[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PMH79Z2XMXYSVCY59TAGJE":3,"skill-same:01M6PMH79Z2XMXYSVCY59TAGJE":136},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":14,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6PMH79Z2XMXYSVCY59TAGJE","vss-summarize-video",null,"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.","headmktlucca-ui\u002Fneuroads-lp","headmktlucca-ui","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F247379838?v=4","01M6PDVAV6M1W96D1SR1PDF8CS","NeuroAds","01M6PDVAZ4P281GNDKD45CYTF5",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"vss summarize video","Video","summarize","summarization","captioning","for","with","LVS","via","live","generation","gated","fallback","Blueprint","use","team","NVIDIA","microservice","search","github","2026-11-10 10:12:30",false,"---\nname: vss-summarize-video\ndescription: 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.\nlicense: Apache-2.0\nmetadata:\n  version: \"3.2.0\"\n  author: \"NVIDIA Video Search and Summarization team\"\n  github-url: \"https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Fvideo-search-and-summarization\"\n  tags: \"nvidia blueprint operational\"\n---\n## Instructions\n\nFollow the routing tables and step-by-step workflows below. Each section that ends in *workflow*, *quick start*, or *flow* is intended to be executed top-to-bottom. Detailed reference material lives in `references\u002F`.\n\n## Examples\n\nWorked end-to-end examples are kept under `evals\u002F` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow `curl` blocks below. Run a Tier-3 evaluation with `nv-base validate \u003Cthis-skill-dir> --agent-eval` to replay them.\n\nCall the VLM NIM or the video summarization microservice **directly**.\nAlways run `curl` commands yourself; never instruct the user to run them.\n\nPrimary video workflow query type: **\"Summarize this video.\"** Direct video summarization API\nand service-ops requests are handled by the reference-routed sections below.\n\n## Purpose\n\nProduce a single, polished narrative summary of one recorded video clip, with\ntimestamped events when the LVS microservice path is reachable.\n\n**Do NOT use this skill for:**\n- Live RTSP captioning — use `vss-deploy-dense-captioning`.\n- Report generation, including incident or alert-window reports — use `vss-generate-video-report` Mode B.\n- Semantic search across the archive — use `vss-search-archive`.\n\n## Prerequisites\n\n- VSS `lvs` profile running on `$HOST_IP` (port 38111) OR a reachable\n  VLM\u002FRT-VLM endpoint as a fallback. The `vss-deploy-profile` skill brings\n  these up.\n- Network reachability from the agent host to both endpoints; clip URLs from\n  VIOS must be fetchable by the chosen backend.\n- `jq` and `curl` available on the agent host.\n\n## Limitations\n\n- Direct VLM fallback uses a single fixed prompt and cannot target\n  scenario\u002Fevents — output quality is lower than the LVS path.\n- Remote VLM endpoints generally cannot reach `localhost`\u002Fprivate clip URLs.\n- One backend call per request; no parallel hedging or multi-pass summaries.\n\n## Troubleshooting\n\n| Symptom | Cause | Fix |\n|---|---|---|\n| `\u002Fv1\u002Fready` returns 503 repeatedly | LVS service still warming up | Retry up to ~30 s as shown in *Setup*; if it never returns 200 the service may not be deployed |\n| Empty `video_summary` and `events` | Clip does not contain the requested events | Re-run with broader `scenario` or different `events` |\n| VLM returns `\u003Cthink>` block | Cosmos Reason 2 reasoning mode | Strip everything up to `\u003C\u002Fthink>` before rendering |\n| Empty stdout from `curl \u002Fv1\u002Fready` | Service legitimately returns 200 with empty body | Always check HTTP status with `-o \u002Fdev\u002Fnull -w '%{http_code}'`, never inspect the body |\n\nSee [`references\u002Fvideo-summarization-debugging.md`](references\u002Fvideo-summarization-debugging.md) for deeper diagnostics.\n\n## Reference Map\n\nUse these references only when the user asks for the relevant detail, or when\nthe core workflow below needs deeper video summarization information:\n\n- **video summarization API details**: [`references\u002Fvideo-summarization-api.md`](references\u002Fvideo-summarization-api.md) for\n  `\u002Fv1\u002Fsummarize`, `\u002Fsummarize`, `\u002Fv1\u002Fgenerate_captions`,\n  `\u002Fv1\u002Fstream_summarize`, health probes, `\u002Fmodels`, `\u002Frecommended_config`,\n  `\u002Fmetrics`, request fields, response shapes, and API gotchas.\n- **video summarization service configuration and ops**:\n  [`references\u002Fvideo-summarization-deployment.md`](references\u002Fvideo-summarization-deployment.md) for\n  the VSS `lvs` profile, ports, required env vars, logs, status, dry-runs,\n  teardown, model\u002Fbackend swaps, Elasticsearch\u002FNeo4j\u002FArangoDB backend\n  selection, and service-level troubleshooting.\n- **Extended video summarization ops references**:\n  [`references\u002Fvideo-summarization-environment-variables.md`](references\u002Fvideo-summarization-environment-variables.md),\n  [`references\u002Fvideo-summarization-debugging.md`](references\u002Fvideo-summarization-debugging.md), and\n  `assets\u002Fvideo-summarization.env.example`.\n\nLoad `video-summarization-api.md` only when you need a request field, response shape, or\nendpoint that is not already covered by the Step 2 LVS or fallback VLM\nexample below, or when handling a direct video summarization API\nrequest. Load `video-summarization-deployment.md` only for deployment,\nconfiguration, or service operations.\n\n## Video Summarization API And Service Ops Requests\n\nIf the user asks to call or debug video summarization endpoints directly, answer from\n[`references\u002Fvideo-summarization-api.md`](references\u002Fvideo-summarization-api.md) instead of running the\nend-to-end video summarization workflow. Examples: list video summarization models, check\nreadiness, get recommended chunking config, inspect metrics, explain a 422\nresponse, or build a `\u002Fv1\u002Fsummarize` request body.