AF bria-ai
Generate, edit, create product images with AI. Remove or replace backgrounds, lifestyle shots, transparent PNGs, visual assets, batch generation, illustrations. Controllable image editing with Bria.ai commercially-safe models — fine-grained control over what gets generated, edited, or removed. Edit by text instruction, mask specific regions, add/replace/remove individual objects, control lighting, season, and style. Use for e-commerce product photography, background removal, image upscaling, style transfer, hero images, icons, banners, and pipeline workflows. Triggers on AI image generation, controllable editing, background removal, or visual asset creation.
As a process F 56/100 · Will not run — References files that are not bundled: ../vgl/SKILL.md, ../image-utils/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../vgl/SKILL.md - warning
missing-refreference to a missing file: ../image-utils/SKILL.md - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 56/100
- 0Tools and files. 2 referenced file(s) missing: ../vgl/SKILL.md, ../image-utils/SKILL.md
- 30Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (bria-ai) differs from the folder (bria-ai-skill)
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 13 steps
- 100Execution cost. Instruction body is 2911 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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)
- +2Single-language instructions
- +3Description length 666: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 13 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.