Tipping Over A Surface Edge logo

Tipping Over A Surface Edge

Organization
graph-robots
tipping-over-a-surface-edge

Turn a body over on the surface it rests on instead of carrying it — pinch two opposite walls LOOSELY and off centre so the pads act as a pin joint, lift so the surface and gravity stand the body up on its own edge, then press it onto the surface and pull the pins toward you about whichever edge is grounded until it is just past balance, and let go. Use when a rigid grasp cannot transmit the torque a full roll needs (a parallel jaw rolling about its own closing axis), when the body is too big to turn over in hand, or when the arm's envelope cannot follow a held body through the roll.

Overview

Publishergraph-robots
Repositoryopen-robot-skills
Skill nametipping-over-a-surface-edge
Stars
58
Forks
8
Bundled files
8
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.

  • 8 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 Tipping Over A Surface Edge 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/graph-robots/open-robot-skills/tree/main/skills/tipping-over-a-surface-edge
  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/graph-robots/open-robot-skills.git /tmp/open-robot-skills
mkdir -p .claude/skills
cp -r /tmp/open-robot-skills/skills/tipping-over-a-surface-edge .claude/skills/tipping-over-a-surface-edge
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tipping Over A Surface Edge 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 Tipping Over A Surface Edge 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 Tipping Over A Surface Edge 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.

tipping-over-a-surface-edge

Turn a body over by letting the surface it rests on do the turning.

Why this is its own skill

A parallel jaw transmits force well and torque about its own closing axis badly: two pads on a 12.6 mm wall are a friction clutch a few millimetres wide. A strategy that grasps rigidly and rolls asks the clutch to carry the whole roll and stalls (63 degrees on the crate, measured, at every grip force and arm gain tried). This strategy asks the pads for force only — a pin joint — and gets the rotation from gravity and from the surface's edge.

When to use

  • The body is wide and flat, and the roll would be about the jaws' closing axis.
  • The body's mass or size is beyond an in-hand roll, or the arm's envelope cannot follow the held body around.
  • There is surface to tip onto: tipping over an edge carries the body one full width in the direction it falls.

When NOT to use

  • There is no room to land: the flip travels a body width across the surface.
  • The body cannot stand on the edge it would pivot on (a round or very narrow section), or its centre of mass sits so far from that edge that the standing body is unstable the wrong way.

Recommended subgraph state flow

text
read_scene → approach → pinch → lift → press_pull → release → check → END
                                                      ↑              │ standing
                                                      └── re-grasp ──┘
  1. read_scene — which hand is on which side, the body's pose, the declared features (sim.query(atom="geometry", ...) on the pinch box and the edges).
  2. approach — both hands to a hover over their pinch points, wrist at the one roll the whole manoeuvre will hold, then straight down onto the wall with the wrist locked.
  3. pinch — robot.set_grip(object_width_m=<wall>, squeeze_m=0.0015, ramp_steps=40). Loose. 3 mm slid where 1.5 held.
  4. lift — straight up, both hands together (robot.stream_dual), wrist still, until the near corner leaves the surface (read the edge's height).
  5. press_pull — chords of 3 degrees about the grounded edge, read live each chord, hands commanded 8 mm below the rotated point, wrist following the measured attitude. Stop on the measured attitude a little past balance.
  6. release — crack, out along the mouth, outboard past the ends, wait.
  7. check — the body's attitude after settling routes the exit.

The numbers in scripts/tipcommon.py are the crate's (crate_flip/flip on yam_i2rt) and each one carries its measurement; read a different body's from its declared features and the packet's attitude facts rather than reusing them.

Required end states

End stateMeaning
invertedTurned over and at rest on the surface.
standingRocked back onto its wall at the release. Re-grasp through the mouth and pull further.
otherSlipped out during the lift, or thrown by the release. Start over from approach.

Bundled files

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

Frequently asked questions

What does the Tipping Over A Surface Edge AI skill do?

Turn a body over on the surface it rests on instead of carrying it — pinch two opposite walls LOOSELY and off centre so the pads act as a pin joint, lift so the surface and gravity stand the body up on its own edge, then press it onto the surface and pull the pins toward you about whichever edge is grounded until it is just past balance, and let go. Use when a rigid grasp cannot transmit the torque a full roll needs (a parallel jaw rolling about its own closing axis), when the body is too big to turn over in hand, or when the arm's envelope cannot follow a held body through the roll.

Why use Tipping Over A Surface Edge on TypingMind?

Because you install it once and use it with any model. Tipping Over A Surface Edge 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 Tipping Over A Surface Edge in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/graph-robots/open-robot-skills/tree/main/skills/tipping-over-a-surface-edge. 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 Tipping Over A Surface Edge?

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 Tipping Over A Surface Edge?

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

Is the Tipping Over A Surface Edge 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

Set up your own AI workspace now

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