CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

muapi-ad-creative

Generate a high-converting ad creative set — hero image, ad copy variations, and platform-optimized crops for Meta, Google Display, and LinkedIn.

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-ad-creative/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 efficient and highly actionable, with concrete commands, models, exact ad dimensions, and a clear two-phase workflow gated by user confirmation. Its main gap is the absence of any output verification or failure handling after the batch Phase B crops, plus some organizational sloppiness (stray divider, split Notes sections, undefined 'plan' submission mechanic).

Suggestions

Add a verification step after the Phase B batch crops — e.g. check each crop kept the product centered and uncropped, and re-run any failed format — to lift workflow clarity past the batch-operation cap.

Define the 'submit a plan' mechanism once (what tool/format the plan goes to) or replace it with direct executable muapi command lines for both phases, matching the curl fallback's concreteness.

Merge the two Notes sections and remove the stray '---' divider mid-file so the executing-agent guidance lives in one clearly labeled section.

DimensionReasoningScore

Conciseness

The body is lean and table/step-driven with no explanations of concepts Claude already knows. Minor waste keeps it below 5: the line under the heading restates the description verbatim, 'Submit ONE the plan' is garbled phrasing, and two Notes sections are split by a stray '---' divider.

4 / 5

Actionability

Concrete throughout: 'muapi image generate (model=nano-banana-pro)', exact aspect ratios with pixel dimensions, a copy-paste curl fallback, and a fully quoted crop prompt template. Below anchor 5 because the 'submit a/the plan' mechanism is never defined and no complete primary-path command line is shown, only fragments.

4 / 5

Workflow Clarity

The two phases are clearly sequenced with an explicit human checkpoint ('Ask which copy variation to use for Phase B. Wait for user confirmation.' and 'Do NOT auto-confirm Phase B'). However, Phase B is a batch operation — 'All crops run in parallel' across four formats — with no output verification or error-recovery step, which caps workflow clarity at 3 per the rubric's batch-operations rule.

3 / 5

Progressive Disclosure

The skill is self-contained and well-sectioned (Inputs, Steps, Notes, Trigger Keywords) with no external references, and none are needed — verified no bundle files exist so no referenced paths are broken. The awkward mid-file '---' divider and duplicated Notes sections, plus being slightly over the ~50-line simple-skill bar, keep it at 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Description

66%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 clearly and concretely states what the skill produces, with good natural platform keywords and low conflict risk. Its main weaknesses are the missing 'when to use' trigger guidance — which caps completeness — and the 'high-converting' marketing over-claim.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks for ad creatives, ad copy, or platform-sized ad crops for Meta, Google, or LinkedIn campaigns.'

Drop or soften the unverifiable 'high-converting' claim; describe what is generated rather than the outcome it cannot guarantee.

Work natural user phrases like 'advertisement', 'ad banner', or 'social media ad' into the description so the trigger terms live in the description, not only in the body's Trigger Keywords section.

DimensionReasoningScore

Specificity

Names multiple concrete deliverables — 'hero image, ad copy variations, and platform-optimized crops' — plus the target platforms, matching the several-specific-actions anchor. Falls short of 5 because 'high-converting' is an unverifiable over-claim rather than a concrete capability.

4 / 5

Completeness

The 'what' is explicit and concrete, but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is clear and specific rather than vague.

3 / 5

Trigger Term Quality

'ad creative set' and the platform names 'Meta, Google Display, and LinkedIn' are phrases users naturally say, but common variations like 'advertisement', 'ad banner', or 'paid ad' are absent from the description. Clear fit for good-coverage-with-a-few-terms-missing, not the comprehensive-synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

Ad-creative generation with named ad platforms (Meta, Google Display, LinkedIn) carves a mostly distinct niche with clear triggers. Minor overlap risk remains with generic image-generation skills, keeping it below anchor 5.

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-ad-creative/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.