[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BK1XGSCG0FBD9PQMB4G73V":3,"skill-same:01M7BK1XGSCG0FBD9PQMB4G73V":80},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7BK1XGSCG0FBD9PQMB4G73V","nemoclaw-user-deploy-remote",null,"Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when deploying NemoClaw to a remote VM, onboarding a Brev instance, or migrating away from the legacy `nemoclaw deploy` wrapper. Trigger keywords - deploy nemoclaw remote gpu, nemoclaw brev cloud deployment, nemoclaw plugins, openclaw plugins, install openclaw plugin, nemoclaw onboard from dockerfile, nemoclaw brev web ui, nemoclaw getting started, brev quickstart, nvidia nemotron agent, nemoclaw sandbox hardening, container security, docker capabilities, process limits.","YYC-Cube\u002FYYC3-AI-Agent-Archive","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79K9J2WD44BBY4662XKNZRB",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fnemoclaw-user-deploy-remote\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"nemoclaw-user-deploy-remote\"\ndescription: \"Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when deploying NemoClaw to a remote VM, onboarding a Brev instance, or migrating away from the legacy `nemoclaw deploy` wrapper. Trigger keywords - deploy nemoclaw remote gpu, nemoclaw brev cloud deployment, nemoclaw plugins, openclaw plugins, install openclaw plugin, nemoclaw onboard from dockerfile, nemoclaw brev web ui, nemoclaw getting started, brev quickstart, nvidia nemotron agent, nemoclaw sandbox hardening, container security, docker capabilities, process limits.\"\ncategory: development-code\nversion: 1.0.0\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# Deploy NemoClaw to a Remote GPU Instance\n\n## Gotchas\n\n- The `nemoclaw deploy` command is deprecated.\n- On Brev, set `CHAT_UI_URL` in the launchable environment configuration so it is available when the installer builds the sandbox image.\n\n## Prerequisites\n\n- The [Brev CLI](https:\u002F\u002Fbrev.nvidia.com) installed and authenticated.\n- A provider credential for the inference backend you want to use during onboarding.\n- `HF_TOKEN` or `HUGGING_FACE_HUB_TOKEN` exported when your remote vLLM or Hugging Face workflow needs access to gated models.\n- NemoClaw installed locally if you plan to use the deprecated `nemoclaw deploy` wrapper. Otherwise, install NemoClaw directly on the remote host after provisioning it.\n\nRun NemoClaw on a remote GPU instance through [Brev](https:\u002F\u002Fbrev.nvidia.com).\nThe preferred path is to provision the VM, run the standard NemoClaw installer on that host, and then run `nemoclaw onboard`.\n\n## Quick Start\n\nIf your Brev instance is already up and has already been onboarded with a sandbox, start with the standard sandbox chat flow:\n\n```console\n$ nemoclaw my-assistant connect\n$ openclaw tui\n```\n\nThis gets you into the sandbox shell first and opens the OpenClaw chat UI right away.\nIf the VM is fresh, run the standard installer on that host and then run `nemoclaw onboard` before trying `nemoclaw my-assistant connect`.\n\nIf you are connecting from your local machine and still need to provision the remote VM, you can still use `nemoclaw deploy \u003Cinstance-name>` as the legacy compatibility path described below.\n\n## Deploy the Instance\n\n**Warning:**\n\nThe `nemoclaw deploy` command is deprecated.\nPrefer provisioning the remote host separately, then running the standard NemoClaw installer and `nemoclaw onboard` on that host.\n\nCreate a Brev instance and run the legacy compatibility flow:\n\n```console\n$ nemoclaw deploy \u003Cinstance-name>\n```\n\nReplace `\u003Cinstance-name>` with a name for your remote instance, for example `my-gpu-box`.\nThe sandbox created on the remote VM uses `NEMOCLAW_SANDBOX_NAME`, or `my-assistant` when the variable is unset.\nSandbox names must be lowercase, start with a letter, contain only letters, numbers, and internal hyphens, and end with a letter or number.\nThe deploy wrapper validates the sandbox name before it provisions the Brev instance, opens SSH, or starts the remote installer.