Agent skill

Rosclaw Embodied

by ros-claw in ros-claw/rosclaw

ROSClaw 具身任务纪律——通用物理原语编排、任务沙箱编码、证据验收、安全分层(何时用:任何涉及机器人/仿真/动作的任务)

MITAuto-check passed

Install Rosclaw Embodied

skills CLI
$ npx skills add ros-claw/rosclaw --skill rosclaw-embodied -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ros-claw/rosclaw rosclaw-embodied --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ros-claw/rosclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/rosclaw-agent/skills/rosclaw-embodied .claude/skills/rosclaw-embodied && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
rosclaw-embodied
GitHub stars
221
Token cost
~348 tokens
SKILL.md length
85 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

ROSClaw 具身任务纪律——通用物理原语编排、任务沙箱编码、证据验收、安全分层(何时用:任何涉及机器人/仿真/动作的任务)

  • SKILL.md covers 通用物理原语(SIM 自动执行,不弹批准), 任务沙箱编码, 证据与验收 and 安全分层, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Rosclaw Embodied is an agent skill from ros-claw/rosclaw. ROSClaw 具身任务纪律——通用物理原语编排、任务沙箱编码、证据验收、安全分层(何时用:任何涉及机器人/仿真/动作的任务)

Its SKILL.md is about 350 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Physical AI runtime for embodied agents — governed action, verified experience, physical memory, and skill evolution. The licence is MIT.

Example prompts

  • “/rosclaw-embodied”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 26fc0ae. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Rosclaw Embodied loads about 348 tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 85 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~348

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ros-claw/rosclaw at commit 26fc0ae, republished under its MIT licence (© ros-claw). 85 words, ~348 tokens.

Download SKILL.mdSave it as .claude/skills/rosclaw-embodied/SKILL.md (or your agent's skills folder).
name
rosclaw-embodied
description
ROSClaw 具身任务纪律——通用物理原语编排、任务沙箱编码、证据验收、安全分层(何时用:任何涉及机器人/仿真/动作的任务)

ROSClaw 具身任务纪律

Pi 是唯一大脑:理解用户目标、调查环境、组合通用原语、没有现成 能力时在任务沙箱写代码、运行观察修错、判断是否完成用户目标。

通用物理原语(SIM 自动执行,不弹批准)

  • trajectory_generate_planar_path:任意路径点 waypoints [{x,y,z,contact?}](contact=false=抬笔移动段)——文字/任意 图形都由你表达为点列;shape=star5|circle 只是便捷参数, 没有默认形状。返回 plan_id 句柄。
  • ur5e_simulate_cartesian_trajectory(plan_id) → trace_id (真实 MuJoCo 动力学 rollout + 跟踪指标)。
  • simulation_verify_tracking(trace_id, max_tracking_error_m) → 诚实 PASS/FAIL + 误差数值。
  • simulation_render_trace(trace_id, format=gif) / simulation_render_scene(trace_id, camera=...) → 交付物。
  • 观测:ur5e.get_end_effector_pose 等 OBSERVE 面。
  • 可信上下文每轮带 workspace_window(安全半径/z 窗口)—— 摆 waypoints 不要越界(规划器硬校验,越界即拒)。

任务沙箱编码

  • 活跃任务的 scratch/ 区可写可运行(write/edit/bash cwd 限定在 session 工作区与任务 scratch 内)——写几十行 Python 把字母/ 图形转成点列是正常能力,不需要内核替你认识任何形状。
  • scratch 是草稿——交付物登记走 outputs/(register_artifact)。

证据与验收

  • 交付物必须登记(rosclaw_artifact_register)——口头提到不算。
  • 仿真证据标 simulated——动力学自洽不证明真机效果。
  • 用户否定结果后修正或重开 revision——不得拿旧结果冒充。

安全分层

  • SIM:物理原语工具 + 任务沙箱代码自动执行。
  • 真机动作:必须走 rosclaw_request_action 的 admission 链 (rosclawd + permit + operator),任何其他路径都不是执行权威。
  • 改产品核心源码不是任务能力——走开发流程(克隆仓库+PR)。
  • 同一调用同一参数失败后不机械重试;先读结构化诊断。

权威资产

  • 机器人模型只认 e-URDF-Zoo 权威资产;测试 fixture 绝不出现在 交付证据里。不确定资产来源时先调查,不从 / 全盘搜索。

© ros-claw, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in packages/rosclaw-agent/skills/rosclaw-embodied of ros-claw/rosclaw.

