[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CSGFYJFTXJ7FPA352KAFKF":3,"skill-same:01M7CSGFYJFTXJ7FPA352KAFKF":76},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M7CSGFYJFTXJ7FPA352KAFKF","holoscan-install-conda",null,"Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container\u002Fwheel.","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\u002Fholoscan-install-conda\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: holoscan-install-conda\nversion: \"1.0.0\"\ndescription: \"Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container\u002Fwheel.\"\nlicense: Apache-2.0\nmetadata:\n  author: \"Holoscan Team \u003Choloscan-team@nvidia.com>\"\n  github-url: \"https:\u002F\u002Fgithub.com\u002Fnvidia-holoscan\u002Fholoscan-sdk\"\n  tags:\n    - holoscan\n    - install\n    - conda\n    - cuda\n---\n\n# Holoscan Conda Installation\n\n## Purpose\n\nInstall the Holoscan SDK (Python runtime and\u002For C++ dev headers) into a Conda environment on Linux x86_64, using conda-forge + rapidsai with a correctly pinned CUDA metapackage.\n\n## Prerequisites\n\n- Linux x86_64 with an NVIDIA GPU and CUDA 13 driver (check `nvidia-smi`).\n- `conda` (Miniforge preferred). Step 1 installs it if missing.\n- Network access to conda-forge, rapidsai, and `docs.nvidia.com`.\n\n## Limitations\n\n- **CUDA 13 only** (since v4.3.0 — earlier releases were CUDA 12). If the user has a CUDA 12 driver, redirect to `\u002Fholoscan-install-container` or `\u002Fholoscan-install-wheel` instead.\n- Linux x86_64 only — no aarch64\u002FiGPU support on conda-forge.\n- `ulimit -s 32768` is recommended in every shell that runs Holoscan — without it, some apps **may** segfault.\n\n## Step 0: Consult the Official Install Instructions\n\nAlways fetch the current Conda section of `https:\u002F\u002Fdocs.nvidia.com\u002Fholoscan\u002Fsdk-user-guide\u002Fsdk_installation.html` before installing — package names, channel selection, and the runtime\u002Fdev split can change between releases. Specifically extract:\n\n- The exact runtime package name (e.g. `holoscan` for Python bindings).\n- The C++ dev package name and whether the user needs it. As of v4.1.0, `libholoscan-dev` is a separate package containing headers and CMake config — install it whenever the user wants to develop C++ apps. Without it, `find_package(holoscan)` fails and there are no headers to `#include`.\n- Supported Python versions for the current release (3.10–3.13 for v4.3).\n- The current `cuda-version` pin (v4.3 → `13`).\n\n`rmm` and `ucxx` are distributed via the `rapidsai` channel; `holoscan`, `libholoscan`, and `libholoscan-dev` come from `conda-forge`.\n\nIf the doc disagrees with anything below, the doc wins — update the install commands accordingly and tell the user.\n\n## Step 1: Prerequisites Check\n\n```bash\nconda --version 2>&1\nnvidia-smi 2>&1 | head -5\n```\n\nIf `conda` is not found, install Miniforge silently (preferred over Miniconda for conda-forge):\n\n```bash\nwget -q https:\u002F\u002Fgithub.com\u002Fconda-forge\u002Fminiforge\u002Freleases\u002Flatest\u002Fdownload\u002FMiniforge3-Linux-x86_64.sh -O \u002Ftmp\u002FMiniforge3.sh\nbash \u002Ftmp\u002FMiniforge3.sh -b -p ~\u002Fminiforge3\nsource ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh\nconda --version\n```\n\nThe `-b` flag installs non-interactively without modifying `.bashrc`. Users must `source ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh` in each new shell (or add it to their shell RC file) to make `conda` available.\n\n## Step 2: Create Environment and Install\n\n### Package roles\n\n- `libholoscan` — C++ runtime symbols (`libholoscan_core.so`). Auto-pulled as a dependency.\n- `holoscan` — Python bindings.