\n\nThe legacy compatibility flow performs the following steps on the VM:\n\n1. Installs Docker and the NVIDIA Container Toolkit if a GPU is present.\n2. Installs the OpenShell CLI.\n3. Runs `nemoclaw onboard` (the setup wizard) to create the gateway, register providers, and launch the sandbox.\n4. Starts optional host auxiliary services (for example the cloudflared tunnel) when `cloudflared` is available. Channel messaging is configured during onboarding and runs through OpenShell-managed processes, not through `nemoclaw tunnel start`.\n\nBy default, the compatibility wrapper asks Brev to provision on `gcp`. Override this with `NEMOCLAW_BREV_PROVIDER` if you need a different Brev cloud provider.\nIf you export `HF_TOKEN` or `HUGGING_FACE_HUB_TOKEN`, the wrapper forwards those values to the VM so remote setup can pull gated Hugging Face model repositories.\n\n## Connect to the Remote Sandbox\n\nAfter deployment finishes, the deploy command opens an interactive shell inside the remote sandbox.\nTo reconnect after closing the session, run the command again:\n\n```console\n$ nemoclaw deploy \u003Cinstance-name>\n```\n\n## Monitor the Remote Sandbox\n\nSSH to the instance and run the OpenShell TUI to monitor activity and approve network requests:\n\n```console\n$ ssh \u003Cinstance-name> 'cd ~\u002Fnemoclaw && set -a && . .env && set +a && openshell term'\n```\n\n## Verify Inference\n\nRun a test agent prompt inside the remote sandbox:\n\n```console\n$ openclaw agent --agent main -m \"Hello from the remote sandbox\" --session-id test\n```\n\n## Remote Dashboard Access\n\nThe NemoClaw dashboard validates the browser origin against an allowlist baked\ninto the sandbox image at build time.  By default the allowlist only contains\n`http:\u002F\u002F127.0.0.1:18789`.  When accessing the dashboard from a remote browser\n(for example through a Brev public URL or an SSH port-forward), set\n`CHAT_UI_URL` to the origin the browser will use **before** running setup:\n\n```console\n$ export CHAT_UI_URL=\"https:\u002F\u002Fopenclaw0-\u003Cid>.brevlab.com\"\n$ nemoclaw deploy \u003Cinstance-name>\n```\n\nFor SSH port-forwarding, the origin is typically `http:\u002F\u002F127.0.0.1:18789` (the\ndefault), so no extra configuration is needed.\n\n**Warning:**\n\nOn Brev, set `CHAT_UI_URL` in the launchable environment configuration so it is\navailable when the installer builds the sandbox image. If `CHAT_UI_URL` is not\nset on a headless host, the compatibility wrapper prints a warning.\n\n`NEMOCLAW_DISABLE_DEVICE_AUTH` is also evaluated at image build time.\nWhen `CHAT_UI_URL` points at a non-loopback origin, NemoClaw disables OpenClaw device pairing in the generated sandbox configuration because browser-only remote users cannot complete terminal-based pairing.\nAny device that can reach the configured dashboard origin can connect without pairing, so avoid exposing that origin on internet-reachable or shared-network deployments.\n\n## First-Run Readiness Budget\n\nOn a remote GPU host, the first `nemoclaw onboard` typically does the slowest work of the lifecycle: the sandbox image is built locally and uploaded into the OpenShell gateway, which can stream hundreds of MiB over the VM's link before the readiness wait even starts.\nThe post-create readiness wait defaults to 180 seconds (`NEMOCLAW_SANDBOX_READY_TIMEOUT`), which is sized for warm-cache, workstation-class onboarding and can be exceeded on:\n\n- DGX Station first runs with large quantised models (70B+ parameter footprints, NVFP4 weights).\n- Cloud VMs where the local image-build cache is cold and the upload runs over the public network.\n- Hosts onboarding the Brave Web Search preset on the first run (the egress policy stack adds boot work).\n\nRaise the budget before re-running onboard:\n\n```console\n$ export NEMOCLAW_SANDBOX_READY_TIMEOUT=600\n$ nemoclaw onboard\n```\n\nIf onboard ends with `Sandbox '\u003Cname>' was created but did not become ready within 180s`, onboard deletes the partially-created sandbox first, so the next attempt with the raised budget starts from a clean state.