[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78DG45X3PAFS6VNDKFXQGYY":3,"skill-same:01M78DG45X3PAFS6VNDKFXQGYY":75},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M78DG45X3PAFS6VNDKFXQGYY","vss-ask-video",null,"Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.","Solizardking\u002Fskillhub-main","Solizardking","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108096810?v=4","01M786KDB10AYV042N0F9BD5B5","Clawd","01M786NYYXSZK1D05WM8JQPC48",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-ask-video\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vss-ask-video\ndescription: Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.\nlicense: Apache-2.0\nmetadata:\n  version: \"3.2.0\"\n  github-url: \"https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Fvideo-search-and-summarization\"\n  tags: \"nvidia blueprint operational\"\n---\n\n# Video QnA using VLM through VSS Agent\n\nUse this skill when you need details about the video which requires VLM to look at the video frames — for example the agent has **no** usable prior answer and needs a **fresh look at the pixels** for a specific clip.\n\n---\n\n## When to Use\n\n- The user asks **what happens in the video**, what **objects \u002F people \u002F actions** appear, **colors**, **timing**, **safety**, or other **visual facts** that require watching the clip.\n- The user asks for **details** that **cannot be answered** from existing messages, summaries, Elasticsearch\u002FMCP results, or filenames alone—you need **model inference on the video**.\n- Follow-up questions about **content details** after a coarse summary or after report generation.\n\nDo **not** use this skill when a **database \u002F MCP \u002F prior tool output** already answers the question, unless the user explicitly wants **verification** against the video.\n\n---\n\n## Deployment prerequisite\n\nThis skill requires a VSS profile that serves the `video_understanding` tool — typically **base** (recommended) or **lvs**. Before any request:\n\n1. Probe the VSS agent:\n   ```bash\n   curl -sf --max-time 5 \"http:\u002F\u002F${HOST_IP}:8000\u002Fdocs\" >\u002Fdev\u002Fnull\n   ```\n\n2. **If the probe fails**, ask the user:\n   > *\"No VSS profile is running on `$HOST_IP`. Shall I deploy `base` (recommended for per-clip VLM QnA) using the `\u002Fvss-deploy-profile` skill? If you prefer `lvs`, say so.\"*\n\n   - If yes → hand off to `\u002Fvss-deploy-profile -p base` (or `-p lvs` if the user prefers). Return here once it succeeds.\n   - If no → stop.\n\n3. If the probe passes, proceed.\n\n---\n\n## Sensor prerequisite\n\n**You MUST list VST sensors before any `\u002Fgenerate` call.** This is required even when the user names the sensor explicitly, even when the user asserts the video is already uploaded, and even when a previous turn appeared to use the same video. Do not skip this step.\n\n1. List sensors:\n   ```bash\n   curl -sf --max-time 5 \"http:\u002F\u002F${HOST_IP}:30888\u002Fvst\u002Fapi\u002Fv1\u002Fsensor\u002Flist\" | jq '.[].name'\n   ```\n\n2. Compare the returned `name` values against the user-supplied `\u003Csensor-id>` (or **filename stem**, e.g. `warehouse_safety_0001`).\n\n3. **If a matching sensor is present** → proceed to the Agent workflow below.\n\n4. **If no matching sensor is present** — upload the video first, then re-list to confirm the new sensor appears:\n   ```bash\n   # filename: must not contain whitespace\n   # timestamp: ISO 8601 UTC — default 2025-01-01T00:00:00.000Z if user did not specify\n   curl -s -X PUT \"http:\u002F\u002F${HOST_IP}:30888\u002Fvst\u002Fapi\u002Fv1\u002Fstorage\u002Ffile\u002F\u003Cfilename>?timestamp=\u003Ctimestamp>\" \\\n     -H \"Content-Type: application\u002Foctet-stream\" \\\n     -H \"Content-Length: \u003Cfile_size_in_bytes>\" \\\n     --upload-file \u002Fpath\u002Fto\u002F\u003Cfilename> | jq .\n   ```\n   See `\u002Fvss-manage-video-io-storage` for full upload semantics (v1 vs v2, conflict handling, delete flow). In interactive runs, confirm with the user before uploading. **Never** issue an unconditional PUT without first running the sensor-list check above — that is exactly the failure mode this prerequisite exists to prevent.