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-hmct-cosine-similarity-tuninggit 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-hmct-cosine-similarity-tuning)<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-hmct-cosine-similarity-tuning"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-hmct-cosine-similarity-tuning/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-hmct-cosine-similarity-tuning"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-hmct-cosine-similarity-tuning.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 | $0.00126 | $0.03980 |
| Opus 5 | $0.00063 | $0.01990 |
| Sonnet 5 | $0.00025 | $0.00796 |
| Haiku 4.5 | $0.00013 | $0.00398 |
Grade A, and why
j6-hmct-cosine-similarity-tuning 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 12d 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
J6 HMCT Cosine Similarity 调优（工作流）
适用前提（必须一致）
- 同一 onnx / 同一校准数据 / 同一评测口径：对比不同量化配置时只改变
quant_config，其余输入保持一致。 - 目标：以 HMCT 打印的
The quantized model output中 Cosine Similarity（输出节点级） 为达标指标（默认阈值 ≥0.99）。
脚本文件
本 Skill 提供以下脚本：
| 脚本 | 说明 |
|---|---|
script/hmct_precision_tuning.py |
主调优脚本：自动执行阶段 1-7 完整流程 |
script/get_sensitivity_of_nodes.py |
节点敏感度分析脚本 |
快速开始
完整自动调优（推荐）
python3 script/hmct_precision_tuning.py \
--onnx_path "model.onnx" \
--cali_data_dir "./cali_data" \
--march nash-p
使用用户固定配置
python3 script/hmct_precision_tuning.py \
--onnx_path "model.onnx" \
--cali_data_dir "./cali_data" \
--node_config_path "fixed_config.json"
指定 bad case 数量
python3 script/hmct_precision_tuning.py \
--onnx_path "model.onnx" \
--cali_data_dir "./cali_data" \
--num_sample 5
自定义渐进式阈值
python3 script/hmct_precision_tuning.py \
--onnx_path "model.onnx" \
--cali_data_dir "./cali_data" \
--progressive_thresholds 0.99 0.999 0.9999
指定校准方法（默认不指定）
默认情况下脚本不在 quant_config 中写入 calibration_type，由 HMCT 内部决定校准策略。
若需要显式指定，可使用 --calibration_type：
# 单一方法
python3 script/hmct_precision_tuning.py \
--onnx_path "model.onnx" \
--cali_data_dir "./cali_data" \
--calibration_type max
# 多方法（HMCT 会做 modelwise search）
python3 script/hmct_precision_tuning.py \
--onnx_path "model.onnx" \
--cali_data_dir "./cali_data" \
--calibration_type max kl
可选值参考 HMCT：max、kl、load 等。
配置量化策略开关（默认不指定）
可在调优过程中显式开关三类量化策略，所有阶段都会以相同配置写入 quant_config：
| 参数 | 写入字段 | 含义 |
|---|---|---|
--per_channel |
model_config.activation.per_channel |
激活 per-channel 量化开启与否，可选 false / true，HMCT 默认 false；支持同时传两个值（如 true false）触发 modelwise search |
--asymmetric |
model_config.activation.asymmetric |
激活非对称量化开启与否，可选 false / true，HMCT 默认 false；支持同时传两个值触发 modelwise search |
--bias_correction |
model_config.weight.bias_correction |
是否开启权重 bias correction；当为 true 时写入 bias_correction 子结构 |
--bias_correction_num_sample |
model_config.weight.bias_correction.num_sample |
bias correction 样本数，int >= 1，默认 1；仅当 --bias_correction true 时生效 |
--bias_correction_metric |
model_config.weight.bias_correction.metric |
bias correction 误差度量，可选 cosine-similarity / mse / mae / mre / sqnr / chebyshev，默认 cosine-similarity；仅当 --bias_correction true 时生效 |
What ships with it
2 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.
- 12d ago First seen · 325 lines · 126 tokens per session scan A b154276fd544
j6-hmct-cosine-similarity-tuning is a skill published in the GitHub repository HorizonRobotics/OE-Skills (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 126 tokens to every session and 3,980 once invoked, about $0.0006 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
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.