\nFor the inference-probe budget that runs earlier in onboarding, see `NEMOCLAW_LOCAL_INFERENCE_TIMEOUT` (use the `nemoclaw-user-configure-inference` skill).\n\n## Proxy Configuration\n\nNemoClaw routes sandbox traffic through a gateway proxy that defaults to `10.200.0.1:3128`.\nIf your network requires a different proxy, set `NEMOCLAW_PROXY_HOST` and `NEMOCLAW_PROXY_PORT` before onboarding:\n\n```console\n$ export NEMOCLAW_PROXY_HOST=proxy.example.com\n$ export NEMOCLAW_PROXY_PORT=8080\n$ nemoclaw onboard\n```\n\nThese values are baked into the sandbox image at build time.\nThey are also forwarded into the runtime container during sandbox creation, so `\u002Ftmp\u002Fnemoclaw-proxy-env.sh` uses the same host and port that the image build used.\nOnly alphanumeric characters, dots, hyphens, and colons are accepted for the host.\nThe port must be numeric (0-65535).\nChanging the proxy after onboarding requires re-running `nemoclaw onboard`.\n\n## GPU Configuration\n\nThe deploy script uses the `NEMOCLAW_GPU` environment variable to select the GPU type.\nThe default value is `a2-highgpu-1g:nvidia-tesla-a100:1`.\nSet this variable before running `nemoclaw deploy` to use a different GPU configuration:\n\n```console\n$ export NEMOCLAW_GPU=\"a2-highgpu-1g:nvidia-tesla-a100:2\"\n$ nemoclaw deploy \u003Cinstance-name>\n```\n\n## References\n\n- **Load [references\u002Finstall-openclaw-plugins.md](references\u002Finstall-openclaw-plugins.md)** when users ask how to install, build, or configure OpenClaw plugins under NemoClaw. Explains the difference between OpenClaw plugins and agent skills, and shows the current Dockerfile-based workflow for baking a plugin into a NemoClaw sandbox.\n- **Load [references\u002Fbrev-web-ui.md](references\u002Fbrev-web-ui.md)** when a user wants to try NemoClaw without installing the CLI, or asks how to get started on Brev. Guides users through deploying NemoClaw with the Brev web UI.\n- **Load [references\u002Fsandbox-hardening.md](references\u002Fsandbox-hardening.md)** when reviewing sandbox image security controls, auditing capability drops, or looking up the runtime resource limits. Includes the sandbox container image hardening reference, covering Docker capabilities and process limits.\n\n## Related Skills\n\n- `nemoclaw-user-manage-sandboxes` — Set Up Messaging Channels (use the `nemoclaw-user-manage-sandboxes` skill) to connect Telegram, Discord, or Slack through OpenShell-managed channel messaging\n- `nemoclaw-user-monitor-sandbox` — Monitor Sandbox Activity (use the `nemoclaw-user-monitor-sandbox` skill) for sandbox monitoring tools\n- `nemoclaw-user-reference` — Commands (use the `nemoclaw-user-reference` skill) for the full `deploy` command reference\n","\u003C!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. -->\n\u003C!-- SPDX-License-Identifier: Apache-2.0 -->\n\n# Deploy NemoClaw to a Remote GPU Instance\n\n## Gotchas\n\n- The `nemoclaw deploy` command is deprecated.\n- On Brev, set `CHAT_UI_URL` in the launchable environment configuration so it is available when the installer builds the sandbox image.\n\n## Prerequisites\n\n- The [Brev CLI](https:\u002F\u002Fbrev.nvidia.com) installed and authenticated.\n- A provider credential for the inference backend you want to use during onboarding.\n- `HF_TOKEN` or `HUGGING_FACE_HUB_TOKEN` exported when your remote vLLM or Hugging Face workflow needs access to gated models.\n- NemoClaw installed locally if you plan to use the deprecated `nemoclaw deploy` wrapper. Otherwise, install NemoClaw directly on the remote host after provisioning it.\n\nRun NemoClaw on a remote GPU instance through [Brev](https:\u002F\u002Fbrev.nvidia.com).\nThe preferred path is to provision the VM, run the standard NemoClaw installer on that host, and then run `nemoclaw onboard`.\n\n## Quick Start\n\nIf your Brev instance is already up and has already been onboarded with a sandbox, start with the standard sandbox chat flow:\n\n```console\n$ nemoclaw my-assistant connect\n$ openclaw tui\n```\n\nThis gets you into the sandbox shell first and opens the OpenClaw chat UI right away.