\n- `libholoscan-dev` — C++ headers, `libholoscan_core.so` symlink, and `holoscan-config.cmake` for `find_package(holoscan)`.\n- `rmm` — RAPIDS Memory Manager (rapidsai channel). Undeclared runtime dep of `holoscan`; `import holoscan` fails without it.\n- `ucxx` — UCX Python bindings (rapidsai channel), needed for distributed\u002Fmulti-process apps.\n- `cuda-version=13` — pins the CUDA 13 metapackage so the solver picks compatible CUDA runtime libs.\n\nCreate the environment first:\n\n```bash\nsource ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh   # if conda not yet on PATH\nconda create -n holoscan python=3.13 -y\nconda activate holoscan\n```\n\nThen pick one of the variants below based on the user's goal.\n\nPick the packages for the user's goal — Python-only needs `holoscan`, C++ dev needs `libholoscan-dev`, both works for combined use:\n\n```bash\nconda install \u003Cpackages> rmm ucxx cuda-version=13 -c rapidsai -c conda-forge -y\n```\n\nFor C++ development, also install the toolchain:\n\n```bash\nconda install -c conda-forge cxx-compiler cmake ninja -y\n```\n\nVerify Python installs with `python3 -c \"import holoscan; print(holoscan.__version__)\"`. Verify C++ dev installs with `ls \"$CONDA_PREFIX\u002Finclude\u002Fholoscan\"`.\n\n## Step 3: Run Python Tests\n\n`ulimit -s 32768` is recommended — without it, some Holoscan apps may segfault on startup.\n\n`video_replayer` is a display app that loops forever by default. Always patch its YAML to\nstop after 10 frames (`count: 10`, `repeat: false`, `realtime: false`) and to run headless\n(`headless: true`) — headless works with or without a display attached and avoids GUI\nfailure modes over SSH, so we don't branch on `$DISPLAY`.\n\nDownload scripts and YAML configs, patch the YAML, then run:\n\n```bash\nsource ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh\nconda activate holoscan\nulimit -s 32768\n\nSDK_VER=$(python3 -c \"import holoscan; print(holoscan.__version__)\")\nBASE=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fnvidia-holoscan\u002Fholoscan-sdk\u002Fv${SDK_VER}\u002Fexamples\"\n\ncurl -fsSL \"${BASE}\u002Fhello_world\u002Fpython\u002Fhello_world.py\"         -o \u002Ftmp\u002Fhs_hello_world.py\ncurl -fsSL \"${BASE}\u002Fvideo_replayer\u002Fpython\u002Fvideo_replayer.py\"   -o \u002Ftmp\u002Fhs_video_replayer.py\ncurl -fsSL \"${BASE}\u002Fvideo_replayer\u002Fpython\u002Fvideo_replayer.yaml\" -o \u002Ftmp\u002Fvideo_replayer.yaml\n\n# Patch video_replayer.yaml — 10 frames, headless.\npython3 -c \"\nc = open('\u002Ftmp\u002Fvideo_replayer.yaml').read()\nc = c.replace('count: 0', 'count: 10')\nc = c.replace('repeat: true', 'repeat: false')\nc = c.replace('realtime: true', 'realtime: false')\nc = c.replace('  width: 854', '  headless: true\\n  width: 854')\nopen('\u002Ftmp\u002Fvideo_replayer.yaml', 'w').write(c)\"\n\n# hello_world — no display, no data needed; expected: \"Hello World!\"\npython3 \u002Ftmp\u002Fhs_hello_world.py\n\n# video_replayer — needs racerx data; expected: frames rendered, \"Graph execution finished.\"\nHOLOSCAN_INPUT_PATH=\u002Fpath\u002Fto\u002Fholoscan\u002Fdata python3 \u002Ftmp\u002Fhs_video_replayer.py\n```\n\n`HOLOSCAN_INPUT_PATH` must point to the directory containing a `racerx\u002F` subdirectory.\nIf the user has the SDK source repo that is `~\u002Frepos\u002Fholoscan-sdk\u002Fdata`; otherwise download\nwith the `download_ngc_data` script from the Debian or source install tree.\n\n## Step 4: Remind the User\n\nThey must do the following in each new shell session:\n\n```bash\nsource ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh   # if Miniforge was installed with -b\nconda activate holoscan\nulimit -s 32768   # recommended — prevents segfaults in some apps\n```\n\nConsider adding these lines to `~\u002F.bashrc` or `~\u002F.zshrc` to avoid repeating them.