render-vo-anchored-motion-listicle

Assemble an expert/educator motion-graphic LISTICLE video ad from a config — a spoken authoritative voiceover carries a numbered listicle while N web-animated hyperframe beats (HTML plus the Web Animations API, one branded design system of alternating tiles, big hero numerals, and glass-pill callouts) are rendered frame-by-frame via Playwright and anchored to the VO's word-level timestamps, periodic color-graded B-roll windows give visual breath, and captions burn ONLY inside those B-roll windows (2-word chunks, ASS Format header carrying a Name field so none drop) with the VO mixed under a low music bed. This is the FREE deterministic assembly stage (Playwright beat render plus ffmpeg concat plus window-masked caption burn plus VO-and-music mix plus final composite) — the VO, the music bed, and the stock B-roll come from create-vo-elevenlabs, create-music-elevenlabs, and media-proxy. Use for the vo-anchored-motion-listicle format.

Quality

72%

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-vo-anchored-motion-listicle/SKILL.md

Quality

Content

61%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 concrete, well-referenced contract with specific rendering parameters and good bundle navigation. Its weak spots are repetition across sections, the absence of a numbered workflow with an explicit validation loop, and inlined detail that an overview would delegate to references.

Suggestions

Collapse the repeated 'FREE, deterministic / no lipsync / fps 25 / captions only on B-roll' points so each appears once; keep the Contract as the single source.

Add a short numbered run sequence with an explicit validation checkpoint (e.g. verify every beat is fps 25 and the ASS carries a Name field before compositing).

Move the full per-step field→script map detail fully into PIPELINE.md and let the body link out rather than restating the pipeline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient technical contract detail, but 'FREE, deterministic', 'no lipsync', 'fps 25', and 'captions only on B-roll' are each restated across the intro, Run, and Contract sections and could be tightened.	3 / 5
Actionability	Gives concrete parameters (fps 25, loudnorm I=-14, h264 crf18, aac 192k, music ~0.18 vol, 2-word chunks, >0.4s gap) and a fallback 'overlay=…:enable="between(t,st,en)"' filter, but no complete copy-paste ffmpeg command.	4 / 5
Workflow Clarity	The Contract is a bulleted principle list rather than a numbered sequence, and this batch render workflow has no explicit validate→fix→retry loop in the body, capping clarity at 3 per the rubric's batch-operation note.	3 / 5
Progressive Disclosure	Clean one-level-deep references to real bundle files ('scripts/PIPELINE.md', 'scripts/README.md', 'scripts/config.example.json'), though the body inlines substantial contract detail that reads as more than a pure overview.	4 / 5
	Total	14 / 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.

A dense, specific description that names concrete assembly actions and an explicit use-when trigger, with very low conflict risk. It is let down only by heavy technical jargon and a narrow single-format trigger clause.

Suggestions

Add a few natural trigger phrases users would say (e.g. 'short-form listicle video', 'vertical 9:16 listicle ad') alongside the format name.

Trim the parenthetical jargon ('glass-pill callouts', 'ASS Format header carrying a Name field') out of the description and keep it for the body.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'rendered frame-by-frame via Playwright', 'anchored to the VO's word-level timestamps', 'ffmpeg concat plus window-masked caption burn plus VO-and-music mix plus final composite' — covering the assembly comprehensively.	5 / 5
Completeness	Clear 'what' (assemble a listicle video ad from a config) plus an explicit 'Use for the vo-anchored-motion-listicle format' trigger, but the 'when' is a single format reference rather than concrete user scenarios.	4 / 5
Trigger Term Quality	Good natural coverage ('LISTICLE video ad', 'voiceover', 'B-roll', 'captions', 'motion-graphic') but dense jargon ('hyperframe beats', 'glass-pill callouts', 'ASS Format header') and a single narrow trigger ('Use for the vo-anchored-motion-listicle format') leave some synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Highly specific niche — vo-anchored motion-graphic listicle assembly — with distinct triggers and minimal overlap risk against other skills.	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-vo-anchored-motion-listicle/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.