Agentacct Workflow
mikehasa/agentacct
A skill your agent uses when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.
Validates ROSClaw simulation workflows across MuJoCo, ROS 2, Gazebo and Isaac Sim with evidence-backed smoke tests, never touching a real robot.
Install ROSClaw SimForge Validator
$ npx skills add ros-claw/rosclaw --skill rosclaw-simforge -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ros-claw/rosclaw rosclaw-simforge --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ros-claw/rosclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/rosclaw-simforge .claude/skills/rosclaw-simforge && rm -rf skills-srcUse ~/.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/
Install the "rosclaw-simforge" agent skill from https://github.com/ros-claw/rosclaw/tree/main/.agents/skills/rosclaw-simforge into .claude/skills/rosclaw-simforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rosclaw-simforge", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ros-claw/rosclaw/tree/main/.agents/skills/rosclaw-simforgeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ros-claw/rosclaw --skill rosclaw-simforge -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ros-claw/rosclaw rosclaw-simforge --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ros-claw/rosclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/rosclaw-simforge .agents/skills/rosclaw-simforge && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "rosclaw-simforge" agent skill from https://github.com/ros-claw/rosclaw/tree/main/.agents/skills/rosclaw-simforge into .agents/skills/rosclaw-simforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rosclaw-simforge", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ros-claw/rosclaw --skill rosclaw-simforge -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ros-claw/rosclaw rosclaw-simforge --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ros-claw/rosclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/rosclaw-simforge .cursor/skills/rosclaw-simforge && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "rosclaw-simforge" agent skill from https://github.com/ros-claw/rosclaw/tree/main/.agents/skills/rosclaw-simforge into .cursor/skills/rosclaw-simforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rosclaw-simforge", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ros-claw/rosclaw.git --path .agents/skills/rosclaw-simforge--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ros-claw/rosclaw --skill rosclaw-simforge -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ros-claw/rosclaw rosclaw-simforge --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ros-claw/rosclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/rosclaw-simforge .gemini/skills/rosclaw-simforge && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "rosclaw-simforge" agent skill from https://github.com/ros-claw/rosclaw/tree/main/.agents/skills/rosclaw-simforge into .gemini/skills/rosclaw-simforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rosclaw-simforge", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ros-claw/rosclaw rosclaw-simforgeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ros-claw/rosclaw --skill rosclaw-simforge -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ros-claw/rosclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/rosclaw-simforge .github/skills/rosclaw-simforge && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "rosclaw-simforge" agent skill from https://github.com/ros-claw/rosclaw/tree/main/.agents/skills/rosclaw-simforge into .github/skills/rosclaw-simforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rosclaw-simforge", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ros-claw/rosclaw --skill rosclaw-simforge -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ros-claw/rosclaw rosclaw-simforge --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ros-claw/rosclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/rosclaw-simforge .opencode/skills/rosclaw-simforge && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "rosclaw-simforge" agent skill from https://github.com/ros-claw/rosclaw/tree/main/.agents/skills/rosclaw-simforge into .opencode/skills/rosclaw-simforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rosclaw-simforge", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
rosclaw-simforge- GitHub stars
- 221
- Token cost
- ~2.5k tokens
- SKILL.md length
- 907 words
- Files
- 7 (incl. scripts, references)
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Validates ROSClaw simulation workflows across MuJoCo, ROS 2, Gazebo and Isaac Sim with evidence-backed smoke tests, never touching a real robot.
- Works in 8 steps: Establish provenance → Validate the ROSClaw core → Validate ROS 2 and Gazebo → …
- Smoke-testing a ROSClaw simulator integration without a real robot
- SKILL.md covers Safety boundary, Workflow and Resources
- Runs Shell scripts from its folder; calls python and git
What it does
This skill validates the full ROSClaw software loop - CLI, safety gates, simulators, MCP, evidence receipts, and asset distribution - using the exact rosclaw CLI from the checkout's own virtual environment rather than a possibly stale global install. It treats real hardware as explicitly out of scope unless separately authorized, and routes any action request through the daemon's own request-action path or the ROSClaw MCP server so the sandbox and firewall stay in the loop; it never publishes actuator commands or calls a motion service directly.
It starts by recording provenance - the current commit, working-tree status, and GPU memory - before validating the ROSClaw core with a temporary home directory, running its doctor and status checks, a deterministic demo, and the universal agent and MCP probe. It then validates ROS 2 and Gazebo separately: a dedicated script builds a Humble rosbridge and turtlesim image, deploys the stack, subscribes to pose, and proves that direct velocity commands are blocked, while a Gazebo script runs a guarded world with real diff-drive, odometry and laser simulation plus a deadman switch under launch testing.
It requires a physics step and a bounded task outcome with a machine-readable receipt before accepting a simulator pass, and it writes raw trajectories, logs and reports to an evidence directory outside the source checkout, treating a dependency failure as something to diagnose and work around rather than a passing skip.
When your agent uses it
- Smoke-testing a ROSClaw simulator integration without a real robot
- Validating ROS 2 and Gazebo stacks through ROSClaw's safety gates
- Producing an evidence-backed ROSClaw verification report
Example prompts
- “Run the ROSClaw Gazebo verification script and show me the receipt.”
- “Validate the ROS 2 rosbridge stack and confirm velocity commands are blocked.”
- “Produce a ROSClaw verification report for this simulator integration.”
Requirements
- The rosclaw CLI from the project's own virtual environment
- A GPU for Isaac Lab multi-GPU validation
Workflow steps
8 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 80c3efe. 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
Ships 4 files in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
pythongit
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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 SimForge Validator loads about 2.5k tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 907 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from ros-claw/rosclaw at commit 80c3efe, republished under its MIT licence (© ros-claw). 907 words, ~2,457 tokens.
Download SKILL.mdSave it as
.claude/skills/rosclaw-simforge/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- rosclaw-simforge
- description
- Safely install, validate, diagnose, and optimize ROSClaw simulation workflows across MuJoCo/MJWarp, ROS 2 rosbridge, turtlesim, Gazebo, Isaac Sim, Isaac Lab multi-GPU training, MCP, and the signed ROSClaw Hub. Use for evidence-backed physical-AI smoke tests, 4-GPU validation, simulator integration, Hub upload/download tests, or ROSClaw verification reports without a real robot.
ROSClaw SimForge
Validate the full software loop from CLI and safety gates through simulators, MCP, evidence receipts, and asset distribution. Treat real hardware as out of scope unless the user separately authorizes it.
Safety boundary
- Use the exact
rosclawCLI from the checkout's.venv/bin; report a stale global CLI before changing it. - Use a temporary
ROSCLAW_HOMEfor smoke tests and Hub operations. - Write raw trajectories, logs, receipts, and reports to an evidence directory outside the source checkout. Commit only reproducible code and tests.
- ROS graph discovery, subscription, and simulation are allowed. Never publish actuator commands directly, call a motion service, or send an action goal.
- Route any action request through
rosclawd request_action/ ROSClaw MCP so the daemon, sandbox, and firewall remain in the path. - Do not stop unrelated GPU processes or containers. Inspect available memory and choose the smallest useful workload.
- A dependency failure is a failure to diagnose and install around, not a passing skip. Keep unsupported real-robot checks explicitly out of scope.
Workflow
1. Establish provenance
Read the repository AGENTS.md and the task's verification document. Record:
git rev-parse HEAD
git status --short
nvidia-smi --query-gpu=index,name,memory.used,memory.free --format=csvFetch or compare upstream before claiming the checkout is current. Preserve all pre-existing user changes.
2. Validate the ROSClaw core
Prepend the repository environment to PATH, use a temporary home, and run
doctor, status, the deterministic demo, receipt explanation, and the universal
agent/MCP probe. Then run the repository test groups requested by the project
verification document.
Do not claim a simulator pass from import-only evidence. Require a physics step, a bounded task outcome, and a receipt or other machine-readable result.
3. Validate ROS 2 and Gazebo
Run scripts/verify_ros2.sh from this skill directory. It builds the Humble
rosbridge/turtlesim image, deploys the stack, discovers the live graph,
subscribes to pose, and proves direct velocity requests are blocked.
For Gazebo, run scripts/verify_gazebo.sh. Humble's recommended pairing is
Gazebo Fortress. The script now runs the Phase 3 GuardedBase world with real
diff-drive, odometry, laser, independent ROS bridges, and a deadman under
launch_testing. It injects actual process signals and requires bounded stop,
observation-loss fail-closed behavior, cancellation/recovery, and no old-action
replay. For the full MCP → rosclawd path and rosbridge-loss recovery, run:
rosclaw chaos run gazebo-guarded-base \
--faults agent-kill,rosbridge-loss,odom-stale,worker-crash \
--output-dir /an/external/evidence/directoryRaw evidence must remain outside the checkout. A /clock sample alone is not
enough to claim GuardedBase integration.
4. Validate Isaac Lab and four GPUs
Read references/verified-stack.md, then run
scripts/verify_isaaclab.sh. The script performs bounded single-GPU and
multi-GPU Cartpole training with Newton/MJWarp. Four visible devices must map
to four ranks, synchronize gradients, advance physics, and exit zero.
An Isaac Sim container that advances physics but aborts during shutdown is a partial pass with a lifecycle defect, not a clean pass.
Show full SKILL.md (476 more words)Show less
5. Validate G1 GoalForge
Use an external checkout of RoboNaldo's G1 deployment assets and keep all
episode trajectories outside ROSClaw. The backend must qualify the exact
29-joint Unitree hg order, ONNX shape, motion tensors, body hash, and prior
hash before physics starts.
Run the product surface from the checkout:
.venv/bin/python -m rosclaw.entrypoint simforge doctor g1-goalforge --all \
--output /evidence/doctor/goalforge-doctor.json
.venv/bin/python -m rosclaw.entrypoint simforge validate g1-goalforge \
--pairs 100 --output /an/external/recovery-100.json
.venv/bin/python -m rosclaw.entrypoint simforge validate g1-goalforge \
--profile nominal-success --workers 4 \
--output /an/external/nominal-success-30.json
.venv/bin/python -m rosclaw.entrypoint demo run g1-goalforge \
--target-zone random --failure-to-success --live-dashboard \
--output-dir /an/external/new/evidence/directory
.venv/bin/python -m rosclaw.entrypoint practice start \
--task g1_penalty_kick --generation 3 \
--output-dir /an/external/new/practice/directory
.venv/bin/python -m rosclaw.entrypoint evolution run \
--task g1_penalty_kick --generation 10 --gpus 0,1,2,3 \
--output-dir /an/external/new/evolution/directory
.venv/bin/python -m rosclaw.entrypoint chaos run g1-goalforge \
--faults agent-kill,worker-crash,dds-loss,state-stale \
--output-dir /an/external/new/chaos/directory
MUJOCO_GL=egl \
.venv/bin/python -m rosclaw.entrypoint evolution export \
/an/external/new/evidence/directory \
--format video \
--output /an/external/new/video/g1-goalforge.mp4The four-GPU screen is a prioritizer. Require a disjoint, balanced CPU MuJoCo label-agreement run before accepting its labels, preserve mismatches as counterexamples, and use CPU MuJoCo strict replay for final physical truth. Private Holdout case rows must not enter candidate generation or public output.
Build E5 proofs only from passing source reports, then independently replay their bundle hash and primitive causal/fault/replay fields:
.venv/bin/python -m rosclaw.entrypoint proof build g1-goalforge \
--demo /evidence/demo/goalforge-demo.json \
--recovery /evidence/recovery/recovery-100.json \
--flywheel /evidence/practice/goalforge-flywheel.json \
--memory /evidence/evolution/memory-ablation-100.json \
--four-gpu /evidence/evolution \
--agreement /evidence/evolution/cpu-gpu-label-agreement.json \
--continual /evidence/evolution/continual-g0-g10.json \
--chaos /evidence/chaos/goalforge-chaos.json \
--output-dir /evidence/proofs
.venv/bin/python -m rosclaw.entrypoint proof replay /evidence/proofs \
--modules body,provider,failure_router,sandbox,practice,memory,know,how,auto,darwin,registry,rosclawd
.venv/bin/python -m rosclaw.entrypoint promotion evaluate g1-goalforge \
--doctor /evidence/doctor/goalforge-doctor.json \
--recovery /evidence/recovery/recovery-100.json \
--flywheel /evidence/practice/goalforge-flywheel.json \
--four-gpu /evidence/evolution \
--continual /evidence/evolution/continual-g0-g10.json \
--chaos /evidence/chaos/goalforge-chaos.json \
--proofs /evidence/proofs \
--output /evidence/promotion-v4.jsonThe Promotion command requires a fresh simulation-only Doctor report. Treat a Doctor/Champion/Proof Body or kick-prior hash mismatch as a hard failure, and require all twelve GoalForge module proofs rather than only the four learning modules.
Unitree DDS tests must use loopback, a non-default isolated domain, canonical
rt/lowcmd and rt/lowstate, simulation-only permits, and
hardware_authorized=false. Never start a physical G1 transport.
GoalForge video export must consume strict-replay trajectory artifacts outside the checkout and write the MP4 and manifest outside the checkout. It is visualization-only: never use rendered pixels or subtitles as Promotion truth.
For success-rate optimization, use --profile nominal-success as the CPU
MuJoCo acceptance surface. Require all 30 balanced nominal cases, at least 95%
success, a gain of at least 30 percentage points over the fixed prior, 100%
safe selection, 100% independent verification, and 100% strict replay. Keep
the two-attempt runtime recovery budget separate from the at-most-32-candidate
offline simulation search. Do not generalize that result to moving balls,
randomized mass/friction/latency/noise/disturbance, or the 0.90 m target unless
those cases pass a separately declared validation profile.
6. Validate MCP
First probe ROSClaw's built-in MCP server and list its tools. For the community Isaac Sim MCP adapter, isolate installation, start its extension only in a simulator, perform an MCP initialize/list-tools/call-tool round trip, and state that it is community-maintained rather than an NVIDIA-official MCP.
Never expose execute_script or scene mutation tools to real hardware.
7. Validate Hub upload/download
Run scripts/verify_hub.sh. It uses the repository fixture key and an isolated
local HTTP registry to exercise validation, signature verification, login,
signed publish, catalog sync/search, remote dry-run download, install, list,
uninstall, and empty final state. Never reuse the fixture key for production.
8. Report the evidence ceiling
Separate PASS, PARTIAL, FAIL, and OUT OF SCOPE. Include exact commit,
versions, commands, exit codes, test counts, GPU mapping, and artifact paths.
The maximum claim must match the strongest verified evidence domain. Simulation
evidence can promote only from baseline to SIM and never proves real-robot safety.
Resources
scripts/verify_ros2.sh— live ROS 2/turtlesim safety loop.scripts/verify_gazebo.sh— Fortress diff-drive, odometry, laser, deadman, and reallaunch_testingprocess faults.scripts/verify_isaaclab.sh— bounded one- and multi-GPU Isaac Lab loop.scripts/verify_hub.sh— signed local Hub upload/download loop.references/verified-stack.md— tested versions, expected evidence, and known compatibility limits.
© 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
SKILL.md and 6 other files (scripts, references) in .agents/skills/rosclaw-simforge of ros-claw/rosclaw.
- SKILL.md
- agents/openai.yaml
- references/verified-stack.md
- scripts/verify_gazebo.sh
- scripts/verify_hub.sh
- scripts/verify_isaaclab.sh
- scripts/verify_ros2.sh
Open the folder on GitHubat commit 80c3efe
Compare with similar skills
ROSClaw SimForge Validator 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| ROSClaw SimForge Validator this skillros-claw/rosclaw | 221 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Agentacct Workflowmikehasa/agentacct | 766 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Hands On Testktnyt/cclsp | 675 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Diff-Driven Smoke TestsSkyvern-AI/skyvern | 23k | — | ~5.2k | Automated safety check: Pass | AGPL-3.0 | |
| Glance TestDebugBase/glance | 156 | — | ~827 | Automated safety check: Pass | MIT | |
| Codex Coding Pluginstyler-ai/ProjectAtlas | 441 | — | ~1.8k | Automated safety check: Pass | MIT |
Similar skills
Hands On Test
ktnyt/cclsp
Performs manual hands-on testing of a web application using playwright-cli.
Diff-Driven Smoke Tests
Skyvern-AI/skyvern
Reads your git diff, writes a handful of happy-path browser smoke tests, runs them with Skyvern or Chrome DevTools MCP and posts screenshot evidence to the PR.
Glance Test
DebugBase/glance
Run E2E browser tests on any web application using Glance MCP.
Codex Coding Plugin
styler-ai/ProjectAtlas
Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation…
Sage Wiki Integrate
xoai/sage-wiki
Pipeline skill that wires sage-wiki into an existing project — detects language, installs the client, runs a smoke test, and reports.
More from ros-claw/rosclaw
Rosclaw Embodied
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）
Related
Works with
Categories
Questions about ROSClaw SimForge Validator
What does ROSClaw SimForge Validator do?
Validates ROSClaw simulation workflows across MuJoCo, ROS 2, Gazebo and Isaac Sim with evidence-backed smoke tests, never touching a real robot. This skill validates the full ROSClaw software loop - CLI, safety gates, simulators, MCP, evidence receipts, and asset distribution - using the exact rosclaw CLI from the checkout's own virtual environment rather than a possibly stale global install. It treats real hardware as explicitly out of scope unless separately authorized, and routes any action request through the daemon's own request-action path or the ROSClaw MCP server so the sandbox and firewall stay in the loop; it never publishes actuator commands or calls a motion service directly.
When should I use ROSClaw SimForge Validator?
ROSClaw SimForge Validator fits situations like: smoke-testing a ROSClaw simulator integration without a real robot; validating ROS 2 and Gazebo stacks through ROSClaw's safety gates; producing an evidence-backed ROSClaw verification report.
How do I install ROSClaw SimForge Validator in Claude Code?
Run `npx skills add ros-claw/rosclaw --skill rosclaw-simforge -a claude-code`. Or copy the skill folder (.agents/skills/rosclaw-simforge in ros-claw/rosclaw) into .claude/skills/rosclaw-simforge in your project. Claude Code loads it when a task matches its description.
How do I install ROSClaw SimForge Validator in Codex?
Run `npx skills add ros-claw/rosclaw --skill rosclaw-simforge -a codex`. Or copy the skill folder (.agents/skills/rosclaw-simforge in ros-claw/rosclaw) into .agents/skills/rosclaw-simforge in your project. Codex loads it when a task matches its description.
Can I use ROSClaw SimForge Validator 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-simforge -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-simforge, .gemini/skills/rosclaw-simforge, .github/skills/rosclaw-simforge and .opencode/skills/rosclaw-simforge in your project.
What does ROSClaw SimForge Validator need to run?
Going by SKILL.md and its folder, ROSClaw SimForge Validator needs a shell for the scripts in its folder and the command-line tools its instructions call (python and git). Our summary lists: The rosclaw CLI from the project's own virtual environment; A GPU for Isaac Lab multi-GPU validation.
Does ROSClaw SimForge Validator access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is ROSClaw SimForge Validator 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does ROSClaw SimForge Validator use?
ROSClaw SimForge Validator 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 SimForge Validator use?
About 2.5k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.
What are the alternatives to ROSClaw SimForge Validator?
Skills that share tags, products or a category with ROSClaw SimForge Validator: Agentacct Workflow (mikehasa/agentacct, 766 stars), Hands On Test (ktnyt/cclsp, 675 stars), Diff-Driven Smoke Tests (Skyvern-AI/skyvern, 23k stars) and Glance Test (DebugBase/glance, 156 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains ROSClaw SimForge Validator?
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 9, 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.