Open the folder on GitHubat commit 26fc0ae

Compare with similar skills

Rosclaw Embodied next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Rosclaw Embodied compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Rosclaw Embodied this skillros-claw/rosclaw221—~348Automated safety check: PassMIT
Embodied AI NewsLeoYeAI/openclaw-master-skills2.2k—~4.8kAutomated safety check: PassMIT
Public Speaking EmbodiedLeoYeAI/openclaw-master-skills2.2k—~6.7kAutomated safety check: PassMIT
Embodied Carbon Esgdatadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction345—~664Automated safety check: PassMIT
Embodiment DescriptionAI4Scientist/nano-scientist1282 repos~1.6kAutomated safety check: NotesNone
Embodied Navigationinfranodus/skills119—~4.4kAutomated safety check: PassNone

Similar skills

  • Embodied AI News

    LeoYeAI/openclaw-master-skills

    Aggregates publicly available Embodied AI and Robotics news from curated sources (robotics media, arXiv, company blogs).

    2.2k GitHub stars~4.8k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed
  • Public Speaking Embodied

    LeoYeAI/openclaw-master-skills

    Physical presence and delivery skills for public speaking and presentations.

    2.2k GitHub stars~6.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Embodied Carbon Esg

    datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

    Estimate embodied carbon and produce ESG/climate reporting for construction: LCA per work item, material-based carbon factors, EU taxonomy and CSRD alignment.

    345 GitHub stars~664 tokensUpdated 1 mo ago
    Auto-check passed
  • Embodiment Description

    AI4Scientist/nano-scientist

    Write detailed embodiment descriptions for patent specifications.

    128 GitHub starsUsed in 2 repos~1.6k tokens
    Legal & ComplianceAuto-check: notes
  • Embodied Navigation

    infranodus/skills

    Transfer embodied movement principles (Vipassana equanimous scanning, Systema adaptive fluidity, contemporary dance tensegrity, EightOS confluence) to navigate work, relationships, projects…

    119 GitHub stars~4.4k tokensUpdated 20 days ago
    Auto-check passed
  • Entropy Box

    sickn33/agentic-awesome-skills

    Entropy Box knowledge-compiler for embodied-AI: turns bounded requirements into grounded workflows via Solution Consult, Search, Lookup, and Evidence.

    47k GitHub starsUsed in 1 repo~5.4k tokens
    Auto-check: warnings

More from ros-claw/rosclaw

  • Validates ROSClaw simulation workflows across MuJoCo, ROS 2, Gazebo and Isaac Sim with evidence-backed smoke tests, never touching a real robot.

    221 GitHub stars~2.5k tokensUpdated today
    Auto-check passed

Questions about Rosclaw Embodied

What does Rosclaw Embodied do?

ROSClaw 具身任务纪律——通用物理原语编排、任务沙箱编码、证据验收、安全分层(何时用:任何涉及机器人/仿真/动作的任务). Rosclaw Embodied is an agent skill from ros-claw/rosclaw.

How do I install Rosclaw Embodied in Claude Code?

Run `npx skills add ros-claw/rosclaw --skill rosclaw-embodied -a claude-code`. Or copy the skill folder (packages/rosclaw-agent/skills/rosclaw-embodied in ros-claw/rosclaw) into .claude/skills/rosclaw-embodied in your project. Claude Code loads it when a task matches its description.

How do I install Rosclaw Embodied in Codex?

Run `npx skills add ros-claw/rosclaw --skill rosclaw-embodied -a codex`. Or copy the skill folder (packages/rosclaw-agent/skills/rosclaw-embodied in ros-claw/rosclaw) into .agents/skills/rosclaw-embodied in your project. Codex loads it when a task matches its description.

Can I use Rosclaw Embodied in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ros-claw/rosclaw --skill rosclaw-embodied -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rosclaw-embodied, .gemini/skills/rosclaw-embodied, .github/skills/rosclaw-embodied and .opencode/skills/rosclaw-embodied in your project.

What does Rosclaw Embodied need to run?

SKILL.md names no scripts, command-line tools or credentials: Rosclaw Embodied is instructions for the agent only. Our summary lists: Python 3.

Does Rosclaw Embodied access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Rosclaw Embodied safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Rosclaw Embodied use?

Rosclaw Embodied is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Rosclaw Embodied use?

About 348 tokens (SKILL.md is roughly 1.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Rosclaw Embodied?

Skills that share tags, products or a category with Rosclaw Embodied: Embodied AI News (LeoYeAI/openclaw-master-skills, 2.2k stars), Public Speaking Embodied (LeoYeAI/openclaw-master-skills, 2.2k stars), Embodied Carbon Esg (datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction, 345 stars) and Embodiment Description (AI4Scientist/nano-scientist, 128 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Rosclaw Embodied?

ros-claw (a GitHub organization) maintains it in ros-claw/rosclaw, which has 221 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 10, 2026.

Source: ros-claw/rosclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.