\n\nIf the user asks to configure, deploy, restart, tear down, or troubleshoot the\nvideo summarization service, prefer the `vss-deploy-profile` skill for full VSS profile\ndeployment and use [`references\u002Fvideo-summarization-deployment.md`](references\u002Fvideo-summarization-deployment.md)\nfor video summarization-specific service details.\n\n## Routing\n\nDecide purely from video summarization service availability (probed in\n*Setup → Availability checks* below). **Duration does not drive routing.**\n\n| `\u002Fv1\u002Fready` | Backend | Endpoint |\n|---|---|---|\n| HTTP 200 | LVS microservice with HITL | `POST ${LVS_BACKEND_URL}\u002Fv1\u002Fsummarize` |\n| Anything else | VLM \u002F RT-VLM with the default prompt + fallback note | `POST ${VLM_BASE_URL}\u002Fv1\u002Fchat\u002Fcompletions` |\n\nFallback message when the LVS service is unreachable — copy verbatim above the summary:\n\n> ⚠ **Note:** Input video `\u003Cname>` is `\u003CN>`s long.\n> The video summarization service is not deployed, so this summary was\n> produced by the VLM alone with a generic default prompt. Deploy the\n> `lvs` profile for higher-quality summaries with scenario\u002Fevents\n> targeting.\n\n## Deployment prerequisite\n\nThe VSS **lvs** profile on `$HOST_IP` is the primary backend. If the\n`\u002Fv1\u002Fready` probe (see *Setup → Availability checks*) returns anything\nother than 200 after the warmup retries, ask the user:\n\n> *\"The VSS `lvs` profile isn't running on `$HOST_IP`. Shall I deploy it now using the `\u002Fvss-deploy-profile` skill with `-p lvs`? Reply `no` to summarize with the VLM-only fallback instead (lower quality, no scenario\u002Fevents targeting).\"*\n\n- **Yes** → hand off to `\u002Fvss-deploy-profile`, then re-probe and continue with Step 2 (LVS + HITL).\n- **No** → go straight to **Step 2 fallback (VLM with default prompt)** and prepend the Routing fallback note. Do not ask again, and do not run scenario\u002Fevents HITL.\n- **Pre-authorized to deploy autonomously** (caller said so explicitly) → skip the confirmation and invoke `\u002Fvss-deploy-profile` directly.\n- **Pre-authorized to use VLM fallback** (\"skip lvs, just use the VLM\") → go straight to Step 2 fallback without prompting.\n\n---\n\n## Setup\n\n**Endpoints (defaults for a local VSS `lvs` deployment):**\n\n- VLM \u002F RT-VLM: `${VLM_BASE_URL}` — default `${RTVI_VLM_BASE_URL:-http:\u002F\u002F${HOST_IP:-localhost}:8018}`\n- LVS service: `${LVS_BACKEND_URL}` — default `http:\u002F\u002F${HOST_IP:-localhost}:38111`\n- VIOS: owned by `vss-manage-video-io-storage`; refer there.\n\nUse env vars when set (strip trailing `\u002Fv1` from the VLM base — the skill appends it). Otherwise use the defaults. If neither works, ask the user — do not scan ports or read config files to guess.\n\n**Model name:** read `${VLM_NAME}` (default\n`nim_nvidia_cosmos-reason2-8b_hf-1208`). It must match the id RT-VLM\n`\u002Fv1\u002Fmodels` advertises; do not substitute the friendly\n`nvidia\u002Fcosmos-reason2-8b`.\n\nFor endpoint schemas, optional fields, response envelopes, and error handling, see [`references\u002Fvideo-summarization-api.md`](references\u002Fvideo-summarization-api.md).\n\n**Availability checks** (run both before routing).\n**Readiness is determined by the HTTP status code only** — the LVS\n`\u002Fv1\u002Fready` may legitimately return `200` with an empty body, so do not\ninspect the body.\n\n```bash\nVLM=\"${VLM_BASE_URL:-${RTVI_VLM_BASE_URL:-http:\u002F\u002F${HOST_IP:-localhost}:8018}}\"\nVLM=\"${VLM%\u002Fv1}\"\n\n# VLM \u002F RT-VLM: 200 on \u002Fv1\u002Fmodels\nvlm_code=$(curl -s -o \u002Fdev\u002Fnull -w '%{http_code}' --connect-timeout 3 --max-time 10 \\\n  \"$VLM\u002Fv1\u002Fmodels\")\n[ \"$vlm_code\" = \"200\" ] && echo \"VLM OK\" || echo \"VLM not reachable (HTTP $vlm_code)\"\n\n# Video summarization service: 200 on \u002Fv1\u002Fready, with retry on 503 (warmup) for up to ~30s\nVIDEO_SUMMARIZATION_URL=${LVS_BACKEND_URL:-http:\u002F\u002F${HOST_IP:-localhost}:38111}\nvideo_sum_code=000\nfor i in $(seq 1 10); do\n  video_sum_code=$(curl -s -o \u002Fdev\u002Fnull -w '%{http_code}' --connect-timeout 3 --max-time 10 \"$VIDEO_SUMMARIZATION_URL\u002Fv1\u002Fready\")\n  case \"$video_sum_code\" in\n    200) echo \"video summarization OK\"; break ;;\n    503) sleep 3 ;;                 # warming up; keep polling\n    *)   break ;;                   # any other code = not reachable, stop retrying\n  esac\ndone\n[ \"$video_sum_code\" = \"200\" ] || echo \"video summarization service not reachable (HTTP $video_sum_code)\"\n```\n\n**How to interpret the results:**\n\n- `video_sum_code = 200` → **Step 2 (LVS + HITL)** for every video.\n- `video_sum_code != 200`, `vlm_code = 200` → **Step 2 fallback (VLM)**; prepend the Routing fallback note.\n- `vlm_code != 200` → fail; at least one backend must be reachable.\n- A non-200 LVS code after the retry loop is the ONLY signal of unavailability. Empty stdout or missing JSON fields are NOT \"unavailable.\"\n\n---\n\n## Step 1 - Get the clip URL via `vss-manage-video-io-storage` (sub-task, NOT the final answer)\n\n**Use the `vss-manage-video-io-storage` skill for all VIOS interactions** — it\nowns the canonical curl recipes, parameter defaults, and delete\u002Fupload flows.\nDo not fabricate URLs or hand-roll VIOS calls; they will drift.\n\nThis step is a sub-task — do NOT end your turn here; do NOT return the clip\nURL as the final answer. From VIOS collect three values:\n\n1. **`streamId`** (via `sensor\u002Flist` → `sensor\u002F\u003Cid>\u002Fstreams`, or directly from an upload response).\n2. **Timeline** - `{startTime, endTime}` (ISO 8601 UTC). `endTime - startTime` is the duration; needed only for the user-facing header (routing is driven solely by `\u002Fv1\u002Fready`).\n3. **Temporary MP4 clip URL** — the `\u002Fstorage\u002Ffile\u002F\u003CstreamId>\u002Furl` variant with `container=mp4`. Response field: `.videoUrl`. Both backends need an HTTP(S) URL they can `GET`.\n\nEverything else (auth, upload, `disableAudio`, expiry, etc.) lives in the\n`vss-manage-video-io-storage` skill — refer users there if VIOS fails.