Proposing Side Grasps

Organization

graph-robots

proposing-side-grasps

Propose horizontal (side-entry) grasps swept around an object's oriented box — twelve azimuths ranked by jaw margin. Use when top-down access is blocked by an overhead shelf, a lid or a bin wall, or when the object's vertical dimension is the only one the hand can span. Declines when the object is wider than the jaws from every azimuth.

Overview

Publisher	graph-robots
Repository	`open-robot-skills`
Skill name	`proposing-side-grasps`
Stars	58
Forks	8
Bundled files	1
License	Apache-2.0
Links	Skill source Repository

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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by graph-robots on GitHub. Read the source before you install it.

Installation

Install the Proposing Side Grasps AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/graph-robots/open-robot-skills/tree/main/skills/proposing-side-grasps
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/graph-robots/open-robot-skills/tree/main/skills/proposing-side-grasps

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/graph-robots/open-robot-skills.git /tmp/open-robot-skills
mkdir -p .claude/skills
cp -r /tmp/open-robot-skills/skills/proposing-side-grasps .claude/skills/proposing-side-grasps

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Proposing Side Grasps 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 Proposing Side Grasps 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 Proposing Side Grasps 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.

proposing-side-grasps

One strategy for the propose stage: horizontal entry, swept around the object.

Why this is its own skill

It is the alternative that exists so a top-down refusal has somewhere to go. proposing-short-axis-grasps declines by measuring a width; it cannot offer a side entry, because approaching horizontally is a different strategy, not a different number. A policy with only one propose rung answers a structural refusal by re-tuning parameters that cannot help.

When to use

Overhead access is blocked — a shelf plate, a lid, a bin rim above the target.
The object is flat and wide on top but narrow in profile.
The top-down rung declined.

When NOT to use

The object stands against a wall or in a corner and only one azimuth is open. This skill will happily rank a blocked side first; the clearance gate in selecting-reachable-grasp is what makes that safe, so do not use this rung without a selector.
The graspable feature is a concave interior — a box's silhouette says nothing about concavity.

Recommended subgraph state flow

text
describe → get_obb → propose → select → END

describe — tool: robot.describe_gripper.
get_obb — tool: sim.get_object_obb (or geometry.filter_and_compute_obb on the vision body).
propose — script: scripts/<sg>/propose_side_grasps.py, inputs target_obb, gripper. Router on route.
select — build a pose per candidate with robot.grasp_frame(approach=…, close_heading_deg=…) and walk them with selecting-reachable-grasp. Its clearance gate is what turns "ranked by margin" into "reachable in this scene".

Required end states

End state	Meaning
`proposed`	Candidates, widest margin first. Continue to select.
`declined`	Wider than the jaws from every azimuth. The remaining option is a part of the object narrower than its whole box.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

scripts/propose_side_grasps.py4 KB

Frequently asked questions

What does the Proposing Side Grasps AI skill do?

Why use Proposing Side Grasps on TypingMind?

Because you install it once and use it with any model. Proposing Side Grasps 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 Proposing Side Grasps in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/graph-robots/open-robot-skills/tree/main/skills/proposing-side-grasps. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Proposing Side Grasps?

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 Proposing Side Grasps?

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

Is the Proposing Side Grasps AI skill free?

Yes. It is published on GitHub by graph-robots 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

Architecture Decision Records

affaan-m

CommunityPopular

コーディングセッション中にアーキテクチャ決定を構造化ADRとして記録し、自動的に決定の瞬間を検出し、コンテキスト、検討された代替案、根拠を記録します。今後の開発者がコードベースの形成理由を理解するためのADRログを維持します。

Automation Audit Ops

ECC用の証拠ベースの自動化インベントリとオーバーラップ監査ワークフロー。ユーザーがどのジョブ、フック、コネクタ、MCPサーバー、またはラッパーがライブか、壊れているか、冗長であるか、修正前に不足しているかを知りたい場合に使用します。

Grok

Delegate coding to xAI Grok Build CLI (features, PRs).

Setup Wizard Generator

NousResearch

OrganizationPopular

Generate a bash wizard guiding a human through manual setup.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

proposing-side-grasps

Why this is its own skill

When to use

When NOT to use

Recommended subgraph state flow

Required end states

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now