Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/7/2026.claude/skills/rdk-x5-toolchain-quantizationRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Real Skill packageSource verifiedClawHub registry
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_mod…
Identity and source
Publisher attributionChao.Maregistry owner unverified by skillvetai
Functional categoryDevOps, Cloud & Observabilityautomatically inferred · 56% rule confidence
Package forminstruction bundle9 recorded files
Canonical sourceClawHub registryclawhub:maxma615:rdk-x5-toolchain-quantization
Platform declarations
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
OpenClawnative officialProvenance: registry distribution
Independent structural checks
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/7/2026.agents/skills/rdk-x5-toolchain-quantizationRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/7/2026skills/rdk-x5-toolchain-quantizationRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Installation and inspection
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @maxma615/rdk-x5-toolchain-quantizationclawhub inspect @maxma615/rdk-x5-toolchain-quantization --version 1.0.0Security evidence
SkillVetAI static result: high signalhighDynamic code or shell execution is presentreferences/setup.md:168 · confidence 78%
This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
- Status
- completed
- Coverage
- full text content
- Files
- 9 / 9 inspected as text
- Checked
- 9/7/2026, 5:49:16 PM
- Scanner
- 0.1.3
- Policy
- 1.0.3
1 automated finding
eval(2 inferred permission indicators
- network access — automatically inferred
- filesystem write — automatically inferred
4 dependency and API indicators
- api: clawhub.ai
- api: d-robotics-aitoolchain.oss-cn-beijing.aliyuncs.com
- api: developer.horizon.cc
- api: netron.app
External clawhub result: suspicious
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
- Evidence checked
- 9/7/2026, 9:08:34 AM
- Release binding
- Matches this record
- skillspector: suspicious
- llm: suspicious
Recorded files
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
Package content hash
sha256:947844ad4497677ea19ef26213e38867bac257843e776a764c994efcd1c1a288Show up to 9 recorded paths
references/accuracy-tuning.mdreferences/accuracy.mdreferences/calibration.mdreferences/performance.mdreferences/setup.mdreferences/troubleshooting.mdreferences/yaml-reference.mdskill-card.mdSKILL.md
Source changelog
Initial release of the RDK X5 PTQ quantization guide and seven Markdown references.