BC fooocus-image-gen
Local AI image generation using Fooocus (Stable Diffusion XL). Use when users want to generate images locally without relying on cloud APIs. Supports text-to-image, image variations, upscaling, inpainting, outpainting, face swap, and style transfer. Triggers on phrases like "generate image with Fooocus", "local image generation", "SDXL generation", "inpaint this image", "upscale image locally", or any image generation request when Fooocus is mentioned or preferred over cloud services.
As a process C 57/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, execution cost
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 · 0
✓ No critical or high findings
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 15857 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 40Execution cost. Instruction body is 15857 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 490 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 21 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
- +4Description does not say when NOT to use the skill (false activations)
- -2localhost URLs: will not work for another user
- -2179 emoji in the instructions: noise for the model
- -43 reference files, but SKILL.md never points to them: the model will not open them
- -35 of 7 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 489: enough signal without eating the budget
- +4Structure: 193 headings
- +3Step-by-step instructions: 490 items
- +3Output format is stated explicitly
- +4Has examples (133 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.