image-ad-clone

Use when the user wants to reverse-engineer an existing image ad into a reusable prompt template. Validates via Arcads — picks gpt-image-2 or Nano Banana at Phase 1. Triggers on "clone this ad as a template", "reverse engineer this ad", "turn this ad into a prompt", "extract a template", "make this ad reusable", "add to my prompt library", "study this ad and make a template". Input is an EXISTING ad image; does NOT trigger for fresh generation (use chatgpt-image-ad or nano-banana-image-ad).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

A well-structured, highly actionable skill body with a clear multi-phase workflow, explicit validation checkpoints, and clean progressive disclosure into shared references. Its only weakness is moderate verbosity from inline historical/migration notes and a partially redundant See-also section.

Suggestions

Move the "replaces the older Uni1-locked image-ad-clone" note and the KIE-repo aspect-ratio comparison into a dedicated "Migration / deprecated" section so the main workflow stays lean and time-sensitive context is contained.

Trim or collapse the "See also" section, since it re-lists the shared guide and sibling-skill links already cited in "Read order" and "Dependencies".

Dimension	Reasoning	Score
Conciseness	Mostly efficient Arcads-specific detail, but it carries inline historical padding ("replaces the older Uni1-locked image-ad-clone", the KIE-repo ratio comparison) and a "See also" section that repeats paths already linked in "Read order" — leaner than ideal but not padded with concepts Claude already knows.	2 / 3
Actionability	Provides concrete, executable guidance throughout — generator script paths, flags ("--image-ref <reference_path>", "--model nano-banana-pro"), exact aspect-ratio mappings, an iteration directory layout, and copy-ready Model-notes templates — matching the fully-executable anchor.	3 / 3
Workflow Clarity	The 10-phase workflow is clearly sequenced with explicit validation feedback loops (Phase 5 compare-and-iterate capped at 4, Phase 7 test-against-a-different-brand with refine-if-broken, Phase 8 cross-model validation) and a Phase 1 fail-with-fix-it guard, matching the clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	A clear "Read order" section signals one-level-deep shared references (guide.md, template-format.md, prompt-library.md) with descriptions, and the generic 10-phase detail is delegated to the shared guide rather than inlined, matching the clear-overview-with-well-signaled-references anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 strong, third-person description that concisely states what the skill does, when to use it, and when not to. Concrete actions, natural trigger phrases, and an explicit negative trigger give it high specificity, completeness, and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "reverse-engineer an existing image ad into a reusable prompt template", "Validates via Arcads", "picks gpt-image-2 or Nano Banana at Phase 1" — matching the multiple-specific-actions anchor rather than the single-domain level 2.	3 / 3
Completeness	Explicitly answers both what (reverse-engineer an ad into a reusable template, validate via Arcads) and when ("Use when…", "Triggers on…", plus a negative trigger), matching the clear-both anchor.	3 / 3
Trigger Term Quality	Lists seven natural quoted phrases users would actually say ("clone this ad as a template", "reverse engineer this ad", "turn this ad into a prompt", etc.), giving good coverage rather than just a few relevant keywords.	3 / 3
Distinctiveness Conflict Risk	Clear niche with an explicit negative trigger ("does NOT trigger for fresh generation (use chatgpt-image-ad or nano-banana-image-ad)") that steers away from sibling skills, making wrong-skill conflicts unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 9 suspicious	Warning

	Total	15 / 16 Passed

Repository: krusemediallc/arcads-claude-code
Path: skills/image-ad-clone/SKILL.md
Commit: 0bfafb2

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.