render-cosmic-mythology-voiceover

Assemble a cosmic-mythology-voiceover reel from a config — one spoken voiceover carries the whole narrative while N curated stills in one chosen look are weighted beat-synced across the delivered VO duration (cut_dur = VO_dur times weight over the weight sum, so emotional beats hold longer), Ken-Burns-zoomed per still (scale 2x, center crop, zoompan, fade-in first and fade-out last), ffmpeg-concatenated, the VO composited under the picture (libx264 crf18 plus aac), the ONE on-screen hook line faded on over the open with a drawtext alpha window, and Whisper/VEED captions burned along the bottom — never in-world text on a still. This is the FREE deterministic assembly stage (weighted sequence plus Ken-Burns plus concat plus VO composite plus hook overlay plus caption burn); the VO and the stills come from create-vo-elevenlabs and create-image-fal. Use for the cosmic-mythology-voiceover 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

Passed

No findings from the security scan

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 strong, highly actionable overview: a single runnable command with full flag documentation, an explicit eight-point contract with parameters and fallbacks, and clean one-level-deep pointers into a real, well-organized bundle. Its main weakness is repetition — the FREE/$0 framing and several rules are restated multiple times across the intro, Run, and Contract sections and could be consolidated.

Suggestions

State the FREE/$0, no-API-key property once (e.g. in the intro) and drop its re-statements in the Run section and the final Contract bullet — the repeated emphasis costs tokens without adding information.

Consolidate the duplicate demo attribution and the no-in-world-text rule, each of which appears in both the intro and later sections.

Add a short explicit validation checkpoint after the run command (e.g. 'check the reported duration/size/bitrate against the expected ~31s master before delivering') to close the workflow-clarity validation gap.

Dimension	Reasoning	Score
Conciseness	The body is dense with real, non-obvious information but repeats the same claims many times: 'FREE, deterministic' assembly appears in the intro, the Run section, and the Contract ('it spends nothing', 'cost $0', 'No paid calls, no keys'), and the demo attribution and the no-in-world-text rule are each stated twice. Anchor 3 ('could be tightened'), not 4 — the repetition goes beyond minor trimming; not 2 — there is no padding that explains concepts Claude already knows.	3 / 5
Actionability	Fully executable: a copy-paste-ready invocation 'python3 scripts/render.py --config config.json --vo working/vo2/vo_atempo.mp3 --stills-dir working/stills --out working/final.mp4 [--words …] [--endcard …]' with every optional flag, plus exact parameters (crf 18, aac 192k, zoom_end ~1.10, fade timings ~0.5s/~0.6s), the weighted formula, and concrete fallbacks when ffmpeg lacks drawtext/libass. Anchor 5 — copy-paste ready with the common cases covered.	5 / 5
Workflow Clarity	The assembly order is explicit and dependency-ordered (weighted cut distribution → Ken-Burns per still → concat → VO composite → hook fade → caption burn → optional end card), and the render script self-reports duration/size/bitrate, but no explicit validate-before-proceed checkpoint exists in the body. Anchor 4 (clear sequence, minor validation gaps); rendering is non-destructive, so the destructive/batch cap does not apply.	4 / 5
Progressive Disclosure	A concise overview body with well-signaled, one-level-deep references that all exist as real files: 'scripts/PIPELINE.md maps every config block to its source step', 'scripts/README.md documents the free assembly' with '§0 for the full arg contract', and 'config.example.json is the worked example — reference only, never the default'. Anchor 5 — every reference is labeled with what it contains and when to consult it, with no nesting or buried references.	5 / 5
	Total	17 / 20 Passed

Description

76%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 exceptionally specific about what the skill does — down to codec settings and the weighted-cut formula — and sits in a distinct niche with explicit stage boundaries. Its weaknesses are trigger quality and a thin 'when': natural user phrasings are sparse among the implementation jargon, and the only trigger clause restates the format name rather than naming situations users would describe.

Suggestions

Add concrete 'when' trigger situations users would actually say, e.g. 'Use when the user asks for a faceless 9:16 myth/storytelling voiceover reel, a Ken-Burns stills video with burned captions, or assembly of an existing VO + stills into a reel.'

Trim implementation jargon ('zoompan', 'libx264 crf18', 'drawtext alpha window', 'atempo') from the description — those details live in the body — in favor of natural synonyms like 'video', 'short-form reel', 'subtitle/caption burn', 'slow zoom'.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete actions with explicit parameters — 'weighted beat-synced across the delivered VO duration (cut_dur = VO_dur times weight over the weight sum)', 'Ken-Burns-zoomed per still (scale 2x, center crop, zoompan)', 'libx264 crf18 plus aac', 'captions burned along the bottom' — giving comprehensive, parameter-level coverage of the capability. Not 4: there are no gaps in the action inventory.	5 / 5
Completeness	Both 'what' and 'when' are present — the 'what' is explicit and detailed, and 'Use for the cosmic-mythology-voiceover format' is explicit trigger guidance, so the missing-trigger cap at 3 does not apply. Not 5: the 'when' is a single, format-name-only phrase rather than concrete trigger situations a user would actually voice.	4 / 5
Trigger Term Quality	Some natural keywords are present ('voiceover', 'reel', 'captions', 'stills', 'Ken-Burns', 'ffmpeg') but they are diluted by heavy implementation jargon ('zoompan', 'libx264 crf18', 'drawtext alpha window', 'atempo'), and common user phrasings like 'faceless video', '9:16', or 'myth storytelling video' are absent; the sole trigger phrase 'Use for the cosmic-mythology-voiceover format' is circular. Not 4: keyword coverage is not yet 'good' with this many natural synonyms missing; not 2: several genuinely natural terms are present.	3 / 5
Distinctiveness Conflict Risk	A single clear niche with a distinctive format name and explicit boundaries ('This is the FREE deterministic assembly stage… the VO and the stills come from create-vo-elevenlabs and create-image-fal') makes triggering for the wrong skill very unlikely. Anchor 5.	5 / 5
	Total	17 / 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-cosmic-mythology-voiceover/SKILL.md
Commit: cc3e518

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.