AD ghost-portrait-generator
Generate haunting ghost portraits and inner demon shadow photos with AI — create spectral ghostly apparitions, paranormal spirit figures, smoky shadow companions standing behind subjects, translucent ethereal ghosts, gothic horror portraits, Halloween spooky imagery, dark supernatural aesthetic art, ghostly phantom visuals, and eerie spectre illustrations perfect for social media viral trends, Halloween content, horror story covers, gothic aesthetic feeds, paranormal enthusiasts, dark fantasy art, and spooky photo transformations inspired by the viral Gemini and ChatGPT ghost portrait trend via the Neta AI image generation API (free trial at neta.art/open).
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "tools"
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 50Steps. 2 steps
- 100Tools and files. Tools declared in frontmatter
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 307 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 665: enough signal without eating the budget
- +4Structure: 6 headings
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.