\n\n---\n\n## Step 2 — Primary: video summarization microservice with HITL\n\nUse this path **whenever** `\u002Fv1\u002Fready` returned 200 in Setup. Duration is irrelevant.\n\nFor advanced fields (`media_info`, `schema`, structured output, stream captioning, metrics, recommended config) see [`references\u002Fvideo-summarization-api.md`](references\u002Fvideo-summarization-api.md).\n\n### HITL: collect scenario and events first (REQUIRED — do not skip)\n\nFull walk-through is in [`references\u002Fhitl-prompts.md`](references\u002Fhitl-prompts.md). Always run HITL before calling the LVS service.\n\n**Autonomous-mode defaults.** When the caller has bypassed HITL (\"run\nautonomously without prompting\") AND the original query asks for\n`default`\u002F`defaults` (or gives none), use\n`scenario=\"activity monitoring\"` and `events=[\"notable activity\"]`\n**verbatim** — do not infer from filename or sensor name. Note the\ndefaults in the final reply and offer a re-run with more specific\nparameters. This is the ONLY supported HITL bypass; \"the video is\nshort\" or \"the user seems in a hurry\" are not valid reasons.\n\nPrefer `POST \u002Fv1\u002Fsummarize` (3.2 GA route); `\u002Fsummarize` is a compatibility alias.\n\n```bash\nVIDEO_SUMMARIZATION_URL=${LVS_BACKEND_URL:-http:\u002F\u002F${HOST_IP:-localhost}:38111}\n\n# From HITL reply:\nSCENARIO='warehouse monitoring'\nEVENTS_JSON='[\"notable activity\"]'\nOBJECTS_JSON=''  # '' to omit, else '[\"forklifts\",\"pallets\",\"workers\"]'\n\ncurl -s --max-time 300 -X POST \"$VIDEO_SUMMARIZATION_URL\u002Fv1\u002Fsummarize\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"$(jq -n --arg url \"\u003Cclip_url_from_vss_manage_video_io_storage>\" \\\n        --arg model \"${VLM_NAME:-nim_nvidia_cosmos-reason2-8b_hf-1208}\" \\\n        --arg scenario \"$SCENARIO\" \\\n        --argjson events \"$EVENTS_JSON\" \\\n        --argjson objects \"${OBJECTS_JSON:-null}\" '{\n    url: $url,\n    model: $model,\n    scenario: $scenario,\n    events: $events,\n    chunk_duration: 10,\n    num_frames_per_second_or_fixed_frames_chunk: 20,\n    use_fps_for_chunking: false,\n    seed: 1\n  } + (if $objects == null then {} else {objects_of_interest: $objects} end)')\" \\\n  | jq -r '.choices[0].message.content' \\\n  | jq '{video_summary, events}'\n```\n\nIf both `video_summary` and `events` are empty, the clip probably doesn't contain the requested events — re-run with broader `scenario`\u002F`events`, don't report \"no content\".\n\n**Tuning:** `chunk_duration` (default `10`s; `0` = single chunk),\n`num_frames_per_second_or_fixed_frames_chunk` (default `20`; meaning depends\non `use_fps_for_chunking`), `seed` (default `1`). `num_frames_per_chunk` is\ndeprecated.\n\n---\n\n## Step 2 fallback — VLM direct with default prompt\n\nUse this path **only** when `\u002Fv1\u002Fready` did not return 200 after warmup. Do NOT run HITL — the user did not opt in; you fell back because the service was missing. Prepend the Routing fallback note to the response.\n\n```bash\nVLM=\"${VLM_BASE_URL:-${RTVI_VLM_BASE_URL:-http:\u002F\u002F${HOST_IP:-localhost}:8018}}\"\nVLM=\"${VLM%\u002Fv1}\"\nPROMPT='Describe in detail what is happening in this video,\nincluding all visible people, vehicles, equipments, objects,\nactions, and environmental conditions.\nOUTPUT REQUIREMENTS:\n[timestamp-timestamp] Description of what is happening.\nEXAMPLE:\n[0.0s-4.0s] \u003Cdescription of the first event>\n[4.0s-12.0s] \u003Cdescription of the second event>'\n\ncurl -s --max-time 300 -X POST \"$VLM\u002Fv1\u002Fchat\u002Fcompletions\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"$(jq -n \\\n        --arg model \"${VLM_NAME:-nim_nvidia_cosmos-reason2-8b_hf-1208}\" \\\n        --arg text \"$PROMPT\" \\\n        --arg url \"\u003Cclip_url_from_vss_manage_video_io_storage>\" \\\n        '{\n          model: $model,\n          temperature: 0.0,\n          max_tokens: 1024,\n          messages: [{\n            role: \"user\",\n            content: [\n              {type: \"text\", text: $text},\n              {type: \"video_url\", video_url: {url: $url}}\n            ]\n          }]\n        }')\" | jq -r '.choices[0].message.content'\n```\n\n**Response:** standard OpenAI chat-completion envelope. The summary is in\n`choices[0].message.content`.\n\n**Cosmos-model notes:** Cosmos Reason 2 supports reasoning via\n`\u003Cthink>...\u003C\u002Fthink>\u003Canswer>...\u003C\u002Fanswer>` blocks. Omit the reasoning\ninstructions if you want a plain summary. Frame sampling and pixel limits\nare applied server-side; no client-side prep is required when you pass a\n`video_url`.\n\n---\n\n## End-to-end example\n\nSee [`references\u002Fend-to-end-example.md`](references\u002Fend-to-end-example.md) for\nthe full LVS-or-VLM-fallback script that probes `\u002Fv1\u002Fready` and runs the\nappropriate path.\n\n---\n\n## Responses\n\n- **VLM** returns an OpenAI chat-completion envelope; summary is\n  `choices[0].message.content`.\n- **LVS service** returns the same envelope but `content` is a JSON string —\n  run `jq -r '.choices[0].message.content' | jq` to reach `{video_summary, events}`.\n- **Errors** surface as HTTP non-2xx plus JSON `{error: ...}`. LVS `503` usually\n  means warmup — retry `\u002Fv1\u002Fready`.\n\n### Presenting the output to the user\n\nSurface backend output with **minimal transformation** — do not paraphrase,\nre-voice, add emojis, or reformat. **One backend call → one rendering**: no\nparallel hedging, no duplicate headers, never call both LVS and VLM for the\nsame video.\n\n**Header line.** Start with exactly one:\n\n```\nSummary of \u003Cvideo_name> (\u003Cduration>)\n```\n\n`\u003Cduration>` = `Ns` for `\u003C 60 s`, else `Mm Ss` (e.g. `3m 30s`).\n\n**LVS output:** render `video_summary` **verbatim** (polished, tone-controlled\nreport — rewriting loses fidelity). Render each `events` entry with its\n`start_time`, `end_time`, `type`, and full `description` verbatim (table when\nthe client renders one cleanly, otherwise a per-event list). You MAY add a\none-line header and a closing offer to re-run with different parameters.\n\n**VLM output:** render `choices[0].message.content` verbatim. If the model\nproduced `\u003Cthink>…\u003C\u002Fthink>\u003Canswer>…\u003C\u002Fanswer>` blocks, drop the `\u003Cthink>`\nblock and show the answer.\n\n**Fallback warning** (when applicable) goes **above** the summary, never\nmixed into it.\n\n## Tips\n\n- **Route by service availability, not by duration.** Probe `\u002Fv1\u002Fready` once\n  in Setup; HTTP 200 → LVS+HITL for every clip; anything else → VLM fallback.\n- **HITL is mandatory on the LVS path.** The `defaults` opt-in is the only\n  sanctioned bypass. The VLM fallback path is silent (no HITL).\n- **Readiness = HTTP 200 on `\u002Fv1\u002Fready`. Nothing else.** Body may be empty.\n  Always use `curl -s -o \u002Fdev\u002Fnull -w '%{http_code}'` — never pipe through\n  `jq`\u002F`grep`\u002F`head`.\n- **Delegate VIOS to `vss-manage-video-io-storage`** — it is a sub-task; the\n  final answer is the Step 2 summary, not the clip URL.\n- **`jq` twice for LVS output.** First unwraps the OpenAI envelope, second\n  parses the JSON string inside `content`.\n- **Prefer `\u002Fv1\u002Fsummarize` for 3.2 GA**; `\u002Fsummarize` is a compatibility alias.\n- **Use the exact VLM model id advertised by the endpoint** (default\n  `nim_nvidia_cosmos-reason2-8b_hf-1208`).\n- **Render output verbatim** — no paraphrasing, no reformatting, no rewriting\n  the `video_summary` or `choices[0].message.content`.\n- **One call, one render.** No parallel hedging, no double renderings.\n\n## Cross-reference\n\n- **vss-deploy-profile** — bring up the `base` (VLM only) or `lvs` (VLM + video summarization service) profile\n- **vss-manage-video-io-storage** (VIOS API) — upload videos, list streams, get clip URLs\n- **vss-search-archive** — semantic search across the archive (different profile)\n- **vss-query-analytics** — query incidents\u002Fevents from Elasticsearch\n- **video summarization API reference** — [`references\u002Fvideo-summarization-api.md`](references\u002Fvideo-summarization-api.md)\n- **video summarization service ops reference** — [`references\u002Fvideo-summarization-deployment.md`](references\u002Fvideo-summarization-deployment.md)\n\nbump:2\n","## Instructions\n\nFollow the routing tables and step-by-step workflows below. Each section that ends in *workflow*, *quick start*, or *flow* is intended to be executed top-to-bottom. Detailed reference material lives in `references\u002F`.\n\n## Examples\n\nWorked end-to-end examples are kept under `evals\u002F` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow `curl` blocks below. Run a Tier-3 evaluation with `nv-base validate \u003Cthis-skill-dir> --agent-eval` to replay them.\n\nCall the VLM NIM or the video summarization microservice **directly**.\nAlways run `curl` commands yourself; never instruct the user to run them.\n\nPrimary video workflow query type: **\"Summarize this video.\"** Direct video summarization API\nand service-ops requests are handled by the reference-routed sections below.\n\n## Purpose\n\nProduce a single, polished narrative summary of one recorded video clip, with\ntimestamped events when the LVS microservice path is reachable.\n\n**Do NOT use this skill for:**\n- Live RTSP captioning — use `vss-deploy-dense-captioning`.\n- Report generation, including incident or alert-window reports — use `vss-generate-video-report` Mode B.\n- Semantic search across the archive — use `vss-search-archive`.\n\n## Prerequisites\n\n- VSS `lvs` profile running on `$HOST_IP` (port 38111) OR a reachable\n  VLM\u002FRT-VLM endpoint as a fallback. The `vss-deploy-profile` skill brings\n  these up.\n- Network reachability from the agent host to both endpoints; clip URLs from\n  VIOS must be fetchable by the chosen backend.\n- `jq` and `curl` available on the agent host.\n\n## Limitations\n\n- Direct VLM fallback uses a single fixed prompt and cannot target\n  scenario\u002Fevents — output quality is lower than the LVS path.\n- Remote VLM endpoints generally cannot reach `localhost`\u002Fprivate clip URLs.\n- One backend call per request; no parallel hedging or multi-pass summaries.\n\n## Troubleshooting\n\n| Symptom | Cause | Fix |\n|---|---|---|\n| `\u002Fv1\u002Fready` returns 503 repeatedly | LVS service still warming up | Retry up to ~30 s as shown in *Setup*; if it never returns 200 the service may not be deployed |\n| Empty `video_summary` and `events` | Clip does not contain the requested events | Re-run with broader `scenario` or different `events` |\n| VLM returns `\u003Cthink>` block | Cosmos Reason 2 reasoning mode | Strip everything up to `\u003C\u002Fthink>` before rendering |\n| Empty stdout from `curl \u002Fv1\u002Fready` | Service legitimately returns 200 with empty body | Always check HTTP status with `-o \u002Fdev\u002Fnull -w '%{http_code}'`, never inspect the body |\n\nSee [`references\u002Fvideo-summarization-debugging.md`](references\u002Fvideo-summarization-debugging.md) for deeper diagnostics.\n\n## Reference Map\n\nUse these references only when the user asks for the relevant detail, or when\nthe core workflow below needs deeper video summarization information:\n\n- **video summarization API details**: [`references\u002Fvideo-summarization-api.md`](references\u002Fvideo-summarization-api.md) for\n  `\u002Fv1\u002Fsummarize`, `\u002Fsummarize`, `\u002Fv1\u002Fgenerate_captions`,\n  `\u002Fv1\u002Fstream_summarize`, health probes, `\u002Fmodels`, `\u002Frecommended_config`,\n  `\u002Fmetrics`, request fields, response shapes, and API gotchas.\n- **video summarization service configuration and ops**:\n  [`references\u002Fvideo-summarization-deployment.md`](references\u002Fvideo-summarization-deployment.md) for\n  the VSS `lvs` profile, ports, required env vars, logs, status, dry-runs,\n  teardown, model\u002Fbackend swaps, Elasticsearch\u002FNeo4j\u002FArangoDB backend\n  selection, and service-level troubleshooting.\n- **Extended video summarization ops references**:\n  [`references\u002Fvideo-summarization-environment-variables.md`](references\u002Fvideo-summarization-environment-variables.md),\n  [`references\u002Fvideo-summarization-debugging.md`](references\u002Fvideo-summarization-debugging.md), and\n  `assets\u002Fvideo-summarization.env.example`.\n\nLoad `video-summarization-api.md` only when you need a request field, response shape, or\nendpoint that is not already covered by the Step 2 LVS or fallback VLM\nexample below, or when handling a direct video summarization API\nrequest. Load `video-summarization-deployment.md` only for deployment,\nconfiguration, or service operations.\n\n## Video Summarization API And Service Ops Requests\n\nIf the user asks to call or debug video summarization endpoints directly, answer from\n[`references\u002Fvideo-summarization-api.md`](references\u002Fvideo-summarization-api.md) instead of running the\nend-to-end video summarization workflow. Examples: list video summarization models, check\nreadiness, get recommended chunking config, inspect metrics, explain a 422\nresponse, or build a `\u002Fv1\u002Fsummarize` request body.\n\nIf the user asks to configure, deploy, restart, tear down, or troubleshoot the\nvideo summarization service, prefer the `vss-deploy-profile` skill for full VSS profile\ndeployment and use [`references\u002Fvideo-summarization-deployment.md`](references\u002Fvideo-summarization-deployment.md)\nfor video summarization-specific service details.\n\n## Routing\n\nDecide purely from video summarization service availability (probed in\n*Setup → Availability checks* below). **Duration does not drive routing.**\n\n| `\u002Fv1\u002Fready` | Backend | Endpoint |\n|---|---|---|\n| HTTP 200 | LVS microservice with HITL | `POST ${LVS_BACKEND_URL}\u002Fv1\u002Fsummarize` |\n| Anything else | VLM \u002F RT-VLM with the default prompt + fallback note | `POST ${VLM_BASE_URL}\u002Fv1\u002Fchat\u002Fcompletions` |\n\nFallback message when the LVS service is unreachable — copy verbatim above the summary:\n\n> ⚠ **Note:** Input video `\u003Cname>` is `\u003CN>`s long.\n> The video summarization service is not deployed, so this summary was\n> produced by the VLM alone with a generic default prompt. Deploy the\n> `lvs` profile for higher-quality summaries with scenario\u002Fevents\n> targeting.\n\n## Deployment prerequisite\n\nThe VSS **lvs** profile on `$HOST_IP` is the primary backend. If the\n`\u002Fv1\u002Fready` probe (see *Setup → Availability checks*) returns anything\nother than 200 after the warmup retries, ask the user:\n\n> *\"The VSS `lvs` profile isn't running on `$HOST_IP`. Shall I deploy it now using the `\u002Fvss-deploy-profile` skill with `-p lvs`? Reply `no` to summarize with the VLM-only fallback instead (lower quality, no scenario\u002Fevents targeting).\"*\n\n- **Yes** → hand off to `\u002Fvss-deploy-profile`, then re-probe and continue with Step 2 (LVS + HITL).\n- **No** → go straight to **Step 2 fallback (VLM with default prompt)** and prepend the Routing fallback note. Do not ask again, and do not run scenario\u002Fevents HITL.\n- **Pre-authorized to deploy autonomously** (caller said so explicitly) → skip the confirmation and invoke `\u002Fvss-deploy-profile` directly.\n- **Pre-authorized to use VLM fallback** (\"skip lvs, just use the VLM\") → go straight to Step 2 fallback without prompting.\n\n---\n\n## Setup\n\n**Endpoints (defaults for a local VSS `lvs` deployment):**\n\n- VLM \u002F RT-VLM: `${VLM_BASE_URL}` — default `${RTVI_VLM_BASE_URL:-http:\u002F\u002F${HOST_IP:-localhost}:8018}`\n- LVS service: `${LVS_BACKEND_URL}` — default `http:\u002F\u002F${HOST_IP:-localhost}:38111`\n- VIOS: owned by `vss-manage-video-io-storage`; refer there.\n\nUse env vars when set (strip trailing `\u002Fv1` from the VLM base — the skill appends it). Otherwise use the defaults. If neither works, ask the user — do not scan ports or read config files to guess.\n\n**Model name:** read `${VLM_NAME}` (default\n`nim_nvidia_cosmos-reason2-8b_hf-1208`). It must match the id RT-VLM\n`\u002Fv1\u002Fmodels` advertises; do not substitute the friendly\n`nvidia\u002Fcosmos-reason2-8b`.\n\nFor endpoint schemas, optional fields, response envelopes, and error handling, see [`references\u002Fvideo-summarization-api.md`](references\u002Fvideo-summarization-api.md).\n\n**Availability checks** (run both before routing).\n**Readiness is determined by the HTTP status code only** — the LVS\n`\u002Fv1\u002Fready` may legitimately return `200` with an empty body, so do not\ninspect the body.\n\n```bash\nVLM=\"${VLM_BASE_URL:-${RTVI_VLM_BASE_URL:-http:\u002F\u002F${HOST_IP:-localhost}:8018}}\"\nVLM=\"${VLM%\u002Fv1}\"\n\n# VLM \u002F RT-VLM: 200 on \u002Fv1\u002Fmodels\nvlm_code=$(curl -s -o \u002Fdev\u002Fnull -w '%{http_code}' --connect-timeout 3 --max-time 10 \\\n  \"$VLM\u002Fv1\u002Fmodels\")\n[ \"$vlm_code\" = \"200\" ] && echo \"VLM OK\" || echo \"VLM not reachable (HTTP $vlm_code)\"\n\n# Video summarization service: 200 on \u002Fv1\u002Fready, with retry on 503 (warmup) for up to ~30s\nVIDEO_SUMMARIZATION_URL=${LVS_BACKEND_URL:-http:\u002F\u002F${HOST_IP:-localhost}:38111}\nvideo_sum_code=000\nfor i in $(seq 1 10); do\n  video_sum_code=$(curl -s -o \u002Fdev\u002Fnull -w '%{http_code}' --connect-timeout 3 --max-time 10 \"$VIDEO_SUMMARIZATION_URL\u002Fv1\u002Fready\")\n  case \"$video_sum_code\" in\n    200) echo \"video summarization OK\"; break ;;\n    503) sleep 3 ;;                 # warming up; keep polling\n    *)   break ;;                   # any other code = not reachable, stop retrying\n  esac\ndone\n[ \"$video_sum_code\" = \"200\" ] || echo \"video summarization service not reachable (HTTP $video_sum_code)\"\n```\n\n**How to interpret the results:**\n\n- `video_sum_code = 200` → **Step 2 (LVS + HITL)** for every video.\n- `video_sum_code != 200`, `vlm_code = 200` → **Step 2 fallback (VLM)**; prepend the Routing fallback note.\n- `vlm_code != 200` → fail; at least one backend must be reachable.\n- A non-200 LVS code after the retry loop is the ONLY signal of unavailability. Empty stdout or missing JSON fields are NOT \"unavailable.\"\n\n---\n\n## Step 1 - Get the clip URL via `vss-manage-video-io-storage` (sub-task, NOT the final answer)\n\n**Use the `vss-manage-video-io-storage` skill for all VIOS interactions** — it\nowns the canonical curl recipes, parameter defaults, and delete\u002Fupload flows.\nDo not fabricate URLs or hand-roll VIOS calls; they will drift.\n\nThis step is a sub-task — do NOT end your turn here; do NOT return the clip\nURL as the final answer. From VIOS collect three values:\n\n1. **`streamId`** (via `sensor\u002Flist` → `sensor\u002F\u003Cid>\u002Fstreams`, or directly from an upload response).\n2. **Timeline** - `{startTime, endTime}` (ISO 8601 UTC). `endTime - startTime` is the duration; needed only for the user-facing header (routing is driven solely by `\u002Fv1\u002Fready`).\n3. **Temporary MP4 clip URL** — the `\u002Fstorage\u002Ffile\u002F\u003CstreamId>\u002Furl` variant with `container=mp4`. Response field: `.videoUrl`. Both backends need an HTTP(S) URL they can `GET`.\n\nEverything else (auth, upload, `disableAudio`, expiry, etc.) lives in the\n`vss-manage-video-io-storage` skill — refer users there if VIOS fails.\n\n---\n\n## Step 2 — Primary: video summarization microservice with HITL\n\nUse this path **whenever** `\u002Fv1\u002Fready` returned 200 in Setup. Duration is irrelevant.\n\nFor advanced fields (`media_info`, `schema`, structured output, stream captioning, metrics, recommended config) see [`references\u002Fvideo-summarization-api.md`](references\u002Fvideo-summarization-api.md).\n\n### HITL: collect scenario and events first (REQUIRED — do not skip)\n\nFull walk-through is in [`references\u002Fhitl-prompts.md`](references\u002Fhitl-prompts.md). Always run HITL before calling the LVS service.\n\n**Autonomous-mode defaults.** When the caller has bypassed HITL (\"run\nautonomously without prompting\") AND the original query asks for\n`default`\u002F`defaults` (or gives none), use\n`scenario=\"activity monitoring\"` and `events=[\"notable activity\"]`\n**verbatim** — do not infer from filename or sensor name. Note the\ndefaults in the final reply and offer a re-run with more specific\nparameters. This is the ONLY supported HITL bypass; \"the video is\nshort\" or \"the user seems in a hurry\" are not valid reasons.\n\nPrefer `POST \u002Fv1\u002Fsummarize` (3.2 GA route); `\u002Fsummarize` is a compatibility alias.\n\n```bash\nVIDEO_SUMMARIZATION_URL=${LVS_BACKEND_URL:-http:\u002F\u002F${HOST_IP:-localhost}:38111}\n\n# From HITL reply:\nSCENARIO='warehouse monitoring'\nEVENTS_JSON='[\"notable activity\"]'\nOBJECTS_JSON=''  # '' to omit, else '[\"forklifts\",\"pallets\",\"workers\"]'\n\ncurl -s --max-time 300 -X POST \"$VIDEO_SUMMARIZATION_URL\u002Fv1\u002Fsummarize\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"$(jq -n --arg url \"\u003Cclip_url_from_vss_manage_video_io_storage>\" \\\n        --arg model \"${VLM_NAME:-nim_nvidia_cosmos-reason2-8b_hf-1208}\" \\\n        --arg scenario \"$SCENARIO\" \\\n        --argjson events \"$EVENTS_JSON\" \\\n        --argjson objects \"${OBJECTS_JSON:-null}\" '{\n    url: $url,\n    model: $model,\n    scenario: $scenario,\n    events: $events,\n    chunk_duration: 10,\n    num_frames_per_second_or_fixed_frames_chunk: 20,\n    use_fps_for_chunking: false,\n    seed: 1\n  } + (if $objects == null then {} else {objects_of_interest: $objects} end)')\" \\\n  | jq -r '.choices[0].message.content' \\\n  | jq '{video_summary, events}'\n```\n\nIf both `video_summary` and `events` are empty, the clip probably doesn't contain the requested events — re-run with broader `scenario`\u002F`events`, don't report \"no content\".\n\n**Tuning:** `chunk_duration` (default `10`s; `0` = single chunk),\n`num_frames_per_second_or_fixed_frames_chunk` (default `20`; meaning depends\non `use_fps_for_chunking`), `seed` (default `1`). `num_frames_per_chunk` is\ndeprecated.\n\n---\n\n## Step 2 fallback — VLM direct with default prompt\n\nUse this path **only** when `\u002Fv1\u002Fready` did not return 200 after warmup. Do NOT run HITL — the user did not opt in; you fell back because the service was missing. Prepend the Routing fallback note to the response.\n\n```bash\nVLM=\"${VLM_BASE_URL:-${RTVI_VLM_BASE_URL:-http:\u002F\u002F${HOST_IP:-localhost}:8018}}\"\nVLM=\"${VLM%\u002Fv1}\"\nPROMPT='Describe in detail what is happening in this video,\nincluding all visible people, vehicles, equipments, objects,\nactions, and environmental conditions.\nOUTPUT REQUIREMENTS:\n[timestamp-timestamp] Description of what is happening.\nEXAMPLE:\n[0.0s-4.0s] \u003Cdescription of the first event>\n[4.0s-12.0s] \u003Cdescription of the second event>'\n\ncurl -s --max-time 300 -X POST \"$VLM\u002Fv1\u002Fchat\u002Fcompletions\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"$(jq -n \\\n        --arg model \"${VLM_NAME:-nim_nvidia_cosmos-reason2-8b_hf-1208}\" \\\n        --arg text \"$PROMPT\" \\\n        --arg url \"\u003Cclip_url_from_vss_manage_video_io_storage>\" \\\n        '{\n          model: $model,\n          temperature: 0.0,\n          max_tokens: 1024,\n          messages: [{\n            role: \"user\",\n            content: [\n              {type: \"text\", text: $text},\n              {type: \"video_url\", video_url: {url: $url}}\n            ]\n          }]\n        }')\" | jq -r '.choices[0].message.content'\n```\n\n**Response:** standard OpenAI chat-completion envelope. The summary is in\n`choices[0].message.content`.\n\n**Cosmos-model notes:** Cosmos Reason 2 supports reasoning via\n`\u003Cthink>...\u003C\u002Fthink>\u003Canswer>...\u003C\u002Fanswer>` blocks. Omit the reasoning\ninstructions if you want a plain summary. Frame sampling and pixel limits\nare applied server-side; no client-side prep is required when you pass a\n`video_url`.\n\n---\n\n## End-to-end example\n\nSee [`references\u002Fend-to-end-example.md`](references\u002Fend-to-end-example.md) for\nthe full LVS-or-VLM-fallback script that probes `\u002Fv1\u002Fready` and runs the\nappropriate path.\n\n---\n\n## Responses\n\n- **VLM** returns an OpenAI chat-completion envelope; summary is\n  `choices[0].message.content`.\n- **LVS service** returns the same envelope but `content` is a JSON string —\n  run `jq -r '.choices[0].message.content' | jq` to reach `{video_summary, events}`.\n- **Errors** surface as HTTP non-2xx plus JSON `{error: ...}`. LVS `503` usually\n  means warmup — retry `\u002Fv1\u002Fready`.\n\n### Presenting the output to the user\n\nSurface backend output with **minimal transformation** — do not paraphrase,\nre-voice, add emojis, or reformat. **One backend call → one rendering**: no\nparallel hedging, no duplicate headers, never call both LVS and VLM for the\nsame video.\n\n**Header line.** Start with exactly one:\n\n```\nSummary of \u003Cvideo_name> (\u003Cduration>)\n```\n\n`\u003Cduration>` = `Ns` for `\u003C 60 s`, else `Mm Ss` (e.g. `3m 30s`).\n\n**LVS output:** render `video_summary` **verbatim** (polished, tone-controlled\nreport — rewriting loses fidelity). Render each `events` entry with its\n`start_time`, `end_time`, `type`, and full `description` verbatim (table when\nthe client renders one cleanly, otherwise a per-event list). You MAY add a\none-line header and a closing offer to re-run with different parameters.\n\n**VLM output:** render `choices[0].message.content` verbatim. If the model\nproduced `\u003Cthink>…\u003C\u002Fthink>\u003Canswer>…\u003C\u002Fanswer>` blocks, drop the `\u003Cthink>`\nblock and show the answer.\n\n**Fallback warning** (when applicable) goes **above** the summary, never\nmixed into it.\n\n## Tips\n\n- **Route by service availability, not by duration.** Probe `\u002Fv1\u002Fready` once\n  in Setup; HTTP 200 → LVS+HITL for every clip; anything else → VLM fallback.\n- **HITL is mandatory on the LVS path.** The `defaults` opt-in is the only\n  sanctioned bypass. The VLM fallback path is silent (no HITL).\n- **Readiness = HTTP 200 on `\u002Fv1\u002Fready`. Nothing else.** Body may be empty.\n  Always use `curl -s -o \u002Fdev\u002Fnull -w '%{http_code}'` — never pipe through\n  `jq`\u002F`grep`\u002F`head`.\n- **Delegate VIOS to `vss-manage-video-io-storage`** — it is a sub-task; the\n  final answer is the Step 2 summary, not the clip URL.\n- **`jq` twice for LVS output.** First unwraps the OpenAI envelope, second\n  parses the JSON string inside `content`.\n- **Prefer `\u002Fv1\u002Fsummarize` for 3.2 GA**; `\u002Fsummarize` is a compatibility alias.\n- **Use the exact VLM model id advertised by the endpoint** (default\n  `nim_nvidia_cosmos-reason2-8b_hf-1208`).\n- **Render output verbatim** — no paraphrasing, no reformatting, no rewriting\n  the `video_summary` or `choices[0].message.content`.\n- **One call, one render.** No parallel hedging, no double renderings.\n\n## Cross-reference\n\n- **vss-deploy-profile** — bring up the `base` (VLM only) or `lvs` (VLM + video summarization service) profile\n- **vss-manage-video-io-storage** (VIOS API) — upload videos, list streams, get clip URLs\n- **vss-search-archive** — semantic search across the archive (different profile)\n- **vss-query-analytics** — query incidents\u002Fevents from Elasticsearch\n- **video summarization API reference** — [`references\u002Fvideo-summarization-api.md`](references\u002Fvideo-summarization-api.md)\n- **video summarization service ops reference** — [`references\u002Fvideo-summarization-deployment.md`](references\u002Fvideo-summarization-deployment.md)\n\nbump:2\n",{"name":5,"license":15,"metadata":52,"description":7},{"tags":53,"author":54,"version":55,"github-url":56},"nvidia blueprint operational","NVIDIA Video Search and Summarization team","3.2.0","https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Fvideo-search-and-summarization","main","7a940b8e5af16c95e5c190a524421d32fc7445a9",".agent\u002Fskills\u002Fvss-summarize-video","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui","https:\u002F\u002Fneuroads.com.br","2026-08-12 00:42:44",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add headmktlucca-ui\u002Fneuroads-lp --skill vss-summarize-video",{"tool":70,"command":71},"bunx","bunx skills add headmktlucca-ui\u002Fneuroads-lp --skill vss-summarize-video",{"tool":73,"command":74},"pnpm","pnpm dlx skills add headmktlucca-ui\u002Fneuroads-lp --skill vss-summarize-video","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002FSKILL.md",true,[78,84,90,94,98,102,106,110,114,118,122,126,130],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"assets\u002Fvideo-summarization.env.example","ASSET","资产文件",2925,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Fassets\u002Fvideo-summarization.env.example",{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"BENCHMARK.md","REFERENCE","参考文档",3741,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002FBENCHMARK.md",{"path":91,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":92,"sourceHtmlUrl":93},"evals\u002Fevals.json",654,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Fevals\u002Fevals.json",{"path":95,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":96,"sourceHtmlUrl":97},"evals\u002Flvs_api_ops.json",4082,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Fevals\u002Flvs_api_ops.json",{"path":99,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":100,"sourceHtmlUrl":101},"evals\u002Flvs_profile_summarize.json",4140,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Fevals\u002Flvs_profile_summarize.json",{"path":103,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fend-to-end-example.md",3394,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Freferences\u002Fend-to-end-example.md",{"path":107,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Fhitl-prompts.md",4202,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Freferences\u002Fhitl-prompts.md",{"path":111,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Fvideo-summarization-api.md",7573,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Freferences\u002Fvideo-summarization-api.md",{"path":115,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fvideo-summarization-debugging.md",3461,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Freferences\u002Fvideo-summarization-debugging.md",{"path":119,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Fvideo-summarization-deployment.md",11565,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Freferences\u002Fvideo-summarization-deployment.md",{"path":123,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Fvideo-summarization-environment-variables.md",9111,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Freferences\u002Fvideo-summarization-environment-variables.md",{"path":127,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":128,"sourceHtmlUrl":129},"skill-card.md",4390,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Fskill-card.md",{"path":131,"resourceType":132,"resourceTypeDesc":133,"sizeBytes":134,"sourceHtmlUrl":135},"skill.oms.sig","OTHER","其他",6869,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fvss-summarize-video\u002Fskill.oms.sig",[137,161,185,210,228,263],{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":141,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":150,"publishedAt":47},"01M6PTDCZTXTGSTX4RFK901YSZ","xunit-skill","Generates