render-cartoon-music-video

Assemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one recurring animated character, one look pack) are each cut to their BAR window from librosa beat-tracking and hard-concatenated on the bar, VEED-whisper white bold-sans captions in the BOTTOM third (Alignment 2, above the logo bug, no pill) burned from the song's word timings re-spelled against the locked lyrics, a persistent brand logo bug held over the body (suppressed on the end card), and closed on a solid-brand-color PIL end card with the song still playing under it — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-bar + hard concat + logo bug + captions + end card + song mux); the song, character, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the cartoon-music-video format.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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 well-structured contract overview with strong per-scene QC feedback loops and clean one-level-deep references to real bundle files. Its main gaps are the absence of any copy-paste code or script invocation in the body itself, and notable duplication of the description's pipeline summary.

Suggestions

Add at least one complete, copy-paste-ready example — e.g., the exact ffmpeg composite command or the `scripts/stitch.py` invocation — so the body is executable without opening the referenced files.

Remove the pipeline summary already covered by the description (cut-to-bar + hard concat + logo bug + captions + end card + song mux) to tighten the body and avoid redundancy.

Make the in-body run order explicit with a short numbered sequence (or a one-line pointer to PIPELINE.md's 6-step order) so the contract reads as a sequenced workflow rather than parallel bullets.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely token-efficient, skipping generic explanations, but it duplicates much of the description (cut-to-bar, hard-concat, logo bug, captions, end card) and carries a few padded parentheticals ('A diffusion model garbles a wordmark').	4 / 5
Actionability	Provides concrete, specific parameters (librosa 4/4, ~4–5 words/cue, margin_v, `overlay=…:enable='between(t,st,en)'`, `loudnorm I=-14`, 1080×1920 h264+aac) and a real ffmpeg filter fragment, but includes no complete copy-paste code block or script invocation in the body itself.	4 / 5
Workflow Clarity	The QC bullet is a strong explicit feedback loop (per-scene QC, FACE/HAND crops, regenerate the drifted KEYFRAME not re-cut, re-check served bytes after publish), but the in-body contract is presented as parallel bullets rather than a strictly ordered run sequence (the ordering lives in PIPELINE.md).	4 / 5
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep references to real bundle files (`scripts/config.example.json`, `scripts/PIPELINE.md`, `scripts/README.md`), each annotated with what it contains; content is appropriately split between SKILL.md and scripts/.	5 / 5
	Total	17 / 20 Passed

Description

83%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 highly specific and clearly distinct, with an explicit 'Use for...' trigger that satisfies the completeness floor. Its main weakness is that the 'when' is a terse format name and the natural-language trigger coverage leans on internal pipeline jargon rather than phrasings a user would actually say.

Suggestions

Add a concrete 'Use when...' clause naming request phrasings a user would naturally say (e.g., 'Use when the user wants to make a cartoon/animated music-video ad from a song and per-bar clips').

Trim implementation minutiae from the description (Alignment 2, 'no pill', 'never AI-rendered text') and keep it in the body to reduce padding while preserving specificity.

Dimension	Reasoning	Score
Specificity	Names multiple concrete assembly actions — cut-to-bar, hard-concat on the bar, librosa beat-tracking, word-timing re-spelling, logo bug burn, captions, solid-color end card, song mux — giving comprehensive coverage of the capability.	5 / 5
Completeness	Clearly answers 'what' with a detailed assembly description and provides an explicit 'when' via 'Use for the cartoon-music-video format', but the trigger is a terse format reference rather than concrete request scenarios.	4 / 5
Trigger Term Quality	Includes natural medium synonyms ('cartoon / animated / hand-crafted music-video ad') plus an explicit 'Use for the cartoon-music-video format' trigger, but most keywords are internal pipeline jargon (i2v, Alignment 2, VEED-whisper) and a few common requester phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — the FREE deterministic assembly stage — and explicitly names its sibling paid capabilities (create-music-elevenlabs / create-image-fal / create-video-fal), minimizing conflict risk.	5 / 5
	Total	18 / 20 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: gooseworks-ai/goose-skills
Path: skills/ads/capabilities/render-cartoon-music-video/SKILL.md
Commit: 2523432

Reviewed: 7 days 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.