CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

muapi-music-video

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

Quality

72%

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

Fix and improve this skill with Tessl

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

Quality

Content

75%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.

The body is a tight, executable runbook: a concrete input table, a correctly sequenced two-layer parallel plan with dependencies and error fallbacks, and copy-nearly-paste-ready CLI guidance including a raw-endpoint fallback. Remaining improvements are structural (merge the two Notes sections, drop the duplicated description line) and a missing output-verification step before returning assets.

Suggestions

Merge the two "Notes" sections ("## Notes" and "## Notes for the Executing Agent") into one and remove the duplicated bold subtitle line at the top to tighten conciseness.

Add an explicit verification step in Layer B or the return phase (e.g. confirm each clip has a non-empty url and the music track duration covers N × 5s before returning asset ids).

Include one complete example invocation of a muapi command with full flag syntax (e.g. a sample `muapi image generate` call for scene 1) so execution does not depend on inferring argument formats, and fill the empty visual_style description cell.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence (command names, model IDs, a duration formula, a fallback curl invocation) with no concept over-explanation. Not 5 because the frontmatter description is repeated verbatim as the bold subtitle and the two "Notes" sections overlap, both trimmable.

4 / 5

Actionability

Concrete commands with specific parameters (muapi image generate with model=nano-banana-pro, muapi audio create kind=music with duration N × 5 + 2s tail, muapi video from-image model=veo3.1-image-to-video duration=5) plus a near copy-paste curl fallback and polling command. Not 5 because no full example invocation shows complete flag syntax, and "image=$nX.url" is schematic.

4 / 5

Workflow Clarity

A clear two-layer sequence with explicit parallelism and dependency, a per-scene failure fallback (video from-image → text-to-video), failover retries, and a cost checkpoint (no auto-confirm above 50 cr). Not 5 because there is no explicit verification of generated assets before returning them, and the failure fallback prevents the batch-operation cap at 3 from applying.

4 / 5

Progressive Disclosure

A single-file skill of roughly 50 lines with well-organized sections (Inputs, Steps, Notes, Trigger Keywords) and no external references needed, so the simple-skill exception nearly applies. Not 5 because of minor organization gaps: duplicate "Notes" headings split by a bare --- divider, a repeated description line, and an empty visual_style description cell.

4 / 5

Total

16

/

20

Passed

Description

58%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.

The description is specific and distinctive, accurately summarizing the full keyframe-to-animation-to-music pipeline in one line. Its main weakness is the missing "Use when..." trigger clause and the absence of trigger variations within the description itself, which caps both completeness and trigger-term quality.

Suggestions

Append an explicit "Use when..." clause to the description (e.g. "Use when the user asks for a music video, song visualization, or an MV from a theme") to lift completeness above the cap of 3.

Fold the natural trigger variations already listed in the body ("music video", "mv", "video story", "song visualization") into the description itself so users' phrasings match without the body being loaded.

Name the concrete deliverable form (N animated 5s clips plus one synced music track) in the description to close the coverage gap that keeps specificity and distinctiveness at 4.

DimensionReasoningScore

Specificity

"N keyframes, animate each, generate matching music" names the domain and three concrete pipeline actions, matching the several-specific-actions-with-minor-gaps anchor. Not 3 (more than 1-2 actions) and not 5 (no mention of the tool used or final output form, so coverage is not comprehensive).

4 / 5

Completeness

The description clearly answers "what" (build a music video from keyframes, animation, and music) but has no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

The description contains natural phrases like "music video" and "song theme", but common variations and synonyms ("mv", "video story", "song visualization") appear only in the body's Trigger Keywords section, not in the description itself. Not 2 because "music video" is a specific, natural user phrase rather than generic filler.

3 / 5

Distinctiveness Conflict Risk

"Build a short music video from a song theme" is a clear niche with minimal conflict risk, though it could overlap with generic image- or video-generation skills. Not 5 because the anchor-5 example pairs the niche with distinct explicit triggers, which this description lacks.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.