[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79FFZ2SZCPKAY655PFRZFY0":3,"skill-same:01M79FFZ2SZCPKAY655PFRZFY0":65},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M79FFZ2SZCPKAY655PFRZFY0","nemo-rl-brev-etiquette",null,"Brev instance operating guidance for NeMo-RL agents working in \u002Fhome\u002Fubuntu\u002FRL with limited workspace disk, a larger \u002Fephemeral volume, and optional \u002Fhome\u002Fubuntu\u002FRL\u002F.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.","Elogic360\u002Fsoftware-factory","Elogic360","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F156535519?v=4","01M74NH3F0RB13PWB7JZDE2V80","elogic360","01M74NH3FPC65082MDZVMFHDM3",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-rl-brev-etiquette\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nemo-rl-brev-etiquette\nlicense: Apache-2.0\ndescription: Brev instance operating guidance for NeMo-RL agents working in \u002Fhome\u002Fubuntu\u002FRL with limited workspace disk, a larger \u002Fephemeral volume, and optional \u002Fhome\u002Fubuntu\u002FRL\u002F.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.\nwhen_to_use: Running on a Brev instance; launching nemo-rl-auto-research campaigns or long jobs; managing large logs, checkpoints, caches, datasets, Ray temp files, W&B files, or Hugging Face auth on Brev.\n---\n\n# Brev Etiquette\n\nOperate as though `\u002Fhome\u002Fubuntu\u002FRL` is the source checkout and `\u002Fephemeral` is the working storage for generated experiment state. Keep the repo small, reproducible, and easy to inspect. Move bulky run outputs to `\u002Fephemeral` before launching anything expensive.\n\n## Storage Rules\n\n- Keep code edits, small config changes, committed experiment hypotheses, and concise reproducibility records under `\u002Fhome\u002Fubuntu\u002FRL`.\n- Put generated experiment assets under `\u002Fephemeral`, including checkpoints, run logs, Ray temp directories, W&B offline files, profiler traces, evaluation dumps, rollout samples, and per-experiment artifacts.\n- Keep reusable caches under one shared `\u002Fephemeral` cache root per user, not under each experiment. This includes Hugging Face models, dataset caches, PyTorch caches, Triton caches, `uv` caches, and pip caches.\n- Before a campaign or long run, check capacity with `df -h \u002Fhome\u002Fubuntu\u002FRL \u002Fephemeral` and avoid starting if `\u002Fephemeral` is missing or nearly full.\n- Create a campaign root such as `\u002Fephemeral\u002Fnemo-rl\u002F${USER:-ubuntu}\u002Fnemo-rl-auto-research\u002F\u003Ccampaign>` and use one subdirectory per experiment.\n- Do not leave large files, cache directories, or generated outputs in the git checkout. If a tool defaults to the repo, override its output\u002Fcache path before running it.\n\n## Environment Secrets\n\n- Treat `\u002Fhome\u002Fubuntu\u002FRL\u002F.env` as the local secret store. It may contain keys such as `WANDB_API_KEY`, `HF_TOKEN`, or `HUGGING_FACE_HUB_TOKEN`.\n- Before any run that may need external auth, load `\u002Fhome\u002Fubuntu\u002FRL\u002F.env` when it exists. Never print, `cat`, log, commit, or summarize secret values.\n- If `\u002Fhome\u002Fubuntu\u002FRL\u002F.env` is absent, or a required key is still unset after loading it, remind the user to add the needed key to that file before launching authenticated work.\n\n```bash\nif [ -f \u002Fhome\u002Fubuntu\u002FRL\u002F.env ]; then\n  set -a\n  . \u002Fhome\u002Fubuntu\u002FRL\u002F.env\n  set +a\nelse\n  echo \"Missing \u002Fhome\u002Fubuntu\u002FRL\u002F.env; add required keys such as WANDB_API_KEY or HF_TOKEN before authenticated runs.