\n\nThen offer next steps:\n- Explore C++ and Python examples at `https:\u002F\u002Fgithub.com\u002Fnvidia-holoscan\u002Fholoscan-sdk\u002Ftree\u002Fv\u003CVERSION>\u002Fexamples`\n- Walk through a specific example: `\u002Fexplain-example`\n- Start building a custom Holoscan application\n\n## Troubleshooting\n\n- **`ImportError: librmm.so: cannot open shared object file`.** `rmm` was not installed. Re-run the Step 2 `conda install` line — `rmm` is an undeclared runtime dependency of `holoscan`.\n- **Solver picks an older `holoscan` build than expected.** Channel order may be wrong. Use `-c rapidsai -c conda-forge` (rapidsai first) — that's the order in the official install command, and under strict channel priority a conda-forge-first ordering can lock the solver to an older `holoscan` build.\n- **Segmentation fault on app startup.** Set `ulimit -s 32768` in the current shell before running any Holoscan app. Not all apps trip this, but the larger stack avoids the failure mode.\n- **`find_package(holoscan)` fails when building C++ apps.** Install `libholoscan-dev` (headers + CMake config are in a separate package since v4.1.0).\n- **`conda: command not found` in a new shell.** Miniforge was installed with `-b` and did not patch `.bashrc`. Run `source ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh` or add it to your shell RC file.\n","# Holoscan Conda Installation\n\n## Purpose\n\nInstall the Holoscan SDK (Python runtime and\u002For C++ dev headers) into a Conda environment on Linux x86_64, using conda-forge + rapidsai with a correctly pinned CUDA metapackage.\n\n## Prerequisites\n\n- Linux x86_64 with an NVIDIA GPU and CUDA 13 driver (check `nvidia-smi`).\n- `conda` (Miniforge preferred). Step 1 installs it if missing.\n- Network access to conda-forge, rapidsai, and `docs.nvidia.com`.\n\n## Limitations\n\n- **CUDA 13 only** (since v4.3.0 — earlier releases were CUDA 12). If the user has a CUDA 12 driver, redirect to `\u002Fholoscan-install-container` or `\u002Fholoscan-install-wheel` instead.\n- Linux x86_64 only — no aarch64\u002FiGPU support on conda-forge.\n- `ulimit -s 32768` is recommended in every shell that runs Holoscan — without it, some apps **may** segfault.\n\n## Step 0: Consult the Official Install Instructions\n\nAlways fetch the current Conda section of `https:\u002F\u002Fdocs.nvidia.com\u002Fholoscan\u002Fsdk-user-guide\u002Fsdk_installation.html` before installing — package names, channel selection, and the runtime\u002Fdev split can change between releases. Specifically extract:\n\n- The exact runtime package name (e.g. `holoscan` for Python bindings).\n- The C++ dev package name and whether the user needs it. As of v4.1.0, `libholoscan-dev` is a separate package containing headers and CMake config — install it whenever the user wants to develop C++ apps. Without it, `find_package(holoscan)` fails and there are no headers to `#include`.\n- Supported Python versions for the current release (3.10–3.13 for v4.3).\n- The current `cuda-version` pin (v4.3 → `13`).\n\n`rmm` and `ucxx` are distributed via the `rapidsai` channel; `holoscan`, `libholoscan`, and `libholoscan-dev` come from `conda-forge`.\n\nIf the doc disagrees with anything below, the doc wins — update the install commands accordingly and tell the user.