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

71%

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

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 well-structured with clear progressive disclosure to real bundle files and a sound assembly sequence, but it is somewhat repetitive and stops short of executable, copy-paste guidance with explicit validation checkpoints.

Suggestions

Add a short, executable ffmpeg command block for the canonical assembly so the guidance is copy-paste ready rather than descriptive.

Include an explicit validate → fix → re-run checkpoint (e.g. probe the concat / verify loudnorm) given this is a batch ffmpeg operation.

Trim the repeated 'FREE / deterministic / $0' framing to a single statement to recover tokens.

Dimension	Reasoning	Score
Conciseness	Largely assumes Claude's competence and avoids explaining known concepts, but the 'FREE, deterministic, $0' point is restated across the intro, Run, and Contract sections and could be tightened.	2 / 3
Actionability	Gives specific ffmpeg flags ('scale=1080:1920 increase', 'loudnorm I=-14', '--placement low') but provides no copy-paste executable code block in the body — the runnable scripts are referenced as living in external client-run directories.	2 / 3
Workflow Clarity	The four-stage sequence (cut → hard-concat → mux → captions → end card) and its ordering rationale are clear, but the body lacks explicit validate-fix-retry checkpoints for this batch/ffmpeg operation, capping it per the rubric.	2 / 3
Progressive Disclosure	Points to real one-level-deep bundle files — 'scripts/config.example.json', 'scripts/PIPELINE.md', 'scripts/README.md' (all present) — with content appropriately split and clearly signaled navigation.	3 / 3
	Total	9 / 12 Passed

Description

85%

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 distinctive, with an explicit use clause and third-person voice. Its main weakness is trigger-term quality: jargon-heavy phrasing crowds out the natural keywords a user would say.

Suggestions

Soften jargon in the description (e.g. 'i2v clips', 'loudnorm I=-14', 'lower-third serif captions') or pair it with plain-language equivalents users would naturally say.

Add common natural variations of the trigger ('music video ad', 'lyric video', 'film-look ad') alongside the technical phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete assembly actions — 'cut-to-window', 'hard-concatenated on the beat', 'anthem muxed at loudnorm I=-14', 'cinematic lower-third serif captions', and 'brand end card composited from the real asset' — matching the top anchor.	3 / 3
Completeness	Clearly states what it does (the FREE deterministic assembly stages) and gives an explicit when clause — 'Use for the cinematic-music-video format' — using third-person voice.	3 / 3
Trigger Term Quality	Contains relevant terms ('cinematic music-video', 'lyric window', 'captions') but leans on technical jargon ('i2v clips', 'loudnorm I=-14', 'lower-third serif') and omits common natural variations a user would actually say.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (cinematic music-video assembly with anthem-driven captions) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: gooseworks-ai/goose-skills
Path: skills/ads/capabilities/render-cinematic-music-video/SKILL.md
Commit: 8866b2a

Reviewed: 1 day 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.