Skip to content
Agentmart
Submit a tool

manipulation-pick-and-place

Use when the user requests a supervised pick of a stable target and placement at an approved destination.

Skill by Chenxi-Li24

IndexedMIT★ 4
Write a review

Chalk Labs

Need help deploying manipulation-pick-and-place?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/chenxi-li24-manipulation-pick-and-place

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when the user requests a supervised pick of a stable target and placement at an approved destination.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/manipulation-pick-and-place

What's inside

Skill name
manipulation-pick-and-place
Description
Use when the user requests a supervised pick of a stable target and placement at an approved destination.
License
MIT
Instructions
36 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: "manipulation-pick-and-place" does not match folder "pick-and-place"

Files (2)

  • SKILL.md
  • manifest.yaml

SKILL.md (first lines)

# Supervised Pick And Place

## Purpose

Coordinate observation, target selection, grasp planning, one-time authorization, execution supervision, gripper control and result verification for a single target.

## Required Flow

1. Resolve a fresh stable `TargetRef`.
2. Call `plan` only; do not move.
3. Return an immutable `thirdhand.task-plan.v1` and concrete risk list.
4. Display the plan and obtain one user authorization.
5. Validate authorization, plan revision, target pose revision and service health.
6. Start independent supervision.
7. Execute through Robot Service.
8. Verify grasp and placement, then return a versioned result.

## Safety Invariants

The Skill never opens `can0` or imports the SDK directly. Robot Service checks joint limits, speed, continuity, fresh feedback, all-zero targets, gripper range and Supervisor state before every physical segment.

Any plan, target, calibration, dependency or action-range change invalidates authorization. Stop or interruption never auto-resumes.

## Dependencies

Requires Robot, Vision and Supervisor services plus Startouch and XVisio devices. Destination geometry and calibration revision must be explicit.

## Current Status

The web, Vision Service and Robot Service adapters are migrated. The supervised
bottle workflow lives in `skills/manipulation/bottlegrasp` and is exposed
through the loopback bottle-pick runtime on port 8766. Physical execution remains
locked until the approved calibration, v3 depth evidence, validated placement
path and explicit supervised-motion authorization are all present.

From Chenxi-Li24/UIEAclub_ThirdHand_VLA, MIT.

More from Chenxi-Li24/UIEAclub_ThirdHand_VLA

Signals

Stars
4
Forks
1
Open issues
0
Last commit (this folder)
Sep 20, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Chenxi-Li24

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get manipulation-pick-and-place running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying manipulation-pick-and-place?

CallGet help
Cite this page

manipulation-pick-and-place skill. Agent Mart. https://agentmart.dev/skills/chenxi-li24-manipulation-pick-and-place (last updated 2026-10-24)