILL.md

Quality

Content

72%

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

The body is concise, well-structured, and self-contained with a clear parallel-layer workflow and failover handling. Main gaps are copy-paste-ready command examples and an explicit validation checkpoint between the batch generation layers.

Suggestions

Add complete executable command examples (e.g. a full `muapi image generate --prompt … --model nano-banana-pro …` block) so the workflow is copy-paste ready.

Insert an explicit validation step between Layer A and Layer B — verify each keyframe/music asset succeeded before animating — to satisfy the batch-operation feedback-loop requirement.

Fix the 'Build one the plan covering:' typo to 'Build the plan covering:' for clarity.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no explanation of what a music video or keyframe is, just inputs, steps, and notes. It is not a 2 because there is no padded concept re-explanation; the only minor redundancy is the restated bold description line.	3 / 3
Actionability	Provides specific model IDs and parameters (nano-banana-pro, veo3.1-image-to-video, duration=5, kind=music) but the main workflow commands are described in prose rather than as complete, copy-paste command strings. It is not a 3 because no fully executable command block with all flags is given, and not a 1 because concrete model/param details are present.	2 / 3
Workflow Clarity	Layer A → Layer B → Return is clearly sequenced with an explicit failover fallback and a cost checkpoint, but there is no explicit validation step confirming Layer A outputs succeeded before animating in Layer B. Per the batch-operation guidance, missing validation caps this at 2; it is not a 1 because the sequence and error recovery are clearly stated.	2 / 3
Progressive Disclosure	Self-contained skill with no bundle files and well-organized sections (Inputs, Steps, Notes, Trigger Keywords, Agent Notes); per the under-50-line simple-skill guidance this earns the top anchor. It is not a 2 because content is appropriately sectioned inline with no nested or misplaced references.	3 / 3
	Total	10 / 12 Passed

Description

67%

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

The description is specific and occupies a distinct niche, but lacks an explicit 'when to use' clause and only partially covers natural trigger phrasings. Adding a 'Use when…' sentence would lift completeness and trigger coverage.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user wants to create a music video, song visualization, or MV from a theme.'

Add common natural variations such as 'mv' and 'song video' to broaden trigger_term_quality.

Keep the concrete action list as-is — it already hits the top specificity anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build a short music video', 'N keyframes', 'animate each', 'generate matching music' — matching the highest anchor. It is not a 2 because it enumerates several specific operations rather than naming a domain with only some actions.	3 / 3
Completeness	Clearly answers 'what' (build/Animate/generate) but has no explicit 'Use when…' trigger guidance in the description field, which caps completeness at 2 per the guidelines. It is not a 1 because the 'what' is strong and explicit.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('music video', 'song', 'music') but misses common variations a user might say such as 'mv' or 'song video'. It is not a 3 because coverage of natural phrasings is narrow, and not a 1 because the core terms are user-facing rather than jargon.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche — generating a music video from a song theme — with distinct triggers unlikely to overlap other skills. It is not a 2 because it is not merely 'works with video files' but a specific multi-asset generation pipeline.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: SamurAIGPT/Generative-Media-Skills
Path: library/motion/music-video/SKILL.md
Commit: 71242e2

Reviewed: about 21 hours ago

Table of Contents

Discovery Implementation Validation

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.