CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

muapi-product-video-ad-maker

Create a high-end cinematic product video advertisement starting from a simple product photo.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/muapi-product-video-ad-maker/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, well-structured recipe: concrete model IDs, prompts, and commands for both phases, with an explicit user-approval checkpoint. Its main gaps are the missing full CLI invocation syntax for the muapi commands and the absence of any error-recovery guidance for failed generations.

DimensionReasoningScore

Conciseness

The body is lean: an inputs table, two phases with exact prompts and models, trigger keywords, and short operational notes. There is no over-explanation of concepts Claude already knows and no padding; every section earns its place. This matches anchor 5 rather than anchor 4, which reserves room for trimmable over-explanation.

5 / 5

Actionability

Concrete commands are given ("muapi image edit (model=flux-2-pro-edit)", "muapi video from-image (model=wan2.5-image-to-video-fast)") with full prompts, aspect ratios, placeholder substitution, auth setup, and a curl fallback. However, the exact CLI flag syntax for passing the reference image and prompt is not written out as a full copy-paste command line, leaving minor gaps. This is anchor 4 (mostly executable, minor gaps) rather than anchor 5 (fully copy-paste ready).

4 / 5

Workflow Clarity

The sequence is clear — check for the missing product image and ask the user, render, present for approval, generate video, present final — with an explicit approval checkpoint between phases. There is no error-recovery or feedback loop (e.g., what to do if generation fails or output is unsatisfactory), which keeps it at anchor 4 rather than anchor 5.

4 / 5

Progressive Disclosure

The skill is a short, single-purpose recipe with no bundle files; all content is appropriately inline and organized under clear sections (Inputs, Steps, Trigger Keywords, Notes). Per the simple-skill guidance, well-organized sections with no nested references score 5.

5 / 5

Total

18

/

20

Passed

Description

61%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 states a clear, concrete capability with natural trigger phrasing, but it lacks a "Use when..." clause, which both caps completeness and leaves the trigger guidance implicit. Adding an explicit when-to-use sentence with a few more synonyms (e.g., "commercial", "promo video") would lift completeness and trigger term quality to anchor 5.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user wants to turn a product photo into a commercial, promo, or cinematic product video advertisement."

Fold in one or two natural synonyms users would say ("product commercial", "ad video", "promo video") to broaden keyword coverage beyond "product video advertisement".

Optionally enumerate the two concrete sub-actions (re-render the product in a premium setting, then animate it) to raise specificity from one action to a comprehensive list.

DimensionReasoningScore

Specificity

"Create a high-end cinematic product video advertisement starting from a simple product photo" names the domain and a concrete action (turn a product photo into a video ad), but enumerates only one action rather than several specific ones. It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) better than anchor 4, which expects a list of several specific actions.

3 / 5

Completeness

"Create a high-end cinematic product video advertisement starting from a simple product photo" answers "what" clearly, but contains no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The what is concrete and unambiguous, placing it at the top of anchor 3 rather than below it.

4 / 5

Trigger Term Quality

"product video advertisement", "cinematic", and "product photo" are natural phrases a user would say, giving good keyword coverage. A few common variations (e.g., "commercial", "ad video", "promo video") are missing, so it sits between anchors 3 and 4, noticeably above the midpoint.

4 / 5

Distinctiveness Conflict Risk

The niche is specific — cinematic product video ads generated from a product photo — and unlikely to trigger for unrelated skills, though it could overlap slightly with generic image-editing or video-generation skills. This matches anchor 4 (mostly distinct, minor overlap risk) rather than anchor 5, since the description alone does not fully separate it from general video-creation skills.

4 / 5

Total

15

/

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.

Validation — 15 / 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

Path

.opencode/skills/muapi-product-video-ad-maker/SKILL.md

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.