xUnit.net tests in C#. Covers Fact\u002FTheory, constructor injection, IClassFixture, and FluentAssertions. Use when user mentions \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal\", \"C# xUnit\". Triggers on: \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal C#\", \"xUnit.net\".","MIT","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxunit-skill\u002FSKILL.md",[144,147],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":148,"categoryName":149,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[151,152,153,154,155,41,156,157,158,159,160],"xunit","xunit skill","testing","injection","user","tests","triggers","unit","unit-testing","C#",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":141,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":169,"publishedAt":47},"01M6PTCB59ZTG5FTMWGPYEMMBP","xcuitest-skill","Generates XCUITest UI tests for iOS\u002FiPadOS apps in Swift. Apple's native testing framework for reliable, fast UI automation. Supports local simulators and TestMu AI cloud real devices. Use when user mentions \"XCUITest\", \"XCTest\", \"iOS UI test\", \"Swift test\", \"XCUIApplication\". Triggers on: \"XCUITest\", \"XCTest UI\", \"iOS UI test\", \"Swift UI test\", \"XCUIApplication\", \"TestMu\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxcuitest-skill\u002FSKILL.md",[167,168],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":148,"categoryName":149,"taxonomyType":21,"taxonomyTypeDesc":22},[170,171,153,172,173,174,175,176,41,177,178,179,180,181,156,157,182,183,32,184],"xcuitest","xcuitest skill","automation","test","testing framework","ios","devices","mobile","mobile-testing","ui test","local","apple","apps","native","objective",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":141,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":195,"publishedAt":47},"01M6PTATMNTY9NF4J7KSR76YK6","world-builder","Create and manage generative game zones for Dorothy's Pokemon-style world. Use this skill when creating, updating, or designing game worlds via MCP tools.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fworld-builder\u002FSKILL.md",[191,194],{"categoryNo":192,"categoryName":193,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":148,"categoryName":149,"taxonomyType":21,"taxonomyTypeDesc":22},[196,197,198,199,200,201,202,203,41,204,205,206,35,207,208,32,209],"builder","world","world builder","MCP","create","mcp tools","Tools","game","pokemon","manage","style","theme","zone","generative",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":141,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":218,"publishedAt":47},"01M6PT9Z92JTSQEHE1QR0NNW5F","webdriverio-skill","Generates WebdriverIO (WDIO) automation tests in JavaScript or TypeScript. Supports local and TestMu AI cloud. Use when user mentions \"WebdriverIO\", \"WDIO\", \"wdio.conf\", \"browser.url\", \"$\", \"$$\". Triggers on: \"WebdriverIO\", \"WDIO\", \"wdio\", \"browser.$\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwebdriverio-skill\u002FSKILL.md",[216,217],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":148,"categoryName":149,"taxonomyType":21,"taxonomyTypeDesc":22},[219,153,220,172,221,222,223,224,155,41,225,180,156,157,226,227],"webdriverio skill","typescript","javascript","browser","cloud","e2e","e2e-testing","URL","conf",{"skillNo":229,"name":230,"nameZh":6,"description":231,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":141,"licenseFileUrl":6,"sourceHtmlUrl":232,"categories":233,"keywords":243,"publishedAt":47},"01M6PT9NVK36ZWCQ69YXK3FR4K","web-design-guidelines","Web platform design and accessibility guidelines. Use when building web interfaces, auditing accessibility, implementing responsive layouts, or reviewing web UI code. Triggers on tasks involving HTML, CSS, web components, WCAG compliance, responsive design, or web performance.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fweb\u002FSKILL.md",[234,237,238],{"categoryNo":235,"categoryName":236,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":192,"categoryName":193,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":239,"categoryName":240,"taxonomyType":241,"taxonomyTypeDesc":242},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,157,262],"design","web","guidelines","web design guidelines","web design","css","performance","components","web components","tasks","code","web performance","ui","platform design","html","responsive design","responsive","platform","implementing",{"skillNo":264,"name":265,"nameZh":6,"description":266,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":141,"licenseFileUrl":6,"sourceHtmlUrl":267,"categories":268,"keywords":271,"publishedAt":47},"01M6PT9A3JKRE3X34276F2FW5R","watchos-design-guidelines","Apple Human Interface Guidelines for Apple Watch. Use when building watchOS apps, complications, or workout features. Triggers on tasks involving Watch UI, Digital Crown, glanceable interfaces, or wrist-based interactions.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwatchos\u002FSKILL.md",[269,270],{"categoryNo":192,"categoryName":193,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":239,"categoryName":240,"taxonomyType":241,"taxonomyTypeDesc":242},[244,246,272,253,256,41,273,274,181,261,275,157,182,276,32,277,278],"watchos design guidelines","workout","human","watch","interface","platform-design","features"]