\"\nfi\n```\n\n## Auto-Research Pattern\n\nWhen using `nemo-rl-auto-research`, keep the git ledger in the repo and heavy evidence on `\u002Fephemeral`.\n\n```bash\nif [ -f \u002Fhome\u002Fubuntu\u002FRL\u002F.env ]; then\n  set -a\n  . \u002Fhome\u002Fubuntu\u002FRL\u002F.env\n  set +a\nfi\n\nBREV_ROOT=\u002Fephemeral\u002Fnemo-rl\u002F${USER:-ubuntu}\nCACHE_ROOT=$BREV_ROOT\u002Fcache\nCAMPAIGN_ROOT=$BREV_ROOT\u002Fnemo-rl-auto-research\u002F\u003Ccampaign>\nEXP_DIR=$CAMPAIGN_ROOT\u002F\u003Cexperiment>\nmkdir -p \"$EXP_DIR\"\u002F{logs,checkpoints,artifacts,ray,tmp,wandb}\nmkdir -p \"$CACHE_ROOT\"\u002F{huggingface,torch,triton,uv,pip,xdg,wandb}\n\nexport HF_HOME=$CACHE_ROOT\u002Fhuggingface\nexport HF_HUB_CACHE=$HF_HOME\u002Fhub\nexport HF_DATASETS_CACHE=$HF_HOME\u002Fdatasets\nexport TRANSFORMERS_CACHE=$HF_HOME\u002Ftransformers\nexport TORCH_HOME=$CACHE_ROOT\u002Ftorch\nexport TRITON_CACHE_DIR=$CACHE_ROOT\u002Ftriton\nexport UV_CACHE_DIR=$CACHE_ROOT\u002Fuv\nexport PIP_CACHE_DIR=$CACHE_ROOT\u002Fpip\nexport XDG_CACHE_HOME=$CACHE_ROOT\u002Fxdg\nexport WANDB_CACHE_DIR=$CACHE_ROOT\u002Fwandb\nexport RAY_TMPDIR=$EXP_DIR\u002Fray\nexport TMPDIR=$EXP_DIR\u002Ftmp\nexport WANDB_DIR=$EXP_DIR\u002Fwandb\n```\n\nRecord the absolute `\u002Fephemeral` paths in the nemo-rl-auto-research TSV fields for log path, checkpoint path, artifacts, shared cache root, and command. If the TSV itself may grow large, store the full TSV in `\u002Fephemeral` and keep a small pointer file or summary in the repo.\n\n## Launch Checklist\n\n- Inspect disk first: `df -h \u002Fhome\u002Fubuntu\u002FRL \u002Fephemeral`.\n- Choose a unique `\u002Fephemeral` run root before editing recipes or launching jobs.\n- Reuse a shared cache root such as `\u002Fephemeral\u002Fnemo-rl\u002F${USER:-ubuntu}\u002Fcache` across experiments unless a run explicitly requires a clean cache.\n- Override recipe output paths, logger paths, checkpoint paths, and temp paths to point under the experiment directory.\n- Override cache paths to point under the shared cache root.\n- Stream stdout\u002Fstderr to `$EXP_DIR\u002Flogs\u002Frun.log` or an equivalent file under `\u002Fephemeral`.\n- Periodically check disk during long runs with `df -h \u002Fephemeral` and stop gracefully if the volume is approaching exhaustion.\n- At the end, summarize the important metrics and paths in the repo ledger; do not copy bulky artifacts back into `\u002Fhome\u002Fubuntu\u002FRL`.\n\n## Cleanup\n\n- Clean only files that belong to the current campaign or experiment.\n- Prefer pruning clearly named experiment directories under `\u002Fephemeral\u002Fnemo-rl\u002F...`; never remove shared caches or another user's run directory without an explicit instruction.\n- Preserve enough small metadata in the repo to reproduce a result after `\u002Fephemeral` is cleaned.\n","# Brev Etiquette\n\nOperate as though `\u002Fhome\u002Fubuntu\u002FRL` is the source checkout and `\u002Fephemeral` is the working storage for generated experiment state. Keep the repo small, reproducible, and easy to inspect. Move bulky run outputs to `\u002Fephemeral` before launching anything expensive.\n\n## Storage Rules\n\n- Keep code edits, small config changes, committed experiment hypotheses, and concise reproducibility records under `\u002Fhome\u002Fubuntu\u002FRL`.\n- Put generated experiment assets under `\u002Fephemeral`, including checkpoints, run logs, Ray temp directories, W&B offline files, profiler traces, evaluation dumps, rollout samples, and per-experiment artifacts.\n- Keep reusable caches under one shared `\u002Fephemeral` cache root per user, not under each experiment. This includes Hugging Face models, dataset caches, PyTorch caches, Triton caches, `uv` caches, and pip caches.