\nIf the VM is fresh, run the standard installer on that host and then run `nemoclaw onboard` before trying `nemoclaw my-assistant connect`.\n\nIf you are connecting from your local machine and still need to provision the remote VM, you can still use `nemoclaw deploy \u003Cinstance-name>` as the legacy compatibility path described below.\n\n## Deploy the Instance\n\n**Warning:**\n\nThe `nemoclaw deploy` command is deprecated.\nPrefer provisioning the remote host separately, then running the standard NemoClaw installer and `nemoclaw onboard` on that host.\n\nCreate a Brev instance and run the legacy compatibility flow:\n\n```console\n$ nemoclaw deploy \u003Cinstance-name>\n```\n\nReplace `\u003Cinstance-name>` with a name for your remote instance, for example `my-gpu-box`.\nThe sandbox created on the remote VM uses `NEMOCLAW_SANDBOX_NAME`, or `my-assistant` when the variable is unset.\nSandbox names must be lowercase, start with a letter, contain only letters, numbers, and internal hyphens, and end with a letter or number.\nThe deploy wrapper validates the sandbox name before it provisions the Brev instance, opens SSH, or starts the remote installer.\n\nThe legacy compatibility flow performs the following steps on the VM:\n\n1. Installs Docker and the NVIDIA Container Toolkit if a GPU is present.\n2. Installs the OpenShell CLI.\n3. Runs `nemoclaw onboard` (the setup wizard) to create the gateway, register providers, and launch the sandbox.\n4. Starts optional host auxiliary services (for example the cloudflared tunnel) when `cloudflared` is available. Channel messaging is configured during onboarding and runs through OpenShell-managed processes, not through `nemoclaw tunnel start`.\n\nBy default, the compatibility wrapper asks Brev to provision on `gcp`. Override this with `NEMOCLAW_BREV_PROVIDER` if you need a different Brev cloud provider.\nIf you export `HF_TOKEN` or `HUGGING_FACE_HUB_TOKEN`, the wrapper forwards those values to the VM so remote setup can pull gated Hugging Face model repositories.\n\n## Connect to the Remote Sandbox\n\nAfter deployment finishes, the deploy command opens an interactive shell inside the remote sandbox.\nTo reconnect after closing the session, run the command again:\n\n```console\n$ nemoclaw deploy \u003Cinstance-name>\n```\n\n## Monitor the Remote Sandbox\n\nSSH to the instance and run the OpenShell TUI to monitor activity and approve network requests:\n\n```console\n$ ssh \u003Cinstance-name> 'cd ~\u002Fnemoclaw && set -a && . .env && set +a && openshell term'\n```\n\n## Verify Inference\n\nRun a test agent prompt inside the remote sandbox:\n\n```console\n$ openclaw agent --agent main -m \"Hello from the remote sandbox\" --session-id test\n```\n\n## Remote Dashboard Access\n\nThe NemoClaw dashboard validates the browser origin against an allowlist baked\ninto the sandbox image at build time.  By default the allowlist only contains\n`http:\u002F\u002F127.0.0.1:18789`.  When accessing the dashboard from a remote browser\n(for example through a Brev public URL or an SSH port-forward), set\n`CHAT_UI_URL` to the origin the browser will use **before** running setup:\n\n```console\n$ export CHAT_UI_URL=\"https:\u002F\u002Fopenclaw0-\u003Cid>.brevlab.com\"\n$ nemoclaw deploy \u003Cinstance-name>\n```\n\nFor SSH port-forwarding, the origin is typically `http:\u002F\u002F127.0.0.1:18789` (the\ndefault), so no extra configuration is needed.\n\n**Warning:**\n\nOn Brev, set `CHAT_UI_URL` in the launchable environment configuration so it is\navailable when the installer builds the sandbox image. If `CHAT_UI_URL` is not\nset on a headless host, the compatibility wrapper prints a warning.\n\n`NEMOCLAW_DISABLE_DEVICE_AUTH` is also evaluated at image build time.\nWhen `CHAT_UI_URL` points at a non-loopback origin, NemoClaw disables OpenClaw device pairing in the generated sandbox configuration because browser-only remote users cannot complete terminal-based pairing.\nAny device that can reach the configured dashboard origin can connect without pairing, so avoid exposing that origin on internet-reachable or shared-network deployments.