\n\n## Step 1: Prerequisites Check\n\n```bash\nconda --version 2>&1\nnvidia-smi 2>&1 | head -5\n```\n\nIf `conda` is not found, install Miniforge silently (preferred over Miniconda for conda-forge):\n\n```bash\nwget -q https:\u002F\u002Fgithub.com\u002Fconda-forge\u002Fminiforge\u002Freleases\u002Flatest\u002Fdownload\u002FMiniforge3-Linux-x86_64.sh -O \u002Ftmp\u002FMiniforge3.sh\nbash \u002Ftmp\u002FMiniforge3.sh -b -p ~\u002Fminiforge3\nsource ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh\nconda --version\n```\n\nThe `-b` flag installs non-interactively without modifying `.bashrc`. Users must `source ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh` in each new shell (or add it to their shell RC file) to make `conda` available.\n\n## Step 2: Create Environment and Install\n\n### Package roles\n\n- `libholoscan` — C++ runtime symbols (`libholoscan_core.so`). Auto-pulled as a dependency.\n- `holoscan` — Python bindings.\n- `libholoscan-dev` — C++ headers, `libholoscan_core.so` symlink, and `holoscan-config.cmake` for `find_package(holoscan)`.\n- `rmm` — RAPIDS Memory Manager (rapidsai channel). Undeclared runtime dep of `holoscan`; `import holoscan` fails without it.\n- `ucxx` — UCX Python bindings (rapidsai channel), needed for distributed\u002Fmulti-process apps.\n- `cuda-version=13` — pins the CUDA 13 metapackage so the solver picks compatible CUDA runtime libs.\n\nCreate the environment first:\n\n```bash\nsource ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh   # if conda not yet on PATH\nconda create -n holoscan python=3.13 -y\nconda activate holoscan\n```\n\nThen pick one of the variants below based on the user's goal.\n\nPick the packages for the user's goal — Python-only needs `holoscan`, C++ dev needs `libholoscan-dev`, both works for combined use:\n\n```bash\nconda install \u003Cpackages> rmm ucxx cuda-version=13 -c rapidsai -c conda-forge -y\n```\n\nFor C++ development, also install the toolchain:\n\n```bash\nconda install -c conda-forge cxx-compiler cmake ninja -y\n```\n\nVerify Python installs with `python3 -c \"import holoscan; print(holoscan.__version__)\"`. Verify C++ dev installs with `ls \"$CONDA_PREFIX\u002Finclude\u002Fholoscan\"`.\n\n## Step 3: Run Python Tests\n\n`ulimit -s 32768` is recommended — without it, some Holoscan apps may segfault on startup.\n\n`video_replayer` is a display app that loops forever by default. Always patch its YAML to\nstop after 10 frames (`count: 10`, `repeat: false`, `realtime: false`) and to run headless\n(`headless: true`) — headless works with or without a display attached and avoids GUI\nfailure modes over SSH, so we don't branch on `$DISPLAY`.\n\nDownload scripts and YAML configs, patch the YAML, then run:\n\n```bash\nsource ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh\nconda activate holoscan\nulimit -s 32768\n\nSDK_VER=$(python3 -c \"import holoscan; print(holoscan.__version__)\")\nBASE=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fnvidia-holoscan\u002Fholoscan-sdk\u002Fv${SDK_VER}\u002Fexamples\"\n\ncurl -fsSL \"${BASE}\u002Fhello_world\u002Fpython\u002Fhello_world.py\"         -o \u002Ftmp\u002Fhs_hello_world.py\ncurl -fsSL \"${BASE}\u002Fvideo_replayer\u002Fpython\u002Fvideo_replayer.py\"   -o \u002Ftmp\u002Fhs_video_replayer.py\ncurl -fsSL \"${BASE}\u002Fvideo_replayer\u002Fpython\u002Fvideo_replayer.yaml\" -o \u002Ftmp\u002Fvideo_replayer.yaml\n\n# Patch video_replayer.yaml — 10 frames, headless.\npython3 -c \"\nc = open('\u002Ftmp\u002Fvideo_replayer.yaml').read()\nc = c.replace('count: 0', 'count: 10')\nc = c.replace('repeat: true', 'repeat: false')\nc = c.replace('realtime: true', 'realtime: false')\nc = c.replace('  width: 854', '  headless: true\\n  width: 854')\nopen('\u002Ftmp\u002Fvideo_replayer.yaml', 'w').write(c)\"\n\n# hello_world — no display, no data needed; expected: \"Hello World!\"\npython3 \u002Ftmp\u002Fhs_hello_world.py\n\n# video_replayer — needs racerx data; expected: frames rendered, \"Graph execution finished.