AB auto-free-banana
Generates images in Google Flow (labs.google/fx) through browser UI automation. Supports Nano Banana 2 and Nano Banana Pro with landscape/portrait aspect ratios. Use when the user requests Flow-based image generation.
As a process B 70/100 · Nearly there — weak spots: result and completion
How to improve
For the model run — optional
- 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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 70/100
- 0Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 57 steps, 1 vague phrases
- 100Failures and branches. 9 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2443 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 12 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 217: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 57 items
- +4Has examples (10 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.
External checks
ClawHub: suspicious
This skill is for Google Flow image generation, but it also reads browser authentication state and saves reusable Google session data locally, so it should be reviewed carefully before use.
LLM: suspicious (high) · VirusTotal: · 29 May 2026