BD gemma4-dev
Use when designing, configuring, or implementing applications targeting the Google Gemma 4 model family. Covers model architecture selection (26B/12B/E2B/E4B), native Thinking Mode formatting, function calling schemas, multimodal audio/vision pipelines, and deployment reference patterns.
Covers model architecture selection (26B/12B/E2B/E4B), native Thinking Mode formatting, function calling schemas, multimodal audio/vision pipelines, and…
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Obfuscation
obf-base64-blobreferences/multimodal.md:37Long base64-looking blob<image mime_type="image/png">iVBO…mNk+M9QD…ggg==</image>
Files scanned: 9. 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 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. 6 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 29 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1702 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 288: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.