CtrlK
BlogDocsLog inGet started
Tessl Logo

render-song-mv

Assemble a song-driven music-video ad from a config — a generated sung track carries the whole narration across N tableaux (one keyframe -> one i2v clip per lyric beat) with NO separate voiceover, captions synced to the song's OWN word timings (script-window, never Whisper) and the hook word landing on the chorus drop, closed on a PIL brand end card. This is the FREE deterministic assembly stage (clip cut-to-timeline + captions + end card + FFmpeg composite); the song, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the song-driven-music-video format.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/ads/capabilities/render-song-mv/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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 well-structured overview with excellent progressive disclosure and a clear assembly sequence, but it is held back by repeated cost/emphasis padding and a lack of executable commands or validation checkpoints in the body itself.

Suggestions

De-duplicate the FREE/$0 emphasis (stated ~4 times across Run and Contract) into a single statement to tighten conciseness.

Add at least one concrete, copy-paste FFmpeg command for the composite/mux step (or an explicit pointer to the exact script/section to run) to lift actionability from descriptive to executable.

Add a validation checkpoint for the batch clip step (e.g., verify N clips match N lyric beats before hard-concat, and confirm loudnorm hits −14 LUFS) to introduce a feedback loop into the workflow.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept explanations, but the 'FREE / $0 / spends nothing / no paid calls' point is repeated ~4 times and the intro paragraph rehashes the description, so not every token earns its place.

2 / 3

Actionability

Concrete parameters appear ('Chunk ~3 words at lyric boundaries', 'loudnorm to −14 LUFS → 1080×1920 h264+aac') but there is no actual executable FFmpeg command or code in the body — the runnable detail is deferred to referenced files.

2 / 3

Workflow Clarity

The sequence is clear (song first → timeline → cut clips → hard-concat → captions → end card → mux), but there are no explicit validation checkpoints, and the N-clip batch operation should have a feedback loop per the scoring notes.

2 / 3

Progressive Disclosure

A concise overview points to three well-signaled, one-level-deep references ('scripts/config.example.json', 'scripts/PIPELINE.md', 'scripts/README.md'), all verified to exist on disk.

3 / 3

Total

9

/

12

Passed

Description

100%

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, complete, and well-differentiated, with explicit what/when guidance and natural trigger terms. Its only weakness is verbosity — it packs in implementation jargon (i2v, tableaux, force_instrumental) that users would not say.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'clip cut-to-timeline + captions + end card + FFmpeg composite' and 'one keyframe -> one i2v clip per lyric beat' — rather than vague language.

3 / 3

Completeness

Explicitly answers both what ('Assemble a song-driven music-video ad from a config') and when ('Use for the song-driven-music-video format'), with an explicit trigger clause.

3 / 3

Trigger Term Quality

Good coverage of natural terms a user would say ('song-driven music-video', 'music-video ad', 'sung track', 'lyrics', 'chorus drop', 'hook'), well beyond the 'some relevant keywords' bar.

3 / 3

Distinctiveness Conflict Risk

A clear niche with distinct triggers ('NO separate voiceover', 'captions synced to the song's OWN word timings', named sibling skills), making it unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation15 / 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
gooseworks-ai/goose-skills
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.