AC rdk-x5-toolchain-quantization
Toolchain-level skill for D-Robotics / Horizon Robotics RDK X5 OpenExplorer v1.2.8 post-training quantization (PTQ). Use when converting arbitrary ONNX models to RDK X5 deployable .bin / .hbm artifacts with hb_mapper, hb_perf, and hrt_model_exec. Covers OE Docker setup, operator compatibility checks, calibration data preparation (nv12, RGBCHW, YUV, featuremap fallback), YAML configuration (calibration_type, node_info, optimization), hb_mapper makertbin compilation, accuracy verification (cosine, hb_verifier, hb_mapper infer), performance profiling, and accuracy tuning for cosine drops or BPU utilization issues. Model-agnostic for YOLO, ResNet, ViT, Transformer, and other ONNX models. Trigger on keywords such as RDK X5, OpenExplorer, OE 1.2.8, PTQ, hb_mapper, hb_perf, hrt_model_exec, ONNX quantization, convert to .bin, convert to .hbm, calibration data, calibration_type, featuremap, cosine mismatch, accuracy drop, and BPU utilization.
Toolchain-level skill for D-Robotics / Horizon Robotics RDK X5 OpenExplorer v1.2.8 post-training quantization (PTQ). Use when converting arbitrary ONNX models…
As a process C 60/100 · Has gaps — 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: 10. 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 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 7 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 23 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1512 tokens
- 100Progress reporting. Reports progress
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 947: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.