\"\nHOLOSCAN_INPUT_PATH=\u002Fpath\u002Fto\u002Fholoscan\u002Fdata python3 \u002Ftmp\u002Fhs_video_replayer.py\n```\n\n`HOLOSCAN_INPUT_PATH` must point to the directory containing a `racerx\u002F` subdirectory.\nIf the user has the SDK source repo that is `~\u002Frepos\u002Fholoscan-sdk\u002Fdata`; otherwise download\nwith the `download_ngc_data` script from the Debian or source install tree.\n\n## Step 4: Remind the User\n\nThey must do the following in each new shell session:\n\n```bash\nsource ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh   # if Miniforge was installed with -b\nconda activate holoscan\nulimit -s 32768   # recommended — prevents segfaults in some apps\n```\n\nConsider adding these lines to `~\u002F.bashrc` or `~\u002F.zshrc` to avoid repeating them.\n\nThen offer next steps:\n- Explore C++ and Python examples at `https:\u002F\u002Fgithub.com\u002Fnvidia-holoscan\u002Fholoscan-sdk\u002Ftree\u002Fv\u003CVERSION>\u002Fexamples`\n- Walk through a specific example: `\u002Fexplain-example`\n- Start building a custom Holoscan application\n\n## Troubleshooting\n\n- **`ImportError: librmm.so: cannot open shared object file`.** `rmm` was not installed. Re-run the Step 2 `conda install` line — `rmm` is an undeclared runtime dependency of `holoscan`.\n- **Solver picks an older `holoscan` build than expected.** Channel order may be wrong. Use `-c rapidsai -c conda-forge` (rapidsai first) — that's the order in the official install command, and under strict channel priority a conda-forge-first ordering can lock the solver to an older `holoscan` build.\n- **Segmentation fault on app startup.** Set `ulimit -s 32768` in the current shell before running any Holoscan app. Not all apps trip this, but the larger stack avoids the failure mode.\n- **`find_package(holoscan)` fails when building C++ apps.** Install `libholoscan-dev` (headers + CMake config are in a separate package since v4.1.0).\n- **`conda: command not found` in a new shell.** Miniforge was installed with `-b` and did not patch `.bashrc`. Run `source ~\u002Fminiforge3\u002Fetc\u002Fprofile.d\u002Fconda.sh` or add it to your shell RC file.\n",{"name":5,"license":15,"version":24,"metadata":25,"description":7},"1.0.0",{"tags":26,"author":31,"github-url":32},[27,28,29,30],"holoscan","install","conda","cuda","Holoscan Team \u003Choloscan-team@nvidia.com>","https:\u002F\u002Fgithub.com\u002Fnvidia-holoscan\u002Fholoscan-sdk","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fholoscan-install-conda",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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill holoscan-install-conda",{"tool":48,"command":49},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill holoscan-install-conda",{"tool":51,"command":52},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill holoscan-install-conda","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\u002Fholoscan-install-conda\u002FSKILL.md",true,[56,62,66,70],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"BENCHMARK.md","REFERENCE","参考文档",3931,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fholoscan-install-conda\u002FBENCHMARK.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"evals\u002Fevals.json",4693,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fholoscan-install-conda\u002Fevals\u002Fevals.json",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"skill-card.md",3709,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fholoscan-install-conda\u002Fskill-card.md",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"skill.oms.sig","OTHER","其他",4597,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fholoscan-install-conda\u002Fskill.oms.sig",[77,85,92,99,106,113],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"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",[],[]]