CtrlK
BlogDocsLog inGet started
Tessl Logo

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).

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 well-structured orchestration skill: crisp read order, one-level-deep references, a fully sequenced 10-phase workflow with explicit validation and feedback loops, and concrete repo-specific details throughout. The two soft spots are mild editorial padding (KIE comparison, uni-1 nostalgia notes) and the absence of a fully spelled-out generator command for Phase 4.

Suggestions

Show one complete Phase 4 invocation per backend (e.g. `python skills/chatgpt-image-ad/scripts/generate_image.py --image-ref ref.png --aspect-ratio 1:1 ...`) so the core generation step is copy-paste ready instead of delegated to the sibling skill's docs.

Trim the KIE-repo comparison parenthetical and the uni-1-era narrative paragraph — both are historical context, not instructions; if kept at all, fold them into a short 'Deprecated / alternatives' note.

The two routing bullet lists (typography-heavy vs photoreal) overlap with Phase 1's auto-detect rule; consider compressing them into a single decision table keyed on the reference's typography-vs-photo balance.

DimensionReasoningScore

Conciseness

The body is dense with repo-specific facts Claude cannot infer (generator paths, aspect-ratio endpoint constraints, model-routing buckets, iteration layout) and explains no general concepts. Minor trim opportunities remain: the KIE-repo comparison parenthetical ("(The KIE per-API repo's...)") and the editorializing "The diff between a uni-1-era library and this one is this `Model notes` block. Don't skip it..." add tokens beyond instruction. This fits anchor 4 (efficient with minor instances that could be trimmed), not anchor 5 where every token earns its place.

4 / 5

Actionability

Guidance is largely executable: exact script paths, env vars (`ARCADS_BASIC_AUTH`, `ARCADS_API_KEY`), the `--image-ref <reference_path>` flag, a concrete aspect-ratio mapping table, a copy-paste iteration directory layout, and fill-in markdown skeletons for `Model notes`. It stops short of anchor 5 because the actual generator invocation line (e.g. a full `python generate_image.py ...` command with the ratio flag) is never shown — Phase 4 says "using the matching generator script" and defers to the sibling skill — leaving a minor gap for the core execution step.

4 / 5

Workflow Clarity

All 10 phases are explicitly sequenced with validation checkpoints and feedback loops: Phase 1 preflight ("Reference image file resolves; `.env` has Arcads creds; both generators detected" with a fail-and-fix-it path), Phase 5 iteration cap, Phase 7 re-testing the generalized template against a different brand with refinement if structure breaks, and Phase 8 cross-model validation with documented deltas. This matches anchor 5's clear sequence, explicit validation, and error-recovery loops; anchor 4 would leave checkpoints implicit.

5 / 5

Progressive Disclosure

The body opens with an explicit numbered "Read order" placing this file as the Arcads-specific layer over the shared 10-phase guide, template format, and prompt library, and every reference is a well-signaled one-level-deep markdown link (shared guide, template-format.md, prompt-library.md, three sibling skills). Detail is appropriately split out — the body holds only routing rules, ratios, and layout, matching anchor 5's clear overview with well-signaled references; anchor 4 would have organization gaps or buried references.

5 / 5

Total

18

/

20

Passed

Description

95%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 strong description: explicit Use-when clause, six natural trigger phrases, concrete model-level specifics, and an explicit exclusion boundary against sibling skills. The only gap is that the full capability surface (document/save-to-library steps) is implied via triggers rather than stated.

DimensionReasoningScore

Specificity

The description names concrete actions — "reverse-engineer an existing image ad into a reusable prompt template" and "Validates via Arcads — picks gpt-image-2 or Nano Banana at Phase 1" — with specific model names rather than generic language. It falls just short of anchor 5 because coverage is narrow: the downstream steps (documenting, saving to the prompt library) are only hinted at via the trigger "add to my prompt library", not stated as capabilities. It is clearly above anchor 3, which expects only 1-2 actions without this level of backend detail.

4 / 5

Completeness

It explicitly answers both questions: what ("reverse-engineer an existing image ad into a reusable prompt template", validated via Arcads with a model choice) and when ("Use when the user wants to..." plus "Triggers on" concrete phrases, plus an explicit negative boundary: "does NOT trigger for fresh generation"). This matches the anchor-5 pattern of what + when with concrete trigger phrases; anchor 4 would require the when to be less explicit.

5 / 5

Trigger Term Quality

Six natural quoted phrases users would actually say — "clone this ad as a template", "reverse engineer this ad", "turn this ad into a prompt", "extract a template", "make this ad reusable", "study this ad and make a template" — give comprehensive synonym-level coverage. This matches the anchor-5 example's breadth (multiple phrasings of the same intent); anchor 4 would leave common variations missing, which is not the case here.

5 / 5

Distinctiveness Conflict Risk

The niche is clear (cloning an EXISTING ad) and it actively disambiguates from the two sibling generators: "does NOT trigger for fresh generation (use chatgpt-image-ad or nano-banana-image-ad)". Minimal conflict risk; this is stronger than anchor 4, which would still leave minor overlap with closely related skills.

5 / 5

Total

19

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 9 suspicious

Warning

Total

15

/

16

Passed

Repository
krusemediallc/arcads-claude-code
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.