render-cosmic-mythology-voiceover

Assemble a cosmic-mythology-voiceover reel from a config — a warm spoken voiceover carries the whole narrative while N curated cosmic stills 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

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ads/capabilities/render-cosmic-mythology-voiceover/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable assembly skill with a clean executable entry point and properly signaled one-level references into the scripts bundle. It loses points on repeated 'FREE/deterministic' framing and on the absence of explicit output-validation checkpoints in the render workflow.

Suggestions

Remove the repeated 'FREE, deterministic assembly' restatements from the Run and Contract sections; state it once and let the Contract focus on the per-step rules.

Add an explicit validation checkpoint after the render (e.g. probe the output with ffprobe to confirm 1080×1920 h264+aac and ~VO duration, and re-run with --verbose on failure) to give the workflow a feedback loop.

Collapse the Contract bullets that re-explain the description (e.g. the weighted-formula line) into a pointer to PIPELINE.md to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is dense with genuinely non-obvious specifics (the weighted formula, atempo clamp ≤1.25, crf18, fade timings, libass→PIL fallback) and avoids explaining concepts Claude already knows, but it repeats the 'FREE, deterministic assembly' framing across the intro, Run section, and Contract, and restates much of the description. Not level 3 because of this redundancy; not level 1 because the bulk of the content earns its tokens.	2 / 3
Actionability	Provides a concrete, copy-paste-ready executable command 'python3 scripts/render.py --config config.json --vo working/vo2/vo_atempo.mp3 --stills-dir working/stills --out working/final.mp4 [--words ...] [--endcard ...]' with real flags, matching the 'fully executable code/commands' anchor. Not level 2 because the command is complete rather than pseudocode.	3 / 3
Workflow Clarity	The assembly sequence is clearly ordered ('distributes the cuts... Ken-Burns-renders each still, concats, composites the VO, fades the hook line, burns the captions, and appends a brand end card → master + poster'), but there are no explicit validation or verification checkpoints for this multi-step ffmpeg pipeline. Not level 3 because validation feedback loops are absent; not level 1 because the sequence is unambiguous.	2 / 3
Progressive Disclosure	The body is a concise overview with well-signaled, one-level-deep references to real bundle files — 'scripts/config.example.json is the worked example', 'scripts/PIPELINE.md maps every config block', 'scripts/README.md documents the free assembly', 'See scripts/README.md §0 for the full arg contract' — all verified to exist. Not level 2 because navigation is clear and references are exactly one level deep with no nesting.	3 / 3
	Total	10 / 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.

A highly specific, third-person description that nails capability detail and explicit trigger guidance for a narrow format. Its main weakness is trigger-term naturalness: it leans on internal jargon and a single restated-format-name trigger rather than phrasings a user would naturally say.

Suggestions

Add natural-language trigger variants a user might actually say (e.g. 'Use when creating a narrated cosmic/mythology short, a faceless voiceover reel over space stills, or a Ken-Burns story reel') alongside the format name.

Move the implementation jargon ('cut_dur = VO_dur times weight over the weight sum', 'zoompan', 'drawtext alpha window') into the body and keep the description on outcomes a user recognizes.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete assembly actions — 'weighted beat-synced', 'Ken-Burns-zoomed per still (scale 2x, center crop, zoompan, fade-in first and fade-out last)', 'ffmpeg-concatenated', 'VO composited under the picture (libx264 crf18 plus aac)', 'captions burned along the bottom' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both what (the full weighted-sequence + Ken-Burns + concat + VO-composite + hook + caption assembly) and when via the explicit trigger clause 'Use for the cosmic-mythology-voiceover format.' It is not level 2 because an explicit 'Use for...' trigger is present, satisfying the when.	3 / 3
Trigger Term Quality	Contains some natural terms ('voiceover reel', 'cosmic stills', 'captions', 'Ken-Burns'), but is heavily loaded with technical jargon ('cut_dur = VO_dur times weight over the weight sum', 'drawtext alpha window', 'zoompan') and the only trigger phrase 'Use for the cosmic-mythology-voiceover format' merely restates the skill name rather than offering common user variations. Not level 3 (no good coverage of natural terms users would say); not level 1 because it does include some relevant keywords.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear narrow niche (the cosmic-mythology-voiceover format) with format-specific triggers, making it unlikely to fire for unrelated skills. Not level 2 because the format name and full pipeline scope distinguish it from generic video/render 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-cosmic-mythology-voiceover/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.