AB vlm-image-helper
Visual inspection helper for VLM and OCR workflows. Use when agent needs to help a vision model see an image more clearly before re-analysis: rotate misaligned or sideways text, crop to a relevant region, zoom small details, enhance readability, or convert an image for re-input. Trigger especially when the model cannot confidently read text, cannot tell similar characters apart such as O/0 or I/l/1, says the image is unclear, needs to inspect only one area of the image, or would benefit from a second pass on a clearer view. Do not use as a general-purpose image editor.
As a process B 71/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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: 8. 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 71/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 546 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 575: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.