\n\n---\n\n## Agent workflow\n\nThe Sensor prerequisite above must have already confirmed (or made) the sensor exist on VST. Then:\n\n1. **Clip** — Identify **sensor id**, **filename**, or **URL** for one video segment. If ambiguous, ask the user.\n2. Call vss agent with the sensor id and ask for it to call video_understanding tool to answer the user's question.\n3. Return the vss agent's answer back to the user.\n\n\n## Query VSS agent (`\u002Fgenerate`)\n\n```bash\n# Set from deployment (compose \u002F .env \u002F host where vss-agent listens)\nexport VSS_AGENT_BASE_URL=\"http:\u002F\u002Flocalhost:8000\"\n\ncurl -s -X POST \"${VSS_AGENT_BASE_URL}\u002Fgenerate\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"input_message\": \"Call video_understanding tool to answer the following question about \u003Csensor-id>: \u003Cuser query>\"}' | jq .\n```\n\n### Response contract and extraction\n\n`\u002Fgenerate` returns a JSON object with the assistant output in `value`, for example:\n\n```json\n{\"value\":\"\u003Cagent-think>\u003Cagent-think-step ...>...\u003C\u002Fagent-think-step>\u003C\u002Fagent-think>\\n\\n\u003Cfinal answer>\\n\\n\"}\n```\n\nThere is no separate clean-answer field. The consumable answer is the text in `.value` after removing any `\u003Cagent-think>...\u003C\u002Fagent-think>` block.\n\nRequired handling for this skill (and any downstream caller):\n\n1. Read `.value` from the JSON response.\n2. Strip `\u003Cagent-think>...\u003C\u002Fagent-think>` sections wherever they appear.\n3. Return only the remaining final-answer text to the user.\n\nExample extraction:\n\n```bash\ncurl -s -X POST \"${VSS_AGENT_BASE_URL}\u002Fgenerate\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"input_message\":\"Call video_understanding tool to answer the following question about \u003Csensor-id>: \u003Cuser query>\"}' \\\n| jq -r '.value' \\\n| python3 -c 'import re,sys; t=sys.stdin.read(); t=re.sub(r\"\u003Cagent-think>.*?\u003C\u002Fagent-think>\\s*\", \"\", t, flags=re.S); print(t.strip())'\n```\n\n---\n\n## Cross-Reference\n\n- **vss-manage-video-io-storage** — VST storage\u002Freplay URLs so **`VIDEO_URL`** is valid for the VLM.\n- **vss-generate-video-report** — timestamped **reports** via **Mode A (direct VLM)** or **Mode B (video-analytics incidents)**; this skill is **VSS-agent `\u002Fgenerate`** for ad-hoc **video Q&A**.\n","# Video QnA using VLM through VSS Agent\n\nUse this skill when you need details about the video which requires VLM to look at the video frames — for example the agent has **no** usable prior answer and needs a **fresh look at the pixels** for a specific clip.\n\n---\n\n## When to Use\n\n- The user asks **what happens in the video**, what **objects \u002F people \u002F actions** appear, **colors**, **timing**, **safety**, or other **visual facts** that require watching the clip.\n- The user asks for **details** that **cannot be answered** from existing messages, summaries, Elasticsearch\u002FMCP results, or filenames alone—you need **model inference on the video**.\n- Follow-up questions about **content details** after a coarse summary or after report generation.\n\nDo **not** use this skill when a **database \u002F MCP \u002F prior tool output** already answers the question, unless the user explicitly wants **verification** against the video.\n\n---\n\n## Deployment prerequisite\n\nThis skill requires a VSS profile that serves the `video_understanding` tool — typically **base** (recommended) or **lvs**. Before any request:\n\n1. Probe the VSS agent:\n   ```bash\n   curl -sf --max-time 5 \"http:\u002F\u002F${HOST_IP}:8000\u002Fdocs\" >\u002Fdev\u002Fnull\n   ```\n\n2. **If the probe fails**, ask the user:\n   > *\"No VSS profile is running on `$HOST_IP`. Shall I deploy `base` (recommended for per-clip VLM QnA) using the `\u002Fvss-deploy-profile` skill? If you prefer `lvs`, say so.\"*\n\n   - If yes → hand off to `\u002Fvss-deploy-profile -p base` (or `-p lvs` if the user prefers). Return here once it succeeds.