CtrlK
BlogDocsLog inGet started
Tessl Logo

muapi-ugc-video-factory

Turn a person photo + a product photo + an optional script into a vertical 9:16 UGC-style video ad. Generates a lifestyle hero image (Nano-Banana Pro Edit), then animates it with native audio using Seedance 2.0 VIP image-to-video.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The content is a tight, highly actionable, well-sequenced pipeline with concrete model parameters, ready-to-run commands, an explicit approval checkpoint, and clean self-contained organization.

DimensionReasoningScore

Conciseness

The body is lean and operational — it never explains concepts Claude already knows (e.g., what a UGC ad is) and every section (inputs table, step prompts, notes) earns its place with concrete, non-padded content, matching the top anchor.

3 / 3

Actionability

It gives fully concrete guidance: real model names, exact parameter values (aspect 9:16, duration 10, CFG 0.5, resolution 1K), templated prompts with {{placeholders}}, ready commands like 'muapi upload file <path> --output-json --jq .url' and a copy-paste curl fallback, satisfying the copy-paste-ready anchor.

3 / 3

Workflow Clarity

The three-stage pipeline is explicitly sequenced with outputs feeding forward ({{step1_prompt}} → {{hero_image}}), an explicit approval checkpoint ('show it to the user for approval before kicking off the video step'), and input-missing handling, meeting the clear-sequence-with-checkpoints anchor.

3 / 3

Progressive Disclosure

No bundle files are provided and none are needed; the skill is self-contained and cleanly organized into Inputs, Steps, Notes, Trigger Keywords, and Notes for the Executing Agent, with no nested references, so it earns the top anchor for a single-file, well-structured skill.

3 / 3

Total

12

/

12

Passed

Description

67%

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 specific and distinct, clearly conveying the transformation it performs, but it omits an explicit 'Use when' trigger clause and embeds technical model names that users would not naturally say, which limits trigger-term quality and completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger scenarios (e.g., 'Use when the user wants a vertical UGC video ad, a talking product reel, or a person-plus-product testimonial video').

Move or soften internal model names ('Nano-Banana Pro Edit', 'Seedance 2.0 VIP') in the description in favor of user-facing terms like 'lifestyle hero image' and 'animated video with native audio'.

Include common variations users actually say ('UGC reel', 'TikTok/Reels product ad', 'person + product video') to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Turn a person photo + a product photo + an optional script into a vertical 9:16 UGC-style video ad', 'Generates a lifestyle hero image', 'animates it with native audio' — rather than vague language, matching the top anchor.

3 / 3

Completeness

Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should invoke it, so completeness is capped at 2 per the guidelines.

2 / 3

Trigger Term Quality

Contains some natural terms a user would say ('UGC-style video ad', 'person photo + a product photo', '9:16') but mixes in model-name jargon ('Nano-Banana Pro Edit', 'Seedance 2.0 VIP') and omits common variations like 'reel' or 'TikTok ad' that appear only in the body, not the description.

2 / 3

Distinctiveness Conflict Risk

The combination of person + product photos into a vertical UGC video ad is a clear, narrow niche with distinct triggers unlikely to collide with other skills.

3 / 3

Total

10

/

12

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
SamurAIGPT/Generative-Media-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.