\n- Before a campaign or long run, check capacity with `df -h \u002Fhome\u002Fubuntu\u002FRL \u002Fephemeral` and avoid starting if `\u002Fephemeral` is missing or nearly full.\n- Create a campaign root such as `\u002Fephemeral\u002Fnemo-rl\u002F${USER:-ubuntu}\u002Fnemo-rl-auto-research\u002F\u003Ccampaign>` and use one subdirectory per experiment.\n- Do not leave large files, cache directories, or generated outputs in the git checkout. If a tool defaults to the repo, override its output\u002Fcache path before running it.\n\n## Environment Secrets\n\n- Treat `\u002Fhome\u002Fubuntu\u002FRL\u002F.env` as the local secret store. It may contain keys such as `WANDB_API_KEY`, `HF_TOKEN`, or `HUGGING_FACE_HUB_TOKEN`.\n- Before any run that may need external auth, load `\u002Fhome\u002Fubuntu\u002FRL\u002F.env` when it exists. Never print, `cat`, log, commit, or summarize secret values.\n- If `\u002Fhome\u002Fubuntu\u002FRL\u002F.env` is absent, or a required key is still unset after loading it, remind the user to add the needed key to that file before launching authenticated work.\n\n```bash\nif [ -f \u002Fhome\u002Fubuntu\u002FRL\u002F.env ]; then\n  set -a\n  . \u002Fhome\u002Fubuntu\u002FRL\u002F.env\n  set +a\nelse\n  echo \"Missing \u002Fhome\u002Fubuntu\u002FRL\u002F.env; add required keys such as WANDB_API_KEY or HF_TOKEN before authenticated runs.\"\nfi\n```\n\n## Auto-Research Pattern\n\nWhen using `nemo-rl-auto-research`, keep the git ledger in the repo and heavy evidence on `\u002Fephemeral`.\n\n```bash\nif [ -f \u002Fhome\u002Fubuntu\u002FRL\u002F.env ]; then\n  set -a\n  . \u002Fhome\u002Fubuntu\u002FRL\u002F.env\n  set +a\nfi\n\nBREV_ROOT=\u002Fephemeral\u002Fnemo-rl\u002F${USER:-ubuntu}\nCACHE_ROOT=$BREV_ROOT\u002Fcache\nCAMPAIGN_ROOT=$BREV_ROOT\u002Fnemo-rl-auto-research\u002F\u003Ccampaign>\nEXP_DIR=$CAMPAIGN_ROOT\u002F\u003Cexperiment>\nmkdir -p \"$EXP_DIR\"\u002F{logs,checkpoints,artifacts,ray,tmp,wandb}\nmkdir -p \"$CACHE_ROOT\"\u002F{huggingface,torch,triton,uv,pip,xdg,wandb}\n\nexport HF_HOME=$CACHE_ROOT\u002Fhuggingface\nexport HF_HUB_CACHE=$HF_HOME\u002Fhub\nexport HF_DATASETS_CACHE=$HF_HOME\u002Fdatasets\nexport TRANSFORMERS_CACHE=$HF_HOME\u002Ftransformers\nexport TORCH_HOME=$CACHE_ROOT\u002Ftorch\nexport TRITON_CACHE_DIR=$CACHE_ROOT\u002Ftriton\nexport UV_CACHE_DIR=$CACHE_ROOT\u002Fuv\nexport PIP_CACHE_DIR=$CACHE_ROOT\u002Fpip\nexport XDG_CACHE_HOME=$CACHE_ROOT\u002Fxdg\nexport WANDB_CACHE_DIR=$CACHE_ROOT\u002Fwandb\nexport RAY_TMPDIR=$EXP_DIR\u002Fray\nexport TMPDIR=$EXP_DIR\u002Ftmp\nexport WANDB_DIR=$EXP_DIR\u002Fwandb\n```\n\nRecord the absolute `\u002Fephemeral` paths in the nemo-rl-auto-research TSV fields for log path, checkpoint path, artifacts, shared cache root, and command. If the TSV itself may grow large, store the full TSV in `\u002Fephemeral` and keep a small pointer file or summary in the repo.\n\n## Launch Checklist\n\n- Inspect disk first: `df -h \u002Fhome\u002Fubuntu\u002FRL \u002Fephemeral`.\n- Choose a unique `\u002Fephemeral` run root before editing recipes or launching jobs.\n- Reuse a shared cache root such as `\u002Fephemeral\u002Fnemo-rl\u002F${USER:-ubuntu}\u002Fcache` across experiments unless a run explicitly requires a clean cache.\n- Override recipe output paths, logger paths, checkpoint paths, and temp paths to point under the experiment directory.\n- Override cache paths to point under the shared cache root.\n- Stream stdout\u002Fstderr to `$EXP_DIR\u002Flogs\u002Frun.log` or an equivalent file under `\u002Fephemeral`.