\n   - If no → stop.\n\n3. If the probe passes, proceed.\n\n---\n\n## Sensor prerequisite\n\n**You MUST list VST sensors before any `\u002Fgenerate` call.** This is required even when the user names the sensor explicitly, even when the user asserts the video is already uploaded, and even when a previous turn appeared to use the same video. Do not skip this step.\n\n1. List sensors:\n   ```bash\n   curl -sf --max-time 5 \"http:\u002F\u002F${HOST_IP}:30888\u002Fvst\u002Fapi\u002Fv1\u002Fsensor\u002Flist\" | jq '.[].name'\n   ```\n\n2. Compare the returned `name` values against the user-supplied `\u003Csensor-id>` (or **filename stem**, e.g. `warehouse_safety_0001`).\n\n3. **If a matching sensor is present** → proceed to the Agent workflow below.\n\n4. **If no matching sensor is present** — upload the video first, then re-list to confirm the new sensor appears:\n   ```bash\n   # filename: must not contain whitespace\n   # timestamp: ISO 8601 UTC — default 2025-01-01T00:00:00.000Z if user did not specify\n   curl -s -X PUT \"http:\u002F\u002F${HOST_IP}:30888\u002Fvst\u002Fapi\u002Fv1\u002Fstorage\u002Ffile\u002F\u003Cfilename>?timestamp=\u003Ctimestamp>\" \\\n     -H \"Content-Type: application\u002Foctet-stream\" \\\n     -H \"Content-Length: \u003Cfile_size_in_bytes>\" \\\n     --upload-file \u002Fpath\u002Fto\u002F\u003Cfilename> | jq .\n   ```\n   See `\u002Fvss-manage-video-io-storage` for full upload semantics (v1 vs v2, conflict handling, delete flow). In interactive runs, confirm with the user before uploading. **Never** issue an unconditional PUT without first running the sensor-list check above — that is exactly the failure mode this prerequisite exists to prevent.\n\n---\n\n## Agent workflow\n\nThe Sensor prerequisite above must have already confirmed (or made) the sensor exist on VST. Then:\n\n1. **Clip** — Identify **sensor id**, **filename**, or **URL** for one video segment. If ambiguous, ask the user.\n2. Call vss agent with the sensor id and ask for it to call video_understanding tool to answer the user's question.\n3. Return the vss agent's answer back to the user.\n\n\n## Query VSS agent (`\u002Fgenerate`)\n\n```bash\n# Set from deployment (compose \u002F .env \u002F host where vss-agent listens)\nexport VSS_AGENT_BASE_URL=\"http:\u002F\u002Flocalhost:8000\"\n\ncurl -s -X POST \"${VSS_AGENT_BASE_URL}\u002Fgenerate\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"input_message\": \"Call video_understanding tool to answer the following question about \u003Csensor-id>: \u003Cuser query>\"}' | jq .\n```\n\n### Response contract and extraction\n\n`\u002Fgenerate` returns a JSON object with the assistant output in `value`, for example:\n\n```json\n{\"value\":\"\u003Cagent-think>\u003Cagent-think-step ...>...\u003C\u002Fagent-think-step>\u003C\u002Fagent-think>\\n\\n\u003Cfinal answer>\\n\\n\"}\n```\n\nThere is no separate clean-answer field. The consumable answer is the text in `.value` after removing any `\u003Cagent-think>...\u003C\u002Fagent-think>` block.\n\nRequired handling for this skill (and any downstream caller):\n\n1. Read `.value` from the JSON response.\n2. Strip `\u003Cagent-think>...\u003C\u002Fagent-think>` sections wherever they appear.\n3. Return only the remaining final-answer text to the user.\n\nExample extraction:\n\n```bash\ncurl -s -X POST \"${VSS_AGENT_BASE_URL}\u002Fgenerate\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"input_message\":\"Call video_understanding tool to answer the following question about \u003Csensor-id>: \u003Cuser query>\"}' \\\n| jq -r '.value' \\\n| python3 -c 'import re,sys; t=sys.stdin.read(); t=re.sub(r\"\u003Cagent-think>.*?\u003C\u002Fagent-think>\\s*\", \"\", t, flags=re.S); print(t.strip())'\n```\n\n---\n\n## Cross-Reference\n\n- **vss-manage-video-io-storage** — VST storage\u002Freplay URLs so **`VIDEO_URL`** is valid for the VLM.\n- **vss-generate-video-report** — timestamped **reports** via **Mode A (direct VLM)** or **Mode B (video-analytics incidents)**; this skill is **VSS-agent `\u002Fgenerate`** for ad-hoc **video Q&A**.