Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HorizonRobotics/OE-Skills --skill j6-plugin-hbdk-generatinggit clone --depth 1 https://github.com/HorizonRobotics/OE-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-plugin-hbdk-generating)<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-plugin-hbdk-generating"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-plugin-hbdk-generating/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-plugin-hbdk-generating"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-plugin-hbdk-generating.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00231 | $0.03429 |
| Opus 5 | $0.00115 | $0.01715 |
| Sonnet 5 | $0.00046 | $0.00686 |
| Haiku 4.5 | $0.00023 | $0.00343 |
Grade A, and why
j6-plugin-hbdk-generating scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
基础结构量化编译全流程代码生成（编排型）
目标
根据用户提供的浮点模型结构，生成一份完整的量化编译全流程代码，从 set_march 到最终编译 HBM。
本 Skill 是编排型 skill，负责按固定顺序调用两个子 skill，不直接实现具体逻辑。
必须遵守的调用顺序
本 Skill 必须按以下顺序调用子 skill，不得跳序：
j6-plugin-quantization（路径：j6-plugin-quantization/SKILL.md）— 量化流程j6-hbdk-export-compile（路径：j6-hbdk-export-compile/SKILL.md）— 导出编译流程
以 export 为界：export 之前属于量化，export 及之后属于导出编译。
为什么必须按这个顺序
1) j6-plugin-quantization（量化）
先完成量化流程，产出校准后或 QAT 训练后的模型。量化流程包括：
set_march— 设置目标平台- 定义模型（含 Quant/DeQuant 边界）— 插入部署边界节点
- 配置量化参数 — 根据 march 选择全局激活类型和 observer
prepare— 插入伪量化节点- 校准（CALIBRATION）— 使用 HistogramObserver 收集统计信息
- QAT 训练（可选）— 使用 MinMaxObserver 重新 prepare 后训练
量化流程的输出取决于用户选择：
- 仅校准：输出
calib_net - 校准 + QAT：输出
qat_net
2) j6-hbdk-export-compile（导出编译）
基于量化流程产出的 QAT 模型，完成导出编译：
export— 切换到 VALIDATION 状态后导出 QAT BCconvert— 转换为量化模型remove_io_op— 删除首尾 Quantize/Dequantize 算子statistics— 检查 CPU 算子compile— 编译生成 HBM
各子 skill 的职责边界
A. j6-plugin-quantization
负责：
- 设置 march
- 在模型中插入 QuantStub/DeQuantStub 部署边界
- 配置量化参数（全局激活类型、observer、Conv/Matmul dtype）
- 执行 prepare、校准
- 询问用户是否进行 QAT 训练（可选）
关键约束：
- 校准用 HistogramObserver，QAT 训练用 MinMaxObserver
- qconfig_setter 只能通过 prepare 传入，QAT 需要重新 prepare 浮点模型
- Quant/DeQuant 每个输入/输出独立 stub，不设置 scale
B. j6-hbdk-export-compile
负责：
- 切换到 VALIDATION 状态并导出 QAT BC（接收
calib_net或qat_net） - 将 QAT BC 转换为量化模型
- 删除首尾量化/反量化节点
- 检查是否存在 CPU 算子
- 编译生成 HBM
关键约束：
- remove_io_op 必须执行，否则 BPU 无法正确运行
- statistics 检查有 hbtl 打印警告，但仍继续执行后续流程
标准执行流程
第一步：确认是否是完整量化编译需求
符合以下描述时，应触发本 Skill：
- "帮我生成量化编译全流程代码"
- "基础结构量化部署"
- "Conv+BN+ReLU+Linear 量化编译"
如果用户只需要量化（不编译），或只需要编译（已有 QAT BC），则直接调用对应子 skill。
第二步：确认 march
在调用子 skill 前，必须先确认用户的 march（目标平台）。如果用户未指定，暂停流程并询问：
向用户提供以下选项：
| march | 平台 | 说明 |
|---|---|---|
"nash-p" |
J6P | 推荐，全局激活支持 float16 |
"nash-h" |
J6H | 全局激活支持 float16 |
"nash-m" |
J6M | 全局激活为 qint8 |
"nash-e" |
J6E | 全局激活为 qint8 |
"nash-b" |
J6B | 全局激活为 qint8 |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 277 lines · 231 tokens per session scan A f333af9bacc9
j6-plugin-hbdk-generating is a skill published in the GitHub repository HorizonRobotics/OE-Skills (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 231 tokens to every session and 3,429 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
minicpm5-deploy-vllm-ascend
Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torchnpu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.
amc-run-video-calibration
Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.