原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

genie_sim Skill

代码仓库 ↗

作者:AgibotTech★ 1,640 (whole repo)34 个 skill

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 34 skills

  • Connects Instruction files the AI reads
  • Account or key Not confirmed yet (README not read yet)
  • Category 其他
Maker’s original description
Simulation Platform from AgiBot
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/agibottech-genie-sim.svg)](https://mcp.popnx.com/en/skills/agibottech-genie-sim)

相似的 Skill

同类工作,排序与 Skill 列表相同

与相似项目对比
本项
genie_sim
llmfitclaude-videoVideoCaptionerclaude-cookbooks
作者AgibotTechAlexsJonesbradautomatesWEIFENG2333anthropics
Skill 数341114
GitHub 星标1,64039,01820,99916,54454,763
最近代码更新2026年11月16日2026年11月16日2026年9月25日2026年9月12日2026年11月5日
许可证–MITMITGPL-3.0MIT

AgibotTech 提供的 34 个 Skill(指令集),AI 读取后照做 · 不是 MCP server

Pick the skill to install

Install only the ones you use. Open a skill to see how to install it

This set has 34 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below

Showing 30 of 34 See all on GitHub

  • add-robot

    Bring a custom robot into the Genie Sim RT Engine — author / fix a xacro / URDF in `genie_sim_robot_model`, prep meshes with the offline tools (`normalize_obj_names.py`, `diagnose_urdf.py`, `recompute_inertia.py`, `fix_dae_units.py`, `copy_dae_material.py`), stage assets into the AS3 layout (`robot…

  • build-workspace

    Build the `geniesim_ros` colcon workspace inside the Genie Sim Docker container using the `geniesim ros build` CLI verb. Produces the `./devel` overlay that every `ros2 launch genie_sim_bringup …` step depends on. Trigger: When the user asks to "build ros workspace", "colcon build", "build genie_si…

  • challenge-baseline-model

    Provision and launch the Season I baseline inference model end to end: clone the inference code from a given git repo/branch, download the checkpoints from ModelScope into the repo's local checkpoints path, install deps, and start the inference agent. Trigger: When the user asks to clone the infere…

  • challenge-diagnose-connection

    Use when the contestant's agent keeps disconnecting from the gateway, a job fails with failure_reason 9 / "tunnel lost: reconnect window expired", or the log shows close 1006 / 1011 / "keepalive ping timeout". Runs read-only local checks (event-loop lag, link loss, throughput during a large frame)…

  • challenge-download-assets

    Query, download, and verify GenieSim simulation assets by task or track with geniesim assets. Supports resumable transfers, ModelScope/HuggingFace source selection, and container asset mounts. Use for scenes, robots, and benchmark runtime assets; use challenge-download-datasets for LeRobot training…

  • challenge-download-datasets

    Download the Simulation Challenge LeRobot v2.1 training datasets from ModelScope using ./scripts/download_dataset.sh. Pulls task-suite data (instruction / manipulation / sim2real / cross_embodiment_transfer / dexterous_manipulation / precision_manipulation / whole_body_coordination) from the agibot…

  • challenge-help

    Entry point for the Simulation Challenge skill set. Use when the user mentions the challenge, leaderboard, submitting a model, or any of the /api/challenge/* endpoints — this skill picks the right downstream skill for them.

  • challenge-login

    Use when the contestant needs to obtain or refresh their Simulation Challenge JWT (CHALLENGE_TOKEN), or wants to inspect the current logged-in user. Trigger words include "log in", "token", "401", "current user", "name", "refresh".

  • challenge-poll-result

    Use to track a Simulation Challenge job's progress — list jobs, watch a job's status until terminal, fetch its per-task scores, or pull execution logs when it failed. Read-only; safe to run without confirmation.

  • challenge-ranking

    Use to fetch the contestant's best score and the leaderboards (Season I per-board leaderboards, the Season II leaderboard, the top-5 overview) for the Simulation Challenge. Read-only; safe to run without confirmation.

  • challenge-route-inference

    Connect existing local or remote GenieSim-compatible inference services to official evaluation through one or more tunnel routes. Use for new or resumed jobs, shared-service concurrency, route management, and simulator observation/ action protocol or adapter questions. Includes the CoRobot protocol…

  • challenge-run-agent

    Use when the contestant wants to launch the inference Agent that connects to the Simulation gateway via WebSocket. Wraps the inference repo's ./scripts/tunnel.sh and scales to PARALLELISM processes. This is side-effecting (consumes GPUs and the job's parallelism slots) — confirm before launching.

  • challenge-submit-job

    Use when the contestant wants to submit a model evaluation job to the Simulation Challenge — POST /api/challenge/job — or put a finished Season II (`board: "v2"`) job up for review (POST /api/challenge/job/{id}/review). Both are side-effecting; submitting a job also consumes quota. Always confirm w…

  • challenge-troubleshoot

    Use when something in the Simulation Challenge pipeline is misbehaving — auth errors, agent disconnects, jobs stuck in Pending, jobs ending in Failed, drain frames. Maps a symptom to its likely cause and the next command to run.

