CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

56

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/ads/capabilities/render-cgi-sizzle/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 well-structured with a clear sequenced pipeline and real, clearly-signaled references, but it repeats key guardrails, lacks inline executable commands, and has no explicit validation checkpoint for its batch operation.

Suggestions

Add an explicit validation/retry checkpoint in the Run sequence (e.g. verify each Kling clip doesn't garble UI before proceeding, with the Ken-Burns fallback as the documented retry path) to lift workflow clarity above the batch cap.

Consolidate the repeated 'real UI, never AI' and 'paid steps are separate capabilities' statements into one canonical location to reduce padding.

Include at least one inline executable snippet (e.g. the FFmpeg zoompan Ken-Burns command or the loudnorm mix command) so the body is actionable without forcing a round-trip to the referenced files.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes domain competence, but the 'REAL UI, always PIL — never AI' guard and the 'paid steps are separate capabilities' note are each repeated across the intro, body, and Contract sections and could be consolidated.

3 / 5

Actionability

Gives a concrete ordered sequence and names specific files (config.example.json → config.json, PIPELINE.md, README.md), but ships no inline executable commands or code — all executable detail is delegated to the referenced files.

3 / 5

Workflow Clarity

The pipeline is clearly sequenced (VO → plates → composites → overlays → Kling → end card → captions → mix → finalize) with a per-beat fallback rule, but there is no explicit validate→fix→retry checkpoint; the batch-operation cap at 3 applies.

3 / 5

Progressive Disclosure

Clear overview with well-signaled, verified one-level-deep references (scripts/README.md, scripts/PIPELINE.md, scripts/config.example.json) and good section structure, though some inlined stage detail slightly duplicates what PIPELINE.md covers.

4 / 5

Total

13

/

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 highly specific and distinctive, listing concrete actions and an explicit trigger, but its trigger-term coverage is narrow and jargon-heavy rather than spanning the natural phrases a user would say.

Suggestions

Add natural-language trigger variants to the 'Use for...' clause (e.g. 'app sizzle video', '3D product demo film', 'Apple-keynote style app ad') so users phrase it more ways than just the format name.

Slightly tighten the dense first sentence — some inline parenthetical detail (e.g. the full plate description) could move to the body to improve readability without losing specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'nano-banana CGI plates', 'PIL compositing of the REAL App Store screenshots onto the bezel', 'Kling 3.0 i2v steady-float', 'Ken-Burns FFmpeg push-in fallback', 'VO/music mix (sidechain duck, loudnorm) + 1.15x speed + anti-AI grain' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Has a clear 'what' (the full assembly pipeline) and an explicit 'Use for...' trigger clause, but the 'when' is a single narrow format reference rather than concrete varied trigger phrases.

4 / 5

Trigger Term Quality

The only trigger phrase is 'Use for the cgi-app-sizzle video format'; it names the format but is narrow domain jargon missing common natural variations or synonyms a user might actually say.

3 / 5

Distinctiveness Conflict Risk

A clearly distinct niche (cgi-app-sizzle format with named tools Kling 3.0, nano-banana, PIL) with minimal overlap risk against other skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
gooseworks-ai/goose-skills
Reviewed

Table of Contents

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.