render-cinematic-music-video

Assemble a cinematic live-action-style music-video ad from a config — an original sung anthem carries the whole narrative while N 35mm-film-look i2v clips are each cut to their lyric window and hard-concatenated on the beat as a 3-act arc, the anthem muxed at loudnorm I=-14, cinematic lower-third serif captions built from the song's OWN word timings (never Whisper) with the hook line landing on the chorus drop, and closed on a brand end card composited from the real asset — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-window + hard concat + anthem mux + captions + end card); the anthem, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the cinematic-music-video format.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ads/capabilities/render-cinematic-music-video/SKILL.md

Quality

Content

55%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.

A well-organized, lean overview that points to real bundle materials and clearly separates the free assembly from paid stages. Its weaknesses are a lack of executable code/commands and no explicit numbered workflow with validation checkpoints.

Suggestions

Add a concrete numbered run workflow (e.g. build words.json → cut each clip to its window → hard-concat → mux anthem with loudnorm → burn ASS captions → overlay end card) with the actual ffmpeg/script commands.

Include a validation/checkpoint step (probe master dimensions, verify duration, check loudnorm target) and an error-recovery loop since rendering is destructive/batch.

Move or summarize the parameter-heavy contract clauses into the referenced scripts and keep the body as a tight overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the contract section restates concepts from the description and some clauses are verbose (e.g. 'Whisper on sung audio returns "Music Playing"'); minor trimming would help.	4 / 5
Actionability	The body gives high-level direction (cut-to-window, hard-concat, mux loudnorm I=-14, burn ASS captions) but no executable commands or code; it describes rather than instructs, deferring actual implementation to un-listed scripts.	2 / 5
Workflow Clarity	A sequence is implied (anthem first → snap tableau boundaries → cut clips → hard-concat → mux → captions → end card) but there are no explicit numbered steps, no validation checkpoints, and no error-recovery feedback loop for this destructive/batch render despite the cap guidance.	3 / 5
Progressive Disclosure	Well structured into Run/Contract sections with clearly signaled one-level-deep references to real bundle files (scripts/config.example.json, scripts/PIPELINE.md, scripts/README.md) that exist and are appropriately split out.	4 / 5
	Total	13 / 20 Passed

Description

85%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 dense, highly specific description that crisply defines the free deterministic assembly stage and its sibling paid capabilities, with clear distinctiveness. Its main weakness is trigger-term naturalness and an only-weakly-explicit 'when' clause.

Suggestions

Add more natural user-facing trigger phrases (e.g. 'Use when assembling a music-video ad, cutting film clips to lyrics, or building a cinematic anthem-driven spot').

Soften the acronym/parameter density (loudnorm I=-14, force_instrumental false) in the description and push those specifics into the body.

Dimension	Reasoning	Score
Specificity	Lists many concrete assembly actions (cut-to-window, hard-concat on the beat, anthem mux with loudnorm I=-14, lower-third serif captions from word timings, end card composite) with comprehensive coverage of the format's mechanics.	5 / 5
Completeness	Clearly answers 'what' (the FREE deterministic assembly: cut-to-window + hard concat + anthem mux + captions + end card) and includes a 'Use for the cinematic-music-video format' when-clause, but the 'when' could be more explicit with concrete user trigger phrases.	4 / 5
Trigger Term Quality	Names concrete format signals ('cinematic-music-video', 'i2v clips', 'anthem', 'end card') but lacks common natural user synonyms and file extensions a user would say; the trigger phrase is somewhat specialized jargon.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (cinematic music-video assembly) and explicitly names sibling capabilities (create-music-elevenlabs / create-image-fal / create-video-fal), minimizing overlap and 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-cinematic-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.