Depalletizing Robot Task logo

Depalletizing Robot Task

Organization
insightos-community
depalletizing-robot-task

将一个搬箱 Robot Task 拆成可串行执行的四个 Robot Skill SubTask

Overview

Publisherinsightos-community
RepositorySemantic-Framework
Skill namedepalletizing-robot-task
Stars
104
Forks
22
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by insightos-community on GitHub. Read the source before you install it.

Installation

Install the Depalletizing Robot Task AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/insightos-community/Semantic-Framework/tree/main/configs/skills/robot/depalletizing-robot-task
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/insightos-community/Semantic-Framework.git /tmp/Semantic-Framework
mkdir -p .claude/skills
cp -r /tmp/Semantic-Framework/configs/skills/robot/depalletizing-robot-task .claude/skills/depalletizing-robot-task
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Depalletizing Robot Task in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Depalletizing Robot Task on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Depalletizing Robot Task is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

拆码垛 Robot Task 规划

本 Skill 只指导 Robot Agent 生成和推进 SubTask,不直接运行 Python、Ability 或 Robot SDK。只能选择当前 Robot 已安装并启用的精确 Robot Skill 版本。

单箱步骤

按当前 Robot Pose 和对象位置生成以下串行步骤:

  1. semantic-navigation:以来源对象的精确 object_ref 为业务目标;实际可操作基座 Pose 由 Navigation Ability 从实时场景和 Robot Profile 解析,不依赖 approach Region。
  2. grasp-object:传目标对象身份、可选几何提示、工具和策略。Skill会实时观测, 并在成功前把双臂整理到携物转运姿态。
  3. semantic-navigation:一次携物导航到目标堆叠列的放置工位,只传目标位姿和 carried_object_ref,不得复制上一项的 HeldObjectState。
  4. place-object:只传 object_ref 与目标列。Skill会实时读取持物、计算下一层 放置 Pose、验证稳定,并恢复 travel 姿态。

状态边界

  • SubTask 依赖表示执行顺序,不表示通过 JSON 搬运物理状态。
  • intent 不得写入 carrying_object、held_object 或 holding_object,包括 布尔值和 null。空载或携物属于执行期状态,写入 completion_criteria;Skill 通过 RobotState Ability 实时读取。carried_object_ref 只表示要搬运的对象 身份,可以保留。
  • Task input 中对象或目标列的 name/object_ref/target_ref 是 Robot Skill 重新观测时使用的业务身份;Map entity_id/region_id 只说明本次规划选择了哪条 地图记录。生成 intent 和可执行输入时必须保留业务身份,不能把 Map ID 改写成 object_ref、carried_object_ref 或放置 target_ref。
  • 来源导航 intent 中的 target.target_ref 必须使用当前要抓取的精确 object_ref; source_pallet 只描述支撑关系,不能替代目标箱体。Task Execution把该对象的中心Pose 作为提示交给 semantic-navigation,Navigation Ability再从实时SceneSnapshot解析支撑面、 箱体extent、当前Robot位置和Profile,选择托盘外且箱体仍在双臂范围内的基座工位。 Robot Agent不手算工作距离、栅格膨胀或四元数,也不使用Layout专用approach点。
  • 携物导航 intent 中的 target.target_ref 必须使用精确目标堆叠列。Robot Agent只提供 目标列中心Pose提示和 carried_object_ref;Navigation Ability结合实时支撑托盘与携物 包络解析一次可达工位,SDK继续对实际路线做碰撞检查。不得先到托盘前再二次导航。
  • Semantic Map只用于选择对象、列和基座目标;每个 Skill在 Stage入口通过Ability 重新观测当前物理事实。
  • 同一 Agent Run 中,参数和 revision 均未变化的 Map 查询结果必须复用;取得当前 Robot、目标、支撑面和邻障碍等计算所需事实后直接形成工位,不重复查询同一实体。
  • robot.run 返回 accepted 后停止模型轮询,等待 Robot Execution事件。
  • 滑移、过载、传感异常或状态未知时先停止并hold;不得重放已经开始的物理Action。
  • Skill进入 waiting_agent 时只在声明的局部决策范围内选择候选、刷新目标或终止; 需要扩大业务范围时交还Leader或询问用户。

Frequently asked questions

What does the Depalletizing Robot Task AI skill do?

将一个搬箱 Robot Task 拆成可串行执行的四个 Robot Skill SubTask

Why use Depalletizing Robot Task on TypingMind?

Because you install it once and use it with any model. Depalletizing Robot Task is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Depalletizing Robot Task in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/insightos-community/Semantic-Framework/tree/main/configs/skills/robot/depalletizing-robot-task. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Depalletizing Robot Task?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Depalletizing Robot Task?

As many as you like. As long as a model supports skills, you can use Depalletizing Robot Task with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Depalletizing Robot Task AI skill free?

Yes. It is published on GitHub by insightos-community under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