SKILLEMALL.ai
RU Sign in

AC rdk-x5-toolchain-quantization

地瓜 RDK X5 OpenExplorer 工具链（OE v1.2.8）PTQ 量化的**工具链层 Skill**（不含 YOLO 训练 / ROS2 部署，端到端用 RDK YOLO Toolkit）。当需要把任意 ONNX 转成 RDK X5 的 .bin / .hbm 时调用，覆盖：环境（Docker 镜像 / OE SDK / 离线包）、`hb_mapper checker` 算子预检、校准数据（nv12 / featuremap / .rgbchw / .yuv）、yaml 配置（`calibration_type` / `node_info` / `optimization`）、`hb_mapper makertbin` 编译、精度（cosine / `hb_verifier` / `hb_mapper infer`）与性能（`hb_perf` / `hrt_model_exec`）评估、精度调优（敏感算子 / int16 / featuremap 兜底）。模型无关，适用于 YOLO/ResNet/ViT/Transformer 等任意 ONNX。当用户提到 hb_mapper、hb_perf、hrt_model_exec、PTQ、量化 ONNX、转 .bin、转 .hbm、校准数据、calibration_type、featuremap、RDK X5 工具链、OE 1.2.8、精度掉点、cosine 不达标、BPU 利用率 等关键词，或在 RDK X5 部署场景下处理 ONNX → 板端可执行产物时使用。

ClawHub Agent Skills author: Chao.Ma v1.0.0 MIT-0 9 files body ≈ 1 515 tokens Open the sourceclawhub.ai↗ analyzed 29 h ago

地瓜 RDK X5 OpenExplorer 工具链（OE v1.2.8）PTQ 量化的工具链层 Skill（不含 YOLO 训练 / ROS2 部署，端到端用 RDK YOLO Toolkit）。当需要把任意 ONNX 转成 RDK X5 的 .bin / .hbm 时调用，覆盖：环境（Docker 镜像 /…

As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationDockerInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
93/100
safety, quality, tests
Safety 60%
96
Quality 40%
88
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

    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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Secrets in code secret-high-entropy-token references/performance.md:199
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "Dequ…ize": { "avg_time": 0.029, ... },
      quoted
    • low Secrets in code secret-high-entropy-token references/performance.md:200
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "MOBI…ert": { "avg_time": 0.011, ... },
      quoted
    • low Secrets in code secret-high-entropy-token references/setup.md:49
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      docker login -u 'ccr$deliver-ronly' registry.d-robotics.cc -p 'VLae…Vlr'
      quoted
    • low Secrets in code secret-high-entropy-token references/troubleshooting.md:304
      High-entropy token-like string (may be an id, hash or a credential)
      Actual: (N11o…xxx), expected: (N11o…xxx)

    Files scanned: 9. 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
    • 20When it triggers. No condition that starts the skill
    • 100Tools and files. No external tools needed
    • 100Steps. 20 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1515 tokens
    • 100Running it twice. No mutating operations
    • 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)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 671: enough signal without eating the budget
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 20 items
    • +4Has examples (7 code blocks)
    • +4Reference files are cited in the instructions (7 of 7)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

    External checks

    ClawHub: suspicious
    The skill is coherent for RDK X5 model quantization, but it publishes a reusable private registry credential and asks users to run unverified external toolchain artifacts.
    LLM: suspicious (high) · 7 Sept 2026