AB camscanner-image-detect-tampering
Use CamScanner to detect whether an image has been PS-edited, manipulated, or tampered with. Powered by a manipulation-detection engine that identifies photo-editing traces, splicing, retouching, and other signs of tampering. Returns a JSON result with `is_tampered` (boolean) and `result_text` (human-readable). Use when the user asks whether a photo is genuine, wants to verify an image's authenticity, or asks "is this PS-ed / photoshopped / edited". Triggers on "检测图片是否PS", "是否被篡改", "图片验真", "PS检测", "detect image tampering", "is this photoshopped", "check if image was edited", or when the user shares an image and asks whether it has been modified.
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. 1 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. 7 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1533 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 653: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.