\n\n## First-Run Readiness Budget\n\nOn a remote GPU host, the first `nemoclaw onboard` typically does the slowest work of the lifecycle: the sandbox image is built locally and uploaded into the OpenShell gateway, which can stream hundreds of MiB over the VM's link before the readiness wait even starts.\nThe post-create readiness wait defaults to 180 seconds (`NEMOCLAW_SANDBOX_READY_TIMEOUT`), which is sized for warm-cache, workstation-class onboarding and can be exceeded on:\n\n- DGX Station first runs with large quantised models (70B+ parameter footprints, NVFP4 weights).\n- Cloud VMs where the local image-build cache is cold and the upload runs over the public network.\n- Hosts onboarding the Brave Web Search preset on the first run (the egress policy stack adds boot work).\n\nRaise the budget before re-running onboard:\n\n```console\n$ export NEMOCLAW_SANDBOX_READY_TIMEOUT=600\n$ nemoclaw onboard\n```\n\nIf onboard ends with `Sandbox '\u003Cname>' was created but did not become ready within 180s`, onboard deletes the partially-created sandbox first, so the next attempt with the raised budget starts from a clean state.\nFor the inference-probe budget that runs earlier in onboarding, see `NEMOCLAW_LOCAL_INFERENCE_TIMEOUT` (use the `nemoclaw-user-configure-inference` skill).\n\n## Proxy Configuration\n\nNemoClaw routes sandbox traffic through a gateway proxy that defaults to `10.200.0.1:3128`.\nIf your network requires a different proxy, set `NEMOCLAW_PROXY_HOST` and `NEMOCLAW_PROXY_PORT` before onboarding:\n\n```console\n$ export NEMOCLAW_PROXY_HOST=proxy.example.com\n$ export NEMOCLAW_PROXY_PORT=8080\n$ nemoclaw onboard\n```\n\nThese values are baked into the sandbox image at build time.\nThey are also forwarded into the runtime container during sandbox creation, so `\u002Ftmp\u002Fnemoclaw-proxy-env.sh` uses the same host and port that the image build used.\nOnly alphanumeric characters, dots, hyphens, and colons are accepted for the host.\nThe port must be numeric (0-65535).\nChanging the proxy after onboarding requires re-running `nemoclaw onboard`.\n\n## GPU Configuration\n\nThe deploy script uses the `NEMOCLAW_GPU` environment variable to select the GPU type.\nThe default value is `a2-highgpu-1g:nvidia-tesla-a100:1`.\nSet this variable before running `nemoclaw deploy` to use a different GPU configuration:\n\n```console\n$ export NEMOCLAW_GPU=\"a2-highgpu-1g:nvidia-tesla-a100:2\"\n$ nemoclaw deploy \u003Cinstance-name>\n```\n\n## References\n\n- **Load [references\u002Finstall-openclaw-plugins.md](references\u002Finstall-openclaw-plugins.md)** when users ask how to install, build, or configure OpenClaw plugins under NemoClaw. Explains the difference between OpenClaw plugins and agent skills, and shows the current Dockerfile-based workflow for baking a plugin into a NemoClaw sandbox.\n- **Load [references\u002Fbrev-web-ui.md](references\u002Fbrev-web-ui.md)** when a user wants to try NemoClaw without installing the CLI, or asks how to get started on Brev. Guides users through deploying NemoClaw with the Brev web UI.\n- **Load [references\u002Fsandbox-hardening.md](references\u002Fsandbox-hardening.md)** when reviewing sandbox image security controls, auditing capability drops, or looking up the runtime resource limits. Includes the sandbox container image hardening reference, covering Docker capabilities and process limits.\n\n## Related Skills\n\n- `nemoclaw-user-manage-sandboxes` — Set Up Messaging Channels (use the `nemoclaw-user-manage-sandboxes` skill) to connect Telegram, Discord, or Slack through OpenShell-managed channel messaging\n- `nemoclaw-user-monitor-sandbox` — Monitor Sandbox Activity (use the `nemoclaw-user-monitor-sandbox` skill) for sandbox monitoring tools\n- `nemoclaw-user-reference` — Commands (use the `nemoclaw-user-reference` skill) for the full `deploy` command