AB ad-ready
Generate advertising images automatically from a product URL + brand profile. ✅ USE WHEN: - User provides a product URL (e-commerce link) - Want automated product scraping + image generation - Have a brand profile to apply (70+ brands available) - Need funnel-stage targeting (awareness/consideration/conversion) - Want AI to auto-select model, scene, lighting based on brand ❌ DON'T USE WHEN: - User provides local product image file → use morpheus-fashion-design - Don't need a person in the image → use nano-banana-pro - Want manual control over model, scene, packs → use morpheus-fashion-design - Already have hero image, need variations → use multishot-ugc - Need video output → use veed-ugc after image generation INPUT: Product URL + brand name (optional) + funnel stage (optional) OUTPUT: PNG advertising image with product + model
As a process B 68/100 · Nearly there — weak spots: progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 3
✓ No critical or high findings
Medium and low: 3
-
low Secrets in code
secret-high-entropy-tokenscripts/generate.py:55High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"Mast…ion",
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/generate.py:61High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"Mast…ive"
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/generate.py:371High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)parser.add_argument("--prompt-profile", default="Mast…ive",detector
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5148 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5148 tokens
- 85Steps. 51 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 842: 120–800 characters recommended
- -212 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 39 headings
- +3Step-by-step instructions: 51 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.