  • check-inference

    Probe a model inference WebSocket server (e.g. `serve_policy`) and validate the response — using the `geniesim benchmark check-inference` CLI verb, which wraps the benchmark package's `check_inference.py`. Trigger: When the user asks to "check inference", "校验模型推理", "test inference server", "verify…

  • convert-dataset

    Convert robot trajectory datasets between formats — currently agibot v1 → LeRobot v2.1 (parquet + HEVC/PNG-encoded MP4). Uses the `geniesim dataset convert agibot-to-lerobot` CLI verb, which wraps the `geniesim_benchmark.dataset.convert.agibot_to_lerobot` Python API. Trigger: When the user asks to…

  • debug-physics

    Diagnose physics misbehaviour in the Genie Sim RT Engine — robot swings on spawn, contacts tunnel, joints drift past their limits, cloth blows up, the convex-hull proxy renders instead of the visual mesh, or the wrong physics backend is active. Walks the user through the engine's debug toggles (vis…

  • find-example

    Find and compare existing GenieSim task examples by scene type, action, RobotAPI calls, and object keywords before authoring or changing data_gen.py.

  • geniesim-asset-search

    Find and verify assets in a local GenieSim asset library for scene generation, using optional Qwen3-VL video embeddings and a directory-index fallback.

  • geniesim-data-collection

    Execute generated GenieSim data_gen.py tasks with the data-collection runtime, record camera videos directly with --render, inspect physical and recording results, and optionally replay recorded trajectories.

  • geniesim-scene-generation

    Design, generate, preview, validate, and optionally generalize GenieSim scenes using the existing DSL, a USD patch, or direct Python USD authoring.

  • geniesim-scene-to-data

    Coordinate GenieSim requests across scene design, optional task orchestration and optional data collection, preserving scene approvals and routing only the requested stages.

  • launch-scene

    Launch a `genie_sim_bringup` scene against a chosen physics + render backend, using `ros2 launch genie_sim_bringup app.launch.py`. Covers the scene × launcher matrix (pick-and-place / whole-body-control / flat-table demos × Isaac PhysX / Newton-standalone backends) and the optional MoveIt 2 + WBC R…

  • material-override

    Tune PBR metallic / roughness on URDF visual meshes without re-exporting DAE — author an inline ` ` element inside any ` `, and let the engine's URDF→USD pipeline patch the converter's defaults post-conversion. Useful for sim-to-real visual fidelity (DAE materials round-trip poorly; Isaac Sim's imp…

  • moveit-wbc

    Bring up MoveIt 2 + whole-body-control RViz for the Genie G2 family, using `ros2 launch genie_sim_moveit wbc.launch.py`. Covers arm × gripper selection, the three packaged IK plugins (KDL-coupled, bio_ik-coupled, relaxed-IK), the GenieBioIK human-prior A/B switch, and the `use_ros2_control:=false`…

  • record-episode

    Capture a Genie Sim RT Engine episode while a scene runs — record the canonical ROS 2 topics (`/joint_states`, `/joint_command`, `/tf`, `/tf_static`, `/clock`, and selected scene, control and camera topics) with `ros2 bag`; check that the required streams reached the bag. Teleop and benchmark loops…

  • run-benchmark

    Launch a geniesim_benchmark task locally (typically inside the GUI Docker container) against a user-provided inference server, using the `geniesim benchmark run` CLI verb. Trigger: When the user asks to "run geniesim", "本地跑仿真", "启动仿真任务", "run a benchmark", "launch _ .yaml", or wants to execute a be…

  • run-dream

    Run Genie Sim Dream G1/G2 world-model rollouts with recorded actions or the pi0.5 policy, then review the generated video with a VLM. Use for Dream inference, example replay, or closed-loop checks after its three Python environments and required checkpoints have been prepared.

  • run-wuji-chef-newton

    Start and verify the Newton engine for the G2 crsB + Wuji wok scene scene_flat_g2_sp_chef_wuji with launcher_newton_mjxpbd, using OpenGL by default or optional OVRtx rendering with ROS image viewing. Use when the user asks to launch, restart, view, or check the Newton chef scene, "start the wok sce…

  • teleop-bridge

    Wire a `geniesim_teleop` VR/Pico session into a running Genie Sim RT Engine scene — pick the right scene yaml, launch `wbc.launch.py` with `use_ros2_control:=false` so move_group serves `/compute_ik` while the teleop publisher owns `/joint_command`, and confirm no topic fighting. Trigger: When the…

Skill 和 MCP 有什么不同

MCP = 手

把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。

Skill = 手册

教 AI 怎么做某项工作的文本文件,不连接任何服务。

有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。

适用的应用

Claude CodeCursor

依据开发者 README 和 repo 中的文件夹

安装

Pick a skill first

This repo has 34 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP

Let the AI install it
Upload to claude.ai

Go to the skill list ↑

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

来自 GitHub

GitHub 星标
1,640
Stars are for the whole repo, not each skill
开发者
AgibotTech
许可证
未注明许可证 此 repo 未注明许可证,默认作者保留所有权利;转发或商用前请先询问作者。
最近代码更新
2026年11月16日
repo 中的 SKILL.md 文件(含译本和模板)
30