What is horizon-tc-ui?

Integration guidance for the OpenExplorer command-line toolchain, which converts and prepares machine-learning models for supported hardware. It covers configuration, compilation, quantization, accuracy checks, performance analysis, and deployment.

Use it when writing YAML configurations, converting ONNX or Caffe models, creating HBIR or HBM outputs, tuning quantization, checking accuracy, analyzing performance, or preparing board deployment.

It helps an agent choose the right tool and procedure for each model-processing task. This reduces confusion around configuration files, output formats, hardware targets, and validation steps.

horizon-tc-ui — Skill for Claude Code and Codex by HorizonRobotics

Install

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.

Any agent

npx skills add HorizonRobotics/OE-Skills --skill horizon-tc-ui

Clone the repo

git clone --depth 1 https://github.com/HorizonRobotics/OE-Skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/horizon-tc-ui/github.svg)](https://agentmods.dev/skills/horizonrobotics/oe-skills/horizon-tc-ui)

Your own site

<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/horizon-tc-ui"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/horizon-tc-ui/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/horizon-tc-ui"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/horizon-tc-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,206 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00172	$0.02206
Opus 5.5	$0.00069	$0.00882
Sonnet 5.5	$0.00034	$0.00441
Haiku 4.5	$0.00017	$0.00221

Measured 2mo ago against content hash 6c46b1c53580, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

horizon-tc-ui 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 2mo ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/detect_env.py, scripts/diff_yaml.py, scripts/export_schema.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/horizon_tc_ui/horizon-tc-ui/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

horizon-tc-ui Skill

适用范围

本 Skill 用于 OpenExplorer 工具链 CLI 包相关任务，覆盖以下六个核心工具：

hb_compile
hb_model_info
hb_verifier
hb_analyzer
hb_config_generator
hb_eval_preprocess

主要覆盖流程：

ONNX/Caffe 模型 → YAML 配置 → PTQ 量化 → HBIR(.bc) → HBM(.hbm) → 精度验证 / 性能分析 / 板端部署

触发词

以下关键词触发本 Skill：

工具名：hb_compile、hb_model_info、hb_verifier、hb_analyzer、hb_config_generator、hb_eval_preprocess
领域术语：yaml配置、编译、量化、板端部署、PTQ、HBIR、HBM、march、calibration、cal_data_dir、定点、浮点、bc类型
常见操作：生成yaml、编译模型、模型信息、精度验证、性能分析、板端推理、fast-perf、check模式
架构名：nash-b-lite、nash-b、nash-b-plus、nash-e、nash-m、nash-p、nash-h
项目名：horizon_tc_ui、OpenExplorer、工具链

场景路由表

用户意图 → 参考文件：

用户想做什么	关键词示例	参考文件
从零写 YAML 配置	生成yaml、写配置、模板	`references/tasks/task-yaml-authoring.md`
编译模型为 HBM	编译、hb_compile、量化	`references/tasks/task-float-to-hbm.md`
快速性能估算	fast-perf、性能估算、不要精度	`references/tasks/task-fast-perf.md`
精度掉点调优	精度掉点、calibration、量化调优	`references/tasks/task-calibration-tuning.md`
精度分析调试	精度分析、cosine、consistency	→ Delegate 见 delegations.md
编译失败排查	编译报错、OP不支持、shape推导	`references/tasks/task-compile-debug.md`
性能分析调试	性能分析、perf、瓶颈	→ Delegate 见 delegations.md
查看模型信息	模型信息、hb_model_info、输入输出	`references/tasks/task-model-inspection.md`
评估数据预处理	hb_eval_preprocess、评估数据	`references/tasks/task-eval-preprocess.md`
板端部署验证	板端、hb_verifier、SSH、推理	`references/tasks/task-board-deploy-verify.md`
判断 BC 模型定点/浮点	定点、浮点、bc类型、quantized/float bc	`references/tips/detect-bc-type.md`
删除/保留模型 IO 节点	删除节点、删Quantize、删Dequantize、删Cast、保留节点、remove_node_type、remove_node_name	`references/tips/remove-io-nodes.md`
YAML 参数含义查询	参数说明、schema、字段	`references/yaml/overview.md`
报错排查	报错、error、失败	`references/troubleshooting/` 下对应文件

Delegate 决策

本 Skill 在以下场景 delegate 到外部 Skill：

Read the full file on GitHub · 159 lines

Files

What ships with it

50 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.

2mo ago First seen · 159 lines · 172 tokens per session scan A 6c46b1c53580

Subscribe to this mod's changes

horizon-tc-ui is a skill published in the GitHub repository HorizonRobotics/OE-Skills (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 172 tokens to every session and 2,206 once invoked, about $0.0007 per session on Opus 5.5. 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.

Data and AI Hardware and IoT

horizon-tc-ui next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
horizon-tc-uiHorizonRobotics/OE-Skills	Skill	27	4mo ago	Apache-2.0	A	172	Claude Code, Codex
spark-environment-setupwshobson/agents	Skill	42k	yesterday	MIT	A	76	Claude Code
spark-memory-thermal-opswshobson/agents	Skill	42k	yesterday	MIT	A	59	Claude Code
spark-training-gotchaswshobson/agents	Skill	42k	yesterday	MIT	A	63	Claude Code
inference-serving-llama-cppdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	80	Claude Code, Codex
amc-run-rtsp-calibrationNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	59	Claude Code, Codex
deepstream-generate-pipelineNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	108	Claude Code