AD rdk-x5-ai-detect
在 RDK X5 的 10TOPS BPU 上运行单个 AI 推理算法：YOLO 目标检测、图像分类、语义分割、人脸识别、手势识别、人体关键点、开放词汇检测（DOSOD/YOLO-World）、双目深度估计、语音识别、端侧轻量 LLM（≤2B 参数量化模型）。Use when the user wants to run a single AI algorithm, deploy pre-built .bin models to BPU, or ask what AI models/LLMs RDK X5 can run (能力咨询). Do NOT use for camera hardware setup (use rdk-x5-camera), multimedia encoding (use rdk-x5-media), running /app demo scripts (use rdk-x5-app), integrated camera+AI+output pipeline (use rdk-x5-tros), model conversion/quantization/export (use Horizon toolchain on PC), large generative models like Stable Diffusion (insufficient VRAM), or custom code that bridges AI results to external services like MQTT.
As a process D 41/100 · Unfinished process — weak spots: steps, result and completion, inputs and preconditions
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 41/100
- 0Steps. Prose only: no discrete steps
- 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
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 578 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
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 674: enough signal without eating the budget
- +4Structure: 13 headings
- +4Has examples (10 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.