AB camscanner-pdf-remove-watermark
Use CamScanner to remove watermarks from PDF documents while preserving the underlying text, images, and original layout. Powered by a high-precision document enhancement engine that intelligently detects and erases overlaid watermarks, stamps, and translucent logos across every page, leaving the document clean and legible. Use when the user wants to remove watermarks from a PDF, clean up stamped PDFs, or recover a clean copy of a watermarked PDF. Triggers on "remove watermark from PDF", "erase PDF watermark", "delete watermark from pdf", "unwatermark pdf", "clean watermarked PDF", or when the user has a PDF with a watermark that needs to be removed.
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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: 2. 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 67/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 15 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 4 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1891 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 658: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.