render-cgi-sizzle

Assemble a 3D-CGI app sizzle — nano-banana CGI plates (blank-glow floating phone + smoky-black studio + amaranth rim-light + placeholder burst shapes) plus PIL compositing of the REAL App Store screenshots onto the bezel + burst-out overlays, driven by Kling 3.0 i2v steady-float per beat with a per-beat Ken-Burns FFmpeg push-in fallback when Kling garbles the UI, then VO/music mix (sidechain duck, loudnorm) + 1.15x speed + anti-AI grain finalize. The on-screen UI, instructor faces, and wordmark are ALWAYS real assets composited via PIL — never AI-rendered. The paid steps (plates, i2v clips, VO, music) are separate capabilities; this ships the config + PIPELINE + FREE assembly and the recipe orchestrates the spend. Use for the cgi-app-sizzle video format.

Quality

77%

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-cgi-sizzle/SKILL.md

Quality

Content

70%

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 a clear sequenced workflow, explicit error-recovery, and clean one-level-deep references to real bundle files, but it loses points on conciseness (repeated guards) and actionability (executable commands deferred to referenced files rather than inline).

Suggestions

State the 'never AI-rendered' guard once in the Contract section and reference it elsewhere rather than repeating the full mantra in the intro and bullets.

Add a short inline executable snippet for at least one FREE step (e.g. the zoompan Ken-Burns push-in or the loudnorm/sidechain mix command) so the body is copy-paste ready, not just a pointer.

Collapse the restated plate→composite→Kling flow in the bullets so it is not duplicated in the Run section.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence with no basic-concept explanations, but the 'ALWAYS real assets — never AI-rendered' guard is repeated across the intro, bullets, and Contract and the plate→composite→Kling flow is restated between the bullet list and the Run section, so it is 'mostly efficient but could be tightened' rather than every token earning its place.	2 / 3
Actionability	Concrete targets and flags are named ('zoompan', 'loudnorm -14 LUFS', '1080x1920', '~22.6s', '1.15x'), but all executable code/commands are deferred to scripts/README.md and scripts/PIPELINE.md rather than given inline, leaving it at 'some concrete guidance but incomplete' instead of copy-paste ready.	2 / 3
Workflow Clarity	The Run section gives an explicit sequenced flow 'VO first → plates → PIL composites → burst-climax overlays → Kling i2v (Ken-Burns fallback per garbled beat) → end card → captions → mix → 1.15x + grain' with an explicit per-beat error-recovery rule and a timeline-locking verification principle, matching the 'clear sequence with explicit validation/feedback' anchor.	3 / 3
Progressive Disclosure	The body is an overview that clearly signals one-level-deep references to real bundle files ('See scripts/README.md for the full FREE-assembly detail and scripts/PIPELINE.md for the config-field → source-step map'), all of which exist, with content appropriately split and easy to navigate.	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.

The description is highly specific and complete with an explicit use-trigger and a clear, non-conflicting niche, but its trigger-term quality is diluted by heavy internal jargon and a lack of common natural-language variations a user would actually say.

Suggestions

Lead with a plain-language trigger phrase (e.g. 'Use when making a CGI app promo/sizzle video') before the technical detail so users can naturally invoke it.

Trim internal codewords like 'nano-banana CGI plates' and 'amaranth rim-light' from the description, or restate them as plain terms, to improve natural trigger matching.

Add common variations such as 'app demo video', 'app store promo', or 'product film' alongside 'cgi-app-sizzle'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Assemble a 3D-CGI app sizzle', 'PIL compositing of the REAL App Store screenshots', 'Ken-Burns FFmpeg push-in fallback', 'VO/music mix (sidechain duck, loudnorm) + 1.15x speed + anti-AI grain finalize' — matching the 'lists multiple specific concrete actions' anchor rather than the partial score-2 anchor.	3 / 3
Completeness	Answers both what (the full assembly pipeline) and when via an explicit trigger clause ('Use for the cgi-app-sizzle video format'), satisfying the score-3 anchor; it is not score 2 because the 'when' is explicit rather than merely implied.	3 / 3
Trigger Term Quality	Has a relevant natural trigger ('Use for the cgi-app-sizzle video format', '3D-CGI app sizzle') but is buried under internal jargon ('nano-banana CGI plates', 'amaranth rim-light', 'sidechain duck', 'loudnorm') and lacks common user variations like 'app promo video' or 'product film', so it stops at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	Targets a narrow, named niche ('cgi-app-sizzle video format') with distinct triggers, making conflict with other skills unlikely; it is clearly above the score-2 'could still overlap' anchor.	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-cgi-sizzle/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.