AC zkrj-aigc-detect
When the user asks whether an image, text, audio/video, or document is AI-generated (AIGC/watermark detection), use this skill to run 睿小鉴 detection directly via the backend HTTP API and report the conclusion with confidence and evidence. 全部能力通过后端 HTTP API 调用完成（不依赖 MCP server）。 当用户要求「检测这张图/这段文本/这个文件是不是 AI 生成」、查 AI 生成概率/依据/水印时使用。
When the user asks whether an image, text, audio/video, or document is AI-generated (AIGC/watermark detection), use this skill to run 睿小鉴 detection directly…
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 55/100
- 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
- 30Running it twice. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (zkrj-aigc-detect) differs from the folder (zkrj-aigc-detection)
- 100Tools and files. No external tools needed
- 100Steps. 29 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1757 tokens
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 329: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.