CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

73%

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-ugc-video-factory/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A strong, actionable body with concrete commands, complete prompt templates, and a well-sequenced pipeline including validation checkpoints. Its weaknesses are repetitive restatement of the pipeline summary and inlining of large prompt templates that a reference file could absorb.

Suggestions

Cut the redundant restatements: drop the bold summary line or the intro paragraph (they repeat the frontmatter description), state the -fast variant tip once, and merge the two 'Notes' sections.

Move the Step 1 and Step 3 prompt templates into a references/ file (or shorten them to their parameterized skeleton) to reduce inline token cost.

Add a brief error-recovery note for failed or poor-quality generations (e.g. regenerate the hero image or re-poll) to close the workflow feedback loop.

DimensionReasoningScore

Conciseness

Mostly efficient with genuinely non-obvious domain notes ('Seedance 2.0 will compress longer scripts and clip words'), but the pipeline summary is restated three times (frontmatter echo, bold intro line, three-stage list), the -fast variant tip appears twice, and there are two separate 'Notes' sections — more than minor trimming would fix.

3 / 5

Actionability

Mostly executable guidance: full copy-pasteable prompt templates in Steps 1 and 3, concrete CLI calls ('muapi predict wait <request_id>', 'muapi upload file <path> --output-json --jq .url'), and a curl fallback. Minor gaps: parameters are bullet descriptions rather than complete command lines, and the curl fallback body is a '{...}' placeholder.

4 / 5

Workflow Clarity

A clear three-step sequence with explicit dataflow ('each step's output feeds the next'), input validation ('If person or product is missing, ask the user... before continuing'), and a user-approval checkpoint before the video step. Not 5 because there is no error-recovery loop for failed generations.

4 / 5

Progressive Disclosure

Well-organized sections with clear headers and no bundle files to coordinate, but at ~127 lines the two large prompt templates (~45 lines) and the curl fallback details are inlined content that would typically live in reference files, keeping it short of a fully split structure.

4 / 5

Total

15

/

20

Passed

Description

67%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.

A highly specific, well-scoped description that names concrete actions, models, and output format. Its main gaps are the absence of any 'when to use' trigger guidance and thin natural-keyword coverage relative to how users actually phrase this need.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to turn photos of a person and a product into a UGC-style video ad, reel, or talking product ad.'

Include natural synonyms users would say — 'reel', 'TikTok-style ad', 'creator ad' — in the description itself rather than only in the body's Trigger Keywords section.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with named models and output format — 'Generates a lifestyle hero image (Nano-Banana Pro Edit)', 'animates it with native audio using Seedance 2.0 VIP image-to-video', 'vertical 9:16 UGC-style video ad' — covering the full pipeline comprehensively.

5 / 5

Completeness

It clearly answers 'what' (a three-stage photo-to-video pipeline with named models) but includes no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

It contains some natural terms ('UGC-style video ad', 'person photo', 'product photo') but misses common variations users would say such as 'reel', 'TikTok ad', 'talking product video', or 'creator-style ad'.

3 / 5

Distinctiveness Conflict Risk

A narrow niche — fusing person and product photos into a 9:16 UGC ad via specific named models (Nano-Banana Pro Edit, Seedance 2.0 VIP) — with distinct triggers and minimal overlap risk against generic video or image skills.

5 / 5

Total

16

/

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-ugc-video-factory/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.