\n",{"name":5,"license":15,"metadata":24,"description":7},{"tags":25,"version":26,"github-url":27},"nvidia blueprint operational","3.2.0","https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Fvideo-search-and-summarization","main","be3de0244dc1a57e323d8160787ebb40fb64930e","skills\u002Fnvidia\u002Fvss-ask-video","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main","https:\u002F\u002Fskills.x402.wtf","https:\u002F\u002Fgithub.com\u002FSolizardking","https:\u002F\u002Fmusebook.trade","Got a mile high and never came down","2026-10-08 23:20:13",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Solizardking\u002Fskillhub-main --skill vss-ask-video",{"tool":43,"command":44},"bunx","bunx skills add Solizardking\u002Fskillhub-main --skill vss-ask-video",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Solizardking\u002Fskillhub-main --skill vss-ask-video","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-ask-video\u002FSKILL.md",true,[51,57,61,65,69],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"BENCHMARK.md","REFERENCE","参考文档",4182,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-ask-video\u002FBENCHMARK.md",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002Fbase_profile_video_understanding.json",3960,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-ask-video\u002Fevals\u002Fbase_profile_video_understanding.json",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"evals\u002Fevals.json",422,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-ask-video\u002Fevals\u002Fevals.json",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"skill-card.md",3863,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-ask-video\u002Fskill-card.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"skill.oms.sig","OTHER","其他",4841,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Fvss-ask-video\u002Fskill.oms.sig",[76,84,91,98,105,113],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M78E0TGCAMNPS207BA3G07S7","zkrouter","Self-hosted OpenAI-compatible LLM router — smart tier-based routing, ZK-stamped routing decisions, mode overrides, free OpenRouter at install via the Birth bot. Save 60-80% on inference costs by routing to the cheapest capable model across 12+ OpenRouter models.","MIT","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzkrouter\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M78E0R1Z8BDT6EDTHY17MTNB","zk","For custom ZK Solana programs and privacy-preserving applications to prevent double spending. Guide to integrate rent-free nullifier PDAs for double-spend prevention.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M78E0P3ZTZ1YWF8MD5MM23QE","zk-omni-messaging","Zero-knowledge omnichain messaging between Robinhood Chain and Solana using CheshireZkOmniMessenger (msgType 4) with nullifier anti-replay and the zk-omni-relayer service.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk-omni-messaging\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M78E0JXZ2PNB1896VXAGDBWD","zerion-wallet-data","Use when the user asks to check a wallet's portfolio, token balances, DeFi positions, PnL, transaction history, or NFTs. Provides interpreted on-chain data across 40+ EVM chains and Solana via x402 pay-per-request or API key — no raw RPC decoding needed.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzerion-wallet-data\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M78E0G14FH9GRRTQYMKD5E59","youtube-clipper","YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\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":80,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M78E0C2ZYA99CFFDNB7ZMK5S","yield-optimization","Multi-chain yield optimization via yield.xyz (StakeKit). Discover 2,988+ yield opportunities across 75+ blockchains, build deposit\u002Fwithdrawal transactions with shell scripts, and sign them with a MoonPay wallet. Use when the user wants to earn yield, find the best lending or staking rate, enter\u002Fexit a position, or check portfolio balances.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyield-optimization\u002FSKILL.md",[],[]]