reference\n",{"name":5,"license":15,"version":24,"category":25,"description":7},"1.0.0","development-code","main","d591030ef9fb1bbcebed3454aa5c2dcb8d608f69","skills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fnemoclaw-user-deploy-remote","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive","https:\u002F\u002Fai-agent.yyc3.vip\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-13 22:26:14",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill nemoclaw-user-deploy-remote",{"tool":40,"command":41},"bunx","bunx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill nemoclaw-user-deploy-remote",{"tool":43,"command":44},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill nemoclaw-user-deploy-remote","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fnemoclaw-user-deploy-remote\u002FSKILL.md",true,[48,54,58,62,66,70,74],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"BENCHMARK.md","REFERENCE","参考文档",3411,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fnemoclaw-user-deploy-remote\u002FBENCHMARK.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"evals\u002Fevals.json",6845,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fnemoclaw-user-deploy-remote\u002Fevals\u002Fevals.json",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fbrev-web-ui.md",5951,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fnemoclaw-user-deploy-remote\u002Freferences\u002Fbrev-web-ui.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Finstall-openclaw-plugins.md",3314,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fnemoclaw-user-deploy-remote\u002Freferences\u002Finstall-openclaw-plugins.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fsandbox-hardening.md",5049,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fnemoclaw-user-deploy-remote\u002Freferences\u002Fsandbox-hardening.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"skill-card.md",2535,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fnemoclaw-user-deploy-remote\u002Fskill-card.md",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"skill.oms.sig","OTHER","其他",5341,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fnemoclaw-user-deploy-remote\u002Fskill.oms.sig",[81,89,96,103,110,118],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7BTB92RE8MT5YE706QBNDTQ","yingmi-skill","当用户需要查询基金、策略、公告、财经资讯，做资产配置、组合诊断、风险回测、现金流分析，或生成图表、PDF 时，优先使用本 Skill 获取真实数据与可执行能力。","MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fyingmi-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7BT7ZYR091HPJYEFNWVTEJJ","web-access","所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fweb-access\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":85,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7BT4NKS0DNP8A53M1BGGZR2","tencentmap-map-assistant","腾讯位置服务·地图助手 Skill，一句自然语言调用腾讯地图全套能力，无需开发者账号、开箱即用。提供 AI 旅游攻略、地点搜索（含评分\u002F人均\u002F营业时间）、关键词提示、路线规划（驾车\u002F步行\u002F公交\u002F骑行）、地址解析与逆解析、行政区划、IP 定位、距离计算、天气查询，并可将行程或多 POI 渲染成网页地图。涉及找地点、规划路线、旅游行程、查天气、坐标转换等出行场景时使用。","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Ftencentmap-map-assistant\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":85,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M7BSWKV1T5XYYRGV4W4JP88C","skill-scanner","Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描, 检查 skill 安全, audit skill, scan skill, check skill safety, analyze skill, inspect skill, verify skill, skill security, skill supply chain. Do NOT trigger for general agent usage, full system health checks, project debugging, or normal development.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-scanner\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":15,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":19},"01M7BSWGTCFW7F123S4BM4XY6W","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized knowledge, workflows, or tool integrations.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":19},"01M7BSVV4DH8JK2ZMQSCW25VCD","shader-dev","Comprehensive GLSL shader techniques for creating stunning visual effects — ray marching, SDF modeling, fluid simulation, particle systems, procedural generation, lighting, post-processing, and more.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fshader-dev\u002FSKILL.md",[],[]]