\n- Periodically check disk during long runs with `df -h \u002Fephemeral` and stop gracefully if the volume is approaching exhaustion.\n- At the end, summarize the important metrics and paths in the repo ledger; do not copy bulky artifacts back into `\u002Fhome\u002Fubuntu\u002FRL`.\n\n## Cleanup\n\n- Clean only files that belong to the current campaign or experiment.\n- Prefer pruning clearly named experiment directories under `\u002Fephemeral\u002Fnemo-rl\u002F...`; never remove shared caches or another user's run directory without an explicit instruction.\n- Preserve enough small metadata in the repo to reproduce a result after `\u002Fephemeral` is cleaned.\n",{"name":5,"license":15,"description":7,"when_to_use":24},"Running on a Brev instance; launching nemo-rl-auto-research campaigns or long jobs; managing large logs, checkpoints, caches, datasets, Ray temp files, W&B files, or Hugging Face auth on Brev.","main","c475fc64e94e803b50d14a791dfee8853fbb2c5c","skills\u002Fnvidia\u002Fnemo-rl-brev-etiquette","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory","https:\u002F\u002Fgithub.com\u002FElogic360","2026-11-08 22:21:22",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Elogic360\u002Fsoftware-factory --skill nemo-rl-brev-etiquette",{"tool":37,"command":38},"bunx","bunx skills add Elogic360\u002Fsoftware-factory --skill nemo-rl-brev-etiquette",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Elogic360\u002Fsoftware-factory --skill nemo-rl-brev-etiquette","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-rl-brev-etiquette\u002FSKILL.md",true,[45,51,55,59],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"BENCHMARK.md","REFERENCE","参考文档",4260,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-rl-brev-etiquette\u002FBENCHMARK.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"evals\u002Fevals.json",2230,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-rl-brev-etiquette\u002Fevals\u002Fevals.json",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"skill-card.md",3842,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-rl-brev-etiquette\u002Fskill-card.md",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"skill.oms.sig","OTHER","其他",4593,"https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fnemo-rl-brev-etiquette\u002Fskill.oms.sig",[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M79G206MT3J6S0GY3C45P2KV","vss-summarize-video","Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-summarize-video\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M79G1WN63PGRE8CKD47WEBQ5","vss-setup-video-analytics-api","Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-video-analytics-api\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M79G1S9F7VY3EF6H53PRP5AN","vss-setup-behavior-analytics","Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-setup-behavior-analytics\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M79G1N1S1Y27PFZPYMNK1MTQ","vss-search-archive","Use this skill to run top-level VSS fusion search on archived video, or to ingest video files \u002F RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-search-archive\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M79G1H6WN0Q6C0VCAXCZX6B7","vss-query-analytics","Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-query-analytics\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M79G1DYPNXQS7QHZ0AAF5FX5","vss-manage-video-io-storage","Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add\u002Fdelete sensors and streams). Not for VLM inference or search.","https:\u002F\u002Fgithub.com\u002FElogic360\u002Fsoftware-factory\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-manage-video-io-storage\u002FSKILL.md",[],[]]