Placing Held Feature

Organization

graph-robots

placing-held-feature

Move a held object so one of its declared features lands on a target point — a ring onto a hook, a tip into a hole, a plug at a bore. Composes the hand pose from the live object pose and the feature's centre in the object's own frame, recomputed each round so in-jaw slip cannot compound. Use for any goal written as "this object's feature at that place"; do NOT drive the hand to the target directly, which is wrong by the length of the held object.

Overview

Publisher	graph-robots
Repository	`open-robot-skills`
Skill name	`placing-held-feature`
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 Placing Held Feature 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/placing-held-feature
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.

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/placing-held-feature .claude/skills/placing-held-feature

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

Use it in TypingMind

Enable Placing Held Feature 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 Placing Held Feature 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 Placing Held Feature 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.

placing-held-feature

The place stage's geometry: where must the hand be so that the thing it is holding arrives where the goal wants it.

Why this is its own skill

Grasping has a whole ladder of strategies and placing had none, which is backwards for any goal phrased as a relation between a held object's feature and a fixture. The composition is small and the mistake is not:


feature_now = object_position + R(object_rotation) · feature_local
move        = target − feature_now
hand_goal   = hand_now + move

Without it the obvious move is to drive the hand at the target, and that is wrong by the length of the tool. It fails as a refusal rather than as a miss, so it reads like an unreachable workspace rather than a mis-specified goal — a diagnosis that costs iterations, because the fix it suggests (try the other arm, give up on the target) is not the fix.

When to use

A goal written as object.feature at fixture.feature or in a region: a loop over a rod, a shaft into a hole, a plug at a bore.
Any time the held object is large relative to the hand.

When NOT to use

To orient. This translates only; turn first, then mate.
Before the object is held. It reads the object's live pose, which before a grasp is wherever it is lying.

Recommended subgraph state flow

text
locate → orient → mate → plan → execute → verify

locate — the target point. For a welded fixture with no body and no OBB, that is sim.query on the goal's own atom and refs; its at is the feature's world position.
orient — turn the held object so the mating axis lines up, as a locked motion.plan_joint at the current position. Transit first, then turn.
mate — script: scripts/<sg>/mate_feature.py. Route on route.
plan/execute — motion.plan_linear(end=Ref("mate.hand_goal"), orientation="lock") then robot.execute_trajectory. Locked, because the orientation you turned to is the one that must survive the move.
verify — re-run mate and read distance_m. Shrinking means the round worked; flat means the move is not being executed as planned.

Use stop_short_axis/stop_short_m when the fixture is mounted flush to a board: close the two free axes fully and stop short on the board's normal, so the approach does not drive the load into the mounting.

Required end states

End state	Meaning
`ready`	`hand_goal`, `move_m`, `feature_now`, `distance_m`.
`unknown`	A pose or point could not be read. Nothing moved; fix the inputs.

Bundled files

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

scripts/mate_feature.py6 KB

Frequently asked questions

What does the Placing Held Feature AI skill do?

Why use Placing Held Feature on TypingMind?

Because you install it once and use it with any model. Placing Held Feature 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 Placing Held Feature in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/graph-robots/open-robot-skills/tree/main/skills/placing-held-feature. 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 Placing Held Feature?

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 Placing Held Feature?

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

Is the Placing Held Feature 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

Cuda Index Width

pytorch

OrganizationPopular

Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. Use when fixing large-tensor indexing overflows, deciding whether to use int64_t, canUse32BitIndexMath, CUDA_KERNEL_LOOP_TYPE, or…

Plan Change

Turn a feature request into a minimal, file-level implementation plan before any code.

Simplified English

Write user-facing comments, plans, and documents in ASD-STE100 Simplified Technical English — short, unambiguous sentences with approved words and one meaning each — so readers understand them the…

Archify Review

Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and code quality assessments.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

placing-held-feature

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