j6-ucp-model-perf-eval

j6-ucp-model-perf-eval is a skill for Claude Code, Codex from HorizonRobotics/OE-Skills. It costs 70 tokens per session (3,556 once invoked), scanned A, original, Apache-2.0.

A repository instruction file for generating software assets such as logos, icons, favicons, illustrations, and hero images. It describes available generation routes and how to handle requests without an image API key.

In plain words
What is it for?
Use it when an agent must create software graphics and choose between the repository's asset tools or a fallback.
Why use it?
It provides consistent guidance for selecting an appropriate asset-generation method, including transparent images and no-key options.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is export LD_LIBRARY_PATH=../aarch64/lib/:\$LD_LIBRARY_PATH && \.

Good fit Use it when an agent must create software graphics and choose between the repository's asset tools or a fallback.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/HorizonRobotics/OE-Skills
agentmods
npx agentmods add skills/horizonrobotics/oe-skills/j6-ucp-model-perf-eval

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for j6-ucp-model-perf-eval

README.md
[![agentmods](https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-model-perf-eval/github.svg)](https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-model-perf-eval)
Your own site
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-model-perf-eval"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-model-perf-eval/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.

agentmods 80×15 button for j6-ucp-model-perf-eval

Your own site · 80×15
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/j6-ucp-model-perf-eval"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/j6-ucp-model-perf-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,556 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.03556
Opus 5 $0.00035 $0.01778
Sonnet 5 $0.00014 $0.00711
Haiku 4.5 $0.00007 $0.00356

Measured 11d ago against content hash 423942dccc97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

j6-ucp-model-perf-eval 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.

horizon/skills/ucp/j6-ucp-model-perf-eval/SKILL.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Perf Eval

通过 SSH/SCP 将 hrt_model_exec 部署到远程 J6 aarch64 开发板,遍历用户指定的 thread_num 和 core_id 参数组合运行 perf 评测,收集 --profile_path 结构化输出与 BPU/CPU 段级性能数据,生成性能汇总报告与最优配置推荐,并将报告保存到本地文件。

适用场景

  • 在 J6 实板上评测 .hbm 模型推理性能(延迟、FPS)
  • 扫描不同 thread_num / core_id 组合,探索最佳性能配置
  • 远程部署 hrt_model_exec 到 aarch64 板端并执行 benchmark
  • 对比不同配置的性能差异,生成结构化报告
  • 分析模型 BPU/CPU 段的执行耗时占比

触发关键词:性能测试、perf、benchmark、性能评估、板端测试、模型吞吐量、参数扫描

工作流程

严格按照以下 6 步顺序执行,不可跳步。

Step 1:收集信息

向用户收集以下信息。缺少必填项时,必须逐一询问,全部收集完毕后方可进入 Step 2。

项目 必填 默认值 示例
板端 IP 地址 - 192.168.1.100
SSH 用户名 root root
SSH 端口 22
认证方式 - 密码 或 密钥路径(如 ~/.ssh/id_rsa
模型文件路径 - /data/models/resnet50.hbm(板端)或本地路径
model_name 自动检测 resnet50
thread_num 范围 1,2,4,8 1-81,2,4,8,16
core_id 选项 0 0,1
frame_count 200 500
板端部署目录 /tmp/hrt_model_exec
enable_warmup true
enable_mem_lru true

必须明确确认的信息

  1. 板端 IP 地址 — 若用户未提供,直接询问:"请提供开发板的 IP 地址"
  2. SSH 用户名 — 若用户未提供,询问:"SSH 登录用户名是什么?(默认 root)"
  3. 认证方式 — 若用户未提供,询问:"SSH 认证方式?密码或密钥路径"
  4. 模型文件路径 — 若用户未提供,询问:"请提供 .hbm 模型文件路径(板端路径或本地路径)"
  5. 模型文件位置 — 若用户只给了路径但未说明位置,询问:"该模型文件在本地还是已在板端?"
  6. 板端部署目录 — 若用户未指定,使用默认值 /tmp/hrt_model_exec,但需确认

thread_num 范围解析规则

  • 范围写法 1-8:展开为 1,2,3,4,5,6,7,8
  • 列表写法 1,2,4,8:直接使用
  • 展开后所有值必须在 [1, 32] 范围内

core_id 说明

  • 0 = 任意核心(运行时自动选择)
  • 1 = BPU Core 0
  • 2 = BPU Core 1
  • 1,2 = 双核并行
  • J6 有 2 个 BPU 核心,有效值:0, 1, 2, "1,2"

模型文件位置判断

  • 用户说明在板端:直接使用板端路径
  • 用户提供本地路径:通过 SCP 上传到板端部署目录

Step 2:检查/构建 hrt_model_exec

  1. 检查本地 tools/hrt_model_exec/output_shared_J6_aarch64/ 目录是否存在且完整:
    • 必须存在:aarch64/bin/hrt_model_exec
    • 必须存在:aarch64/lib/ 下的 .so 文件
  2. 若目录不存在或不完整,执行构建:
    cd tools/hrt_model_exec && bash build_aarch64.sh
    
  3. 构建依赖 LINARO_GCC_ROOT 环境变量指向交叉编译工具链。若构建失败,提示用户检查工具链配置。

Step 3:部署到远程板端

  1. SCP 部署 hrt_model_exec 工具目录:
    scp -P <port> -r tools/hrt_model_exec/output_shared_J6_aarch64/ <user>@<ip>:<deploy_dir>/
    
  2. 若模型文件在本地,SCP 上传:
    scp -P <port> <local_model_path> <user>@<ip>:<deploy_dir>/model.hbm
    
  3. 通过 SSH 验证部署:
    ssh -p <port> <user>@<ip> "ls <deploy_dir>/aarch64/bin/hrt_model_exec && ls <deploy_dir>/aarch64/lib/"
    
  4. 运行 model_info 检查模型信息,确认编译核数:
    ssh -p <port> <user>@<ip> "cd <deploy_dir>/script && \
      export LD_LIBRARY_PATH=../aarch64/lib/:\$LD_LIBRARY_PATH && \
      ../aarch64/bin/hrt_model_exec model_info --model_file=<model_path>"
    
    若用户配置了多核 core_id 但模型仅编译为单核,给出警告提示。

Read the full file on GitHub · 286 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 286 lines · 70 tokens per session scan E 423942dccc97

Subscribe to this mod's changes

j6-ucp-model-perf-eval is a skill published in the GitHub repository HorizonRobotics/OE-Skills (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 3,556 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens