[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CSREYP9SFMXRN8K5QSHV3K":3,"skill-same:01M7CSREYP9SFMXRN8K5QSHV3K":87},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7CSREYP9SFMXRN8K5QSHV3K","nemoclaw-user-manage-sandboxes",null,"Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw sandboxes, nemoclaw status, nemoclaw list, nemoclaw dashboard port, nemoclaw rebuild, nemoclaw upgrade sandboxes, nemoclaw uninstall, sandbox mutability, sandbox runtime configuration, sandbox rebuild, nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw messaging channels, nemoclaw telegram, nemoclaw discord, nemoclaw slack, nemoclaw wechat, nemoclaw whatsapp, openshell channel messaging, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"nemoclaw-user-manage-sandboxes\"\ndescription: \"Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw sandboxes, nemoclaw status, nemoclaw list, nemoclaw dashboard port, nemoclaw rebuild, nemoclaw upgrade sandboxes, nemoclaw uninstall, sandbox mutability, sandbox runtime configuration, sandbox rebuild, nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw messaging channels, nemoclaw telegram, nemoclaw discord, nemoclaw slack, nemoclaw wechat, nemoclaw whatsapp, openshell channel messaging, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.\"\nlicense: \"Apache-2.0\"\n---\n\n\u003C!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. -->\n\u003C!-- SPDX-License-Identifier: Apache-2.0 -->\n\n# Manage Sandbox Lifecycle\n\nUse this guide after you finish the OpenClaw quickstart (use the `nemoclaw-user-get-started` skill).\nIt covers day-two sandbox operations such as listing sandboxes, checking health, managing ports, rebuilding safely, upgrading, and uninstalling.\nWhen a workflow uses the lower-level OpenShell CLI, see CLI Selection Guide (use the `nemoclaw-user-reference` skill) for the boundary between `nemoclaw` and `openshell`.\n\n## List Sandboxes\n\nList every sandbox registered on this host:\n\n```console\n$ nemoclaw list\n```\n\nThe list shows each sandbox's model, provider, policy presets, active SSH session indicator, and dashboard URL when a dashboard port is recorded.\nUse JSON output for scripts:\n\n```console\n$ nemoclaw list --json\n```\n\n## Check Sandbox Health\n\nCheck a specific sandbox's health, inference route, active connections, live policy, update status, and messaging-channel overlap warnings:\n\n```console\n$ nemoclaw my-assistant status\n```\n\nUse the host-level status command when you want the sandbox inventory plus host auxiliary service state, such as cloudflared:\n\n```console\n$ nemoclaw status\n```\n\n## Inspect Logs\n\nView recent sandbox logs:\n\n```console\n$ nemoclaw my-assistant logs\n```\n\nStream logs while you reproduce a problem:\n\n```console\n$ nemoclaw my-assistant logs --follow\n```\n\nThe log command reads both OpenClaw gateway output and OpenShell audit events, so policy denials appear beside gateway logs.\n\n## Collect Diagnostics\n\nCollect diagnostics for bug reports or support handoff:\n\n```console\n$ nemoclaw debug --sandbox my-assistant --output nemoclaw-debug.tar.gz\n```\n\nUse `--quick` for a smaller local summary:\n\n```console\n$ nemoclaw debug --quick --sandbox my-assistant\n```\n\nThe debug command gathers system information, Docker state, gateway logs, and sandbox status.\n\n## Manage Dashboard Ports\n\nIf the forward stopped, or the installer reported that no active forward was found and the URL does not load, restart it manually with the port from the install summary.\n\n```console\n$ openshell forward start --background \u003Cdashboard-port> my-gpt-claw\n```\n\nTo list active forwards across all sandboxes, run the following command.\n\n```console\n$ openshell forward list\n```\n\n## Run Multiple Sandboxes\n\nEach sandbox needs its own dashboard port, since `openshell forward` refuses to bind a port that another sandbox is already using.\nWhen the default port is already held by another sandbox, `nemoclaw onboard` scans ports `18789` through `18799` and uses the next free port.\n\n```console\n$ nemoclaw onboard                                      # first sandbox uses 18789\n$ nemoclaw onboard                                      # second sandbox uses the next free port, such as 18790\n```\n\nTo choose a specific port, pass `--control-ui-port`:\n\n```console\n$ nemoclaw onboard --control-ui-port 19000\n```\n\nYou can also set `CHAT_UI_URL` or `NEMOCLAW_DASHBOARD_PORT` before onboarding:\n\n```console\n$ CHAT_UI_URL=http:\u002F\u002F127.0.0.1:19000 nemoclaw onboard\n$ NEMOCLAW_DASHBOARD_PORT=19000 nemoclaw onboard\n```\n\nFor full details on port conflicts and overrides, refer to Port already in use (use the `nemoclaw-user-reference` skill).\n\n## Reconfigure or Recover\n\nRecover from a misconfigured sandbox without re-running the full onboard wizard or destroying workspace state.\n\n### Change Inference Model or API\n\nChange the active model or provider at runtime without rebuilding the sandbox:\n\n```console\n$ nemoclaw inference set --model \u003Cmodel> --provider \u003Cprovider>\n```\n\nRefer to Switch Inference Providers (use the `nemoclaw-user-configure-inference` skill) for provider-specific model IDs and API compatibility notes.\n\n### Restart the Gateway and Port Forward\n\nIf `nemoclaw \u003Cname> status` reports the sandbox is alive but the gateway is not running, run the recover command instead of opening a shell.\n\n```console\n$ nemoclaw \u003Csandbox-name> recover\n```\n\nThe command restarts the in-sandbox gateway and re-establishes the dashboard port-forward in one step.\nIt is idempotent and safe to script.\nRefer to `nemoclaw \u003Cname> recover` (use the `nemoclaw-user-reference` skill) for details.\n\n### Reset a Stored Credential\n\nIf a provider credential was entered incorrectly during onboarding, clear the gateway-registered value and re-enter it on the next onboard run:\n\n```console\n$ nemoclaw credentials list                # see which providers are registered\n$ nemoclaw credentials reset \u003CPROVIDER>    # clear a single provider, for example nvidia-prod\n$ nemoclaw onboard                         # re-run to re-enter the cleared provider\n```\n\nThe credentials command is documented in full at `nemoclaw credentials reset \u003CPROVIDER>` (use the `nemoclaw-user-reference` skill).\n\n### Rebuild a Sandbox While Preserving Workspace State\n\nIf you changed the underlying Dockerfile, upgraded OpenClaw, or want to pick up a new base image without losing your sandbox's workspace files, use `rebuild` instead of destroying and recreating:\n\n```console\n$ nemoclaw \u003Csandbox-name> rebuild\n```\n\nRebuild preserves the mounted workspace and registered policies while recreating the container.\nIf NemoClaw cannot archive any requested state path, it reports the backup failure and stops before deleting the original sandbox.\nRefer to `nemoclaw \u003Cname> rebuild` (use the `nemoclaw-user-reference` skill) for flag details.\n\n### Add a Network Preset After Onboarding\n\nApply an additional preset, such as Telegram or GitHub, to a running sandbox without re-onboarding:\n\n```console\n$ nemoclaw \u003Csandbox-name> policy-add\n```\n\nRefer to `nemoclaw \u003Cname> policy-add` (use the `nemoclaw-user-reference` skill) for usage details and flags.\n\nNon-interactive re-onboards in the default `suggested` policy mode preserve presets added this way.\nTo make a re-onboard authoritative, set `NEMOCLAW_POLICY_MODE=custom` and provide `NEMOCLAW_POLICY_PRESETS` with the exact list to apply; onboarding removes anything else.\nSee `NEMOCLAW_POLICY_MODE` (use the `nemoclaw-user-reference` skill) for the full table.\n\n## Update to the Latest Version\n\nWhen a new NemoClaw release becomes available, update the `nemoclaw` CLI on your host and check existing sandboxes for stale agent\u002Fruntime versions.\n\n### Update the NemoClaw CLI\n\nRe-run the installer.\nBefore it onboards anything, the installer calls `nemoclaw backup-all` (use the `nemoclaw-user-reference` skill) automatically, storing a snapshot of each running sandbox in `~\u002F.nemoclaw\u002Frebuild-backups\u002F` as a safety net.\nIf your existing gateway is from OpenShell earlier than `0.0.37`, the installer prompts before it runs the new automatic gateway upgrade path.\nThe automatic path is offered only when the existing `nemoclaw` CLI supports `backup-all`; older installs must preserve sandbox state manually before retiring the gateway.\nFor unattended installs, set `NEMOCLAW_ACCEPT_EXPERIMENTAL_OPENSHELL_UPGRADE=1`, or manually run `nemoclaw backup-all` and `openshell gateway destroy -g nemoclaw || openshell gateway destroy` before rerunning the installer as `curl -fsSL https:\u002F\u002Fwww.nvidia.com\u002Fnemoclaw.sh | NEMOCLAW_OPENSHELL_UPGRADE_PREPARED=1 bash`.\n\n```console\n$ curl -fsSL https:\u002F\u002Fwww.nvidia.com\u002Fnemoclaw.sh | bash\n```\n\n### Upgrade Sandboxes with Stale Agent and Runtime Versions\n\nThe installer checks registered sandboxes after onboarding succeeds and runs `nemoclaw upgrade-sandboxes --auto` for stale running sandboxes.\nUse `upgrade-sandboxes` directly to verify the result, rebuild when you skipped the installer or onboarding step, or handle sandboxes that were stopped or could not be version-checked.\nThe upgrade flow is non-destructive by default because NemoClaw preserves manifest-defined workspace state, but a manual snapshot before any major upgrade gives you a state restore point.\n\n```console\n$ nemoclaw \u003Csandbox-name> snapshot create --name pre-upgrade   # optional, recommended\n$ nemoclaw update --yes                                        # updates CLI through the maintained installer flow\n$ nemoclaw upgrade-sandboxes --check                            # verify or list remaining stale\u002Funknown sandboxes\n$ nemoclaw upgrade-sandboxes                                    # manually rebuild remaining stale running sandboxes\n```\n\n`nemoclaw update` is the CLI wrapper around the same installer path as `curl -fsSL https:\u002F\u002Fwww.nvidia.com\u002Fnemoclaw.sh | bash`.\nUse `nemoclaw update --check` when you only want to inspect version state and see the maintained update command.\n\nFor scripted manual rebuilds, use `nemoclaw upgrade-sandboxes --auto` to skip the confirmation prompt.\n\nIf the upgraded sandbox needs its workspace state reverted, restore the pre-upgrade snapshot into the running sandbox.\nThis restores saved state directories only; it does not downgrade the sandbox image or agent\u002Fruntime:\n\n```console\n$ nemoclaw \u003Csandbox-name> snapshot restore pre-upgrade\n```\n\nLoad [references\u002Flifecycle-details.md](references\u002Flifecycle-details.md) for detailed steps on What Changes During a Rebuild.\n\n## Uninstall\n\nTo remove NemoClaw and all resources created during setup, run the CLI's built-in uninstall command:\n\n```bash\nnemoclaw uninstall\n```\n\n| Flag               | Effect                                               |\n|--------------------|------------------------------------------------------|\n| `--yes`            | Skip the confirmation prompt.                        |\n| `--keep-openshell` | Leave OpenShell binaries installed.                  |\n| `--delete-models`  | Also remove NemoClaw-pulled Ollama models.           |\n\n`nemoclaw uninstall` runs the version-pinned `uninstall.sh` that shipped with your installed CLI, so it does not fetch anything over the network at uninstall time.\n\nIf the `nemoclaw` CLI is missing or broken, fall back to the hosted script:\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002FNVIDIA\u002FNemoClaw\u002Frefs\u002Fheads\u002Fmain\u002Funinstall.sh | bash\n```\n\nThe same `--yes`, `--keep-openshell`, and `--delete-models` flags listed above also apply to the hosted script. Pass them after `bash -s --`.\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002FNVIDIA\u002FNemoClaw\u002Frefs\u002Fheads\u002Fmain\u002Funinstall.sh | bash -s -- --yes --delete-models\n```\n\nFor a full comparison of the two forms, including what they fetch, what they trust, and when to prefer each, see `nemoclaw uninstall` vs. the hosted `uninstall.sh` (use the `nemoclaw-user-reference` skill).\n\n## References\n\n- **[references\u002Fruntime-controls.md](references\u002Fruntime-controls.md)** — Single page that answers what can change at runtime versus what requires a rebuild for NemoClaw sandboxes.\n- **Load [references\u002Fbackup-restore.md](references\u002Fbackup-restore.md)** when downloading workspace files from a sandbox, uploading restored files into a new sandbox, or preserving sandbox state across rebuilds. Backs up and restores OpenClaw workspace files before destructive operations such as sandbox rebuilds.\n- **Load [references\u002Fmessaging-channels.md](references\u002Fmessaging-channels.md)** when setting up messaging channels, chat interfaces, or integrations without relying on nemoclaw tunnel start for bridges. Explains how Telegram, Discord, Slack, WeChat, and WhatsApp reach sandboxed OpenClaw and Hermes agents through OpenShell-managed processes and NemoClaw channel commands.\n- **Load [references\u002Fworkspace-files.md](references\u002Fworkspace-files.md)** when users ask about `SOUL.md`, `USER.md`, `IDENTITY.md`, `AGENTS.md`, or other workspace files, or when preparing to back up or restore workspace state. Explains what workspace personality and configuration files are, where they live, and how they persist across sandbox restarts.\n- **Load [references\u002Flifecycle-details.md](references\u002Flifecycle-details.md)** when you need detailed steps for What Changes During a Rebuild.\n\n## Related Skills\n\n- [Set Up Messaging Channels](references\u002Fmessaging-channels.md) to connect Telegram, Discord, or Slack.\n- [Workspace Files](references\u002Fworkspace-files.md) for persistent OpenClaw files inside the sandbox.\n- [Backup and Restore](references\u002Fbackup-restore.md) for snapshot and restore workflows.\n- `nemoclaw-user-monitor-sandbox` — Monitor Sandbox Activity (use the `nemoclaw-user-monitor-sandbox` skill) for observability tools\n","\u003C!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. -->\n\u003C!-- SPDX-License-Identifier: Apache-2.0 -->\n\n# Manage Sandbox Lifecycle\n\nUse this guide after you finish the OpenClaw quickstart (use the `nemoclaw-user-get-started` skill).\nIt covers day-two sandbox operations such as listing sandboxes, checking health, managing ports, rebuilding safely, upgrading, and uninstalling.\nWhen a workflow uses the lower-level OpenShell CLI, see CLI Selection Guide (use the `nemoclaw-user-reference` skill) for the boundary between `nemoclaw` and `openshell`.\n\n## List Sandboxes\n\nList every sandbox registered on this host:\n\n```console\n$ nemoclaw list\n```\n\nThe list shows each sandbox's model, provider, policy presets, active SSH session indicator, and dashboard URL when a dashboard port is recorded.\nUse JSON output for scripts:\n\n```console\n$ nemoclaw list --json\n```\n\n## Check Sandbox Health\n\nCheck a specific sandbox's health, inference route, active connections, live policy, update status, and messaging-channel overlap warnings:\n\n```console\n$ nemoclaw my-assistant status\n```\n\nUse the host-level status command when you want the sandbox inventory plus host auxiliary service state, such as cloudflared:\n\n```console\n$ nemoclaw status\n```\n\n## Inspect Logs\n\nView recent sandbox logs:\n\n```console\n$ nemoclaw my-assistant logs\n```\n\nStream logs while you reproduce a problem:\n\n```console\n$ nemoclaw my-assistant logs --follow\n```\n\nThe log command reads both OpenClaw gateway output and OpenShell audit events, so policy denials appear beside gateway logs.\n\n## Collect Diagnostics\n\nCollect diagnostics for bug reports or support handoff:\n\n```console\n$ nemoclaw debug --sandbox my-assistant --output nemoclaw-debug.tar.gz\n```\n\nUse `--quick` for a smaller local summary:\n\n```console\n$ nemoclaw debug --quick --sandbox my-assistant\n```\n\nThe debug command gathers system information, Docker state, gateway logs, and sandbox status.\n\n## Manage Dashboard Ports\n\nIf the forward stopped, or the installer reported that no active forward was found and the URL does not load, restart it manually with the port from the install summary.\n\n```console\n$ openshell forward start --background \u003Cdashboard-port> my-gpt-claw\n```\n\nTo list active forwards across all sandboxes, run the following command.\n\n```console\n$ openshell forward list\n```\n\n## Run Multiple Sandboxes\n\nEach sandbox needs its own dashboard port, since `openshell forward` refuses to bind a port that another sandbox is already using.\nWhen the default port is already held by another sandbox, `nemoclaw onboard` scans ports `18789` through `18799` and uses the next free port.\n\n```console\n$ nemoclaw onboard                                      # first sandbox uses 18789\n$ nemoclaw onboard                                      # second sandbox uses the next free port, such as 18790\n```\n\nTo choose a specific port, pass `--control-ui-port`:\n\n```console\n$ nemoclaw onboard --control-ui-port 19000\n```\n\nYou can also set `CHAT_UI_URL` or `NEMOCLAW_DASHBOARD_PORT` before onboarding:\n\n```console\n$ CHAT_UI_URL=http:\u002F\u002F127.0.0.1:19000 nemoclaw onboard\n$ NEMOCLAW_DASHBOARD_PORT=19000 nemoclaw onboard\n```\n\nFor full details on port conflicts and overrides, refer to Port already in use (use the `nemoclaw-user-reference` skill).\n\n## Reconfigure or Recover\n\nRecover from a misconfigured sandbox without re-running the full onboard wizard or destroying workspace state.\n\n### Change Inference Model or API\n\nChange the active model or provider at runtime without rebuilding the sandbox:\n\n```console\n$ nemoclaw inference set --model \u003Cmodel> --provider \u003Cprovider>\n```\n\nRefer to Switch Inference Providers (use the `nemoclaw-user-configure-inference` skill) for provider-specific model IDs and API compatibility notes.\n\n### Restart the Gateway and Port Forward\n\nIf `nemoclaw \u003Cname> status` reports the sandbox is alive but the gateway is not running, run the recover command instead of opening a shell.\n\n```console\n$ nemoclaw \u003Csandbox-name> recover\n```\n\nThe command restarts the in-sandbox gateway and re-establishes the dashboard port-forward in one step.\nIt is idempotent and safe to script.\nRefer to `nemoclaw \u003Cname> recover` (use the `nemoclaw-user-reference` skill) for details.\n\n### Reset a Stored Credential\n\nIf a provider credential was entered incorrectly during onboarding, clear the gateway-registered value and re-enter it on the next onboard run:\n\n```console\n$ nemoclaw credentials list                # see which providers are registered\n$ nemoclaw credentials reset \u003CPROVIDER>    # clear a single provider, for example nvidia-prod\n$ nemoclaw onboard                         # re-run to re-enter the cleared provider\n```\n\nThe credentials command is documented in full at `nemoclaw credentials reset \u003CPROVIDER>` (use the `nemoclaw-user-reference` skill).\n\n### Rebuild a Sandbox While Preserving Workspace State\n\nIf you changed the underlying Dockerfile, upgraded OpenClaw, or want to pick up a new base image without losing your sandbox's workspace files, use `rebuild` instead of destroying and recreating:\n\n```console\n$ nemoclaw \u003Csandbox-name> rebuild\n```\n\nRebuild preserves the mounted workspace and registered policies while recreating the container.\nIf NemoClaw cannot archive any requested state path, it reports the backup failure and stops before deleting the original sandbox.\nRefer to `nemoclaw \u003Cname> rebuild` (use the `nemoclaw-user-reference` skill) for flag details.\n\n### Add a Network Preset After Onboarding\n\nApply an additional preset, such as Telegram or GitHub, to a running sandbox without re-onboarding:\n\n```console\n$ nemoclaw \u003Csandbox-name> policy-add\n```\n\nRefer to `nemoclaw \u003Cname> policy-add` (use the `nemoclaw-user-reference` skill) for usage details and flags.\n\nNon-interactive re-onboards in the default `suggested` policy mode preserve presets added this way.\nTo make a re-onboard authoritative, set `NEMOCLAW_POLICY_MODE=custom` and provide `NEMOCLAW_POLICY_PRESETS` with the exact list to apply; onboarding removes anything else.\nSee `NEMOCLAW_POLICY_MODE` (use the `nemoclaw-user-reference` skill) for the full table.\n\n## Update to the Latest Version\n\nWhen a new NemoClaw release becomes available, update the `nemoclaw` CLI on your host and check existing sandboxes for stale agent\u002Fruntime versions.\n\n### Update the NemoClaw CLI\n\nRe-run the installer.\nBefore it onboards anything, the installer calls `nemoclaw backup-all` (use the `nemoclaw-user-reference` skill) automatically, storing a snapshot of each running sandbox in `~\u002F.nemoclaw\u002Frebuild-backups\u002F` as a safety net.\nIf your existing gateway is from OpenShell earlier than `0.0.37`, the installer prompts before it runs the new automatic gateway upgrade path.\nThe automatic path is offered only when the existing `nemoclaw` CLI supports `backup-all`; older installs must preserve sandbox state manually before retiring the gateway.\nFor unattended installs, set `NEMOCLAW_ACCEPT_EXPERIMENTAL_OPENSHELL_UPGRADE=1`, or manually run `nemoclaw backup-all` and `openshell gateway destroy -g nemoclaw || openshell gateway destroy` before rerunning the installer as `curl -fsSL https:\u002F\u002Fwww.nvidia.com\u002Fnemoclaw.sh | NEMOCLAW_OPENSHELL_UPGRADE_PREPARED=1 bash`.\n\n```console\n$ curl -fsSL https:\u002F\u002Fwww.nvidia.com\u002Fnemoclaw.sh | bash\n```\n\n### Upgrade Sandboxes with Stale Agent and Runtime Versions\n\nThe installer checks registered sandboxes after onboarding succeeds and runs `nemoclaw upgrade-sandboxes --auto` for stale running sandboxes.\nUse `upgrade-sandboxes` directly to verify the result, rebuild when you skipped the installer or onboarding step, or handle sandboxes that were stopped or could not be version-checked.\nThe upgrade flow is non-destructive by default because NemoClaw preserves manifest-defined workspace state, but a manual snapshot before any major upgrade gives you a state restore point.\n\n```console\n$ nemoclaw \u003Csandbox-name> snapshot create --name pre-upgrade   # optional, recommended\n$ nemoclaw update --yes                                        # updates CLI through the maintained installer flow\n$ nemoclaw upgrade-sandboxes --check                            # verify or list remaining stale\u002Funknown sandboxes\n$ nemoclaw upgrade-sandboxes                                    # manually rebuild remaining stale running sandboxes\n```\n\n`nemoclaw update` is the CLI wrapper around the same installer path as `curl -fsSL https:\u002F\u002Fwww.nvidia.com\u002Fnemoclaw.sh | bash`.\nUse `nemoclaw update --check` when you only want to inspect version state and see the maintained update command.\n\nFor scripted manual rebuilds, use `nemoclaw upgrade-sandboxes --auto` to skip the confirmation prompt.\n\nIf the upgraded sandbox needs its workspace state reverted, restore the pre-upgrade snapshot into the running sandbox.\nThis restores saved state directories only; it does not downgrade the sandbox image or agent\u002Fruntime:\n\n```console\n$ nemoclaw \u003Csandbox-name> snapshot restore pre-upgrade\n```\n\nLoad [references\u002Flifecycle-details.md](references\u002Flifecycle-details.md) for detailed steps on What Changes During a Rebuild.\n\n## Uninstall\n\nTo remove NemoClaw and all resources created during setup, run the CLI's built-in uninstall command:\n\n```bash\nnemoclaw uninstall\n```\n\n| Flag               | Effect                                               |\n|--------------------|------------------------------------------------------|\n| `--yes`            | Skip the confirmation prompt.                        |\n| `--keep-openshell` | Leave OpenShell binaries installed.                  |\n| `--delete-models`  | Also remove NemoClaw-pulled Ollama models.           |\n\n`nemoclaw uninstall` runs the version-pinned `uninstall.sh` that shipped with your installed CLI, so it does not fetch anything over the network at uninstall time.\n\nIf the `nemoclaw` CLI is missing or broken, fall back to the hosted script:\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002FNVIDIA\u002FNemoClaw\u002Frefs\u002Fheads\u002Fmain\u002Funinstall.sh | bash\n```\n\nThe same `--yes`, `--keep-openshell`, and `--delete-models` flags listed above also apply to the hosted script. Pass them after `bash -s --`.\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002FNVIDIA\u002FNemoClaw\u002Frefs\u002Fheads\u002Fmain\u002Funinstall.sh | bash -s -- --yes --delete-models\n```\n\nFor a full comparison of the two forms, including what they fetch, what they trust, and when to prefer each, see `nemoclaw uninstall` vs. the hosted `uninstall.sh` (use the `nemoclaw-user-reference` skill).\n\n## References\n\n- **[references\u002Fruntime-controls.md](references\u002Fruntime-controls.md)** — Single page that answers what can change at runtime versus what requires a rebuild for NemoClaw sandboxes.\n- **Load [references\u002Fbackup-restore.md](references\u002Fbackup-restore.md)** when downloading workspace files from a sandbox, uploading restored files into a new sandbox, or preserving sandbox state across rebuilds. Backs up and restores OpenClaw workspace files before destructive operations such as sandbox rebuilds.\n- **Load [references\u002Fmessaging-channels.md](references\u002Fmessaging-channels.md)** when setting up messaging channels, chat interfaces, or integrations without relying on nemoclaw tunnel start for bridges. Explains how Telegram, Discord, Slack, WeChat, and WhatsApp reach sandboxed OpenClaw and Hermes agents through OpenShell-managed processes and NemoClaw channel commands.\n- **Load [references\u002Fworkspace-files.md](references\u002Fworkspace-files.md)** when users ask about `SOUL.md`, `USER.md`, `IDENTITY.md`, `AGENTS.md`, or other workspace files, or when preparing to back up or restore workspace state. Explains what workspace personality and configuration files are, where they live, and how they persist across sandbox restarts.\n- **Load [references\u002Flifecycle-details.md](references\u002Flifecycle-details.md)** when you need detailed steps for What Changes During a Rebuild.\n\n## Related Skills\n\n- [Set Up Messaging Channels](references\u002Fmessaging-channels.md) to connect Telegram, Discord, or Slack.\n- [Workspace Files](references\u002Fworkspace-files.md) for persistent OpenClaw files inside the sandbox.\n- [Backup and Restore](references\u002Fbackup-restore.md) for snapshot and restore workflows.\n- `nemoclaw-user-monitor-sandbox` — Monitor Sandbox Activity (use the `nemoclaw-user-monitor-sandbox` skill) for observability tools\n",{"name":5,"license":15,"description":7},"main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill nemoclaw-user-manage-sandboxes",{"tool":39,"command":40},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill nemoclaw-user-manage-sandboxes",{"tool":42,"command":43},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill nemoclaw-user-manage-sandboxes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002FSKILL.md",true,[47,53,57,61,65,69,73,77,81],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"BENCHMARK.md","REFERENCE","参考文档",3326,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002FBENCHMARK.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"evals\u002Fevals.json",8569,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002Fevals\u002Fevals.json",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fbackup-restore.md",6826,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002Freferences\u002Fbackup-restore.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Flifecycle-details.md",2475,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002Freferences\u002Flifecycle-details.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fmessaging-channels.md",20285,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002Freferences\u002Fmessaging-channels.md",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fruntime-controls.md",4844,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002Freferences\u002Fruntime-controls.md",{"path":74,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fworkspace-files.md",4536,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002Freferences\u002Fworkspace-files.md",{"path":78,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":79,"sourceHtmlUrl":80},"skill-card.md",2761,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002Fskill-card.md",{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"skill.oms.sig","OTHER","其他",5829,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002Fskill.oms.sig",[88,96,103,110,117,124],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]