BD 日常物体检测
输入一张图像，对其中的人/宠物/车/火焰/纸箱进行检测，输出图片中所有目标的检测框、置信度和标签。
输入一张图像，对其中的人/宠物/车/火焰/纸箱进行检测，输出图片中所有目标的检测框、置信度和标签。
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 49/100
- 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
- 40Consistency. Frontmatter name (日常物体检测) differs from the folder (daily-object-detection)
- 100Tools and files. No external tools needed
- 100Steps. 14 steps
- 100Execution cost. Instruction body is 542 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 49: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 13 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (2 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.
External checks
ClawHub: suspicious
The skill likely performs object detection, but it asks for and stores an API key, sends image data to an external service, and contains mismatched Gaokao configuration artifacts that warrant review.
LLM: suspicious (high) · VirusTotal: · 9 Jul 2026