[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BKGVFEFVMPHVS0BBT3F8QP":3,"skill-same:01M7BKGVFEFVMPHVS0BBT3F8QP":129},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M7BKGVFEFVMPHVS0BBT3F8QP","vss-manage-alerts",null,"Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.","YYC-Cube\u002FYYC3-AI-Agent-Archive","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79K9J2WD44BBY4662XKNZRB",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vss-manage-alerts\ndescription: Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.\ncategory: development-code\nversion: 1.0.0\nlicense: Apache-2.0\nmetadata:\n  version: \"3.2.0\"\n  author: \"NVIDIA Video Search and Summarization Team \u003Cvss-team@nvidia.com>\"\n  github-url: \"https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Fvideo-search-and-summarization\"\n  tags: \"nvidia blueprint operational\"\nrelated_skills: [vss-generate-video-report]\n---\n## Purpose\n\nOperate the VSS alert pipeline (mode detection, Alert-Bridge subscriptions, Slack notifications, queries, camera onboarding, verifier-prompt customization).\n\n## Prerequisites\n\n- Active VSS deployment reachable on `$HOST_IP` (see `vss-deploy-profile` and `references\u002F`).\n- NGC credentials in `$NGC_CLI_API_KEY` and `$NVIDIA_API_KEY` for any image pulls.\n- `curl`, `jq`, and Docker available on the caller.\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` and helper scripts live in `scripts\u002F` — call them via `run_script` when the skill points to a script by name.\n\n## Examples\n\nRunnable end-to-end scenarios live under `evals\u002F` (each `*.json` manifest); inline `curl` blocks appear in each workflow below. Replay with `nv-base validate \u003Cthis-skill-dir> --agent-eval`.\n\n## Limitations\n\nRequires the matching VSS profile\u002Fmicroservice deployed and reachable. NGC-hosted models\u002FNIMs are subject to rate-limits, GPU-memory needs, and license terms; concurrency and storage limits depend on host hardware and the profile's compose file.\n\n## Troubleshooting\n\n- **Connection refused** → microservice not running: probe `\u002Fdocs` or `\u002Fhealth`, redeploy via `vss-deploy-profile`.\n- **HTTP 401\u002F403 on NGC pulls** → missing\u002Fexpired `NGC_CLI_API_KEY`: `docker login nvcr.io` and re-export the key.\n- **OOM \u002F model load failure** → insufficient GPU memory: use a smaller variant or `docker compose down` to free GPUs.\n\n# VSS Alert Management\n\nThe alerts profile runs in one of two modes (chosen at `\u002Fvss-deploy-profile -p alerts -m {verification,real-time}`) — see **The Two Modes** table below. This skill routes by **deployed mode + user intent** (monitoring vs subscription CRUD vs Slack webhook).\n\n## When to Use\n\n- Start\u002Fstop a real-time alert on a sensor (\"Start real-time alert for boxes dropped on warehouse_sample\")\n- Create\u002Flist\u002Fstop realtime subscription rules on Alert Bridge\n- Set up or manage Slack incident notifications\n- List or query detected incidents \u002F alerts; check verdicts (confirmed\u002Frejected\u002Funverified)\n- Add a new camera to the alerts pipeline; customize VLM-verifier prompts (CV mode)\n\n  tools: [webhook]\n---\n\n## Deployment prerequisite\n\nRequires the VSS **alerts** profile on `$HOST_IP` in either `verification` (CV) or `real-time` (VLM) mode.\n\n```bash\n# Either vss-rtvi-cv (CV mode) OR vss-rtvi-vlm (VLM mode) must be present.\ncurl -sf --max-time 5 \"http:\u002F\u002F${HOST_IP}:8000\u002Fdocs\" >\u002Fdev\u002Fnull \\\n  && docker ps --format '{{.Names}}' \\\n     | grep -qE '^(vss-rtvi-cv|vss-rtvi-vlm)$'\n```\n\nIf the probe fails, ask which mode to deploy and hand off to `\u002Fvss-deploy-profile -p alerts -m \u003Cmode>` (decline → stop; pre-authorized autonomous deploy → run directly with `verification` by default). If it passes, detect the mode per Step 1.\n\n---\n\n## The Two Modes (Deploy-Time Choice)\n\n| Mode | Deploy flag | Env (`.env`) | What runs | What is available |\n|---|---|---|---|---|\n| **CV (verification)** | `-m verification` | `MODE=2d_cv` | RT-CV (Grounding DINO) + Behavior Analytics + `alert-bridge` VLM verifier + **`rtvi-vlm`** | **Both** static CV pipeline (Workflow A) **and** dynamic VLM real-time alerts (Workflows B\u002FD) |\n| **VLM (real-time)** | `-m real-time` | `MODE=2d_vlm` | `alert-bridge` + `rtvi-vlm` | **Only** dynamic VLM real-time alerts (Workflows B\u002FD) and `alert-bridge` backend. No static CV pipeline. |\n\n**Switching modes** uses the `vss-deploy-profile` teardown + deploy flow with the other `-m` flag (VLM → CV adds the CV pipeline; CV → VLM tears it down). `rtvi-vlm` runs in both modes.\n\n---\n\n## Step 1 — Detect the Currently Deployed Mode\n\nBefore running any alert workflow, check which mode is live. Use **CV-only** containers as the signal — `vss-rtvi-vlm` is **not** a reliable mode signal because it runs in both modes.\n\n```bash\n# CV verification mode (vss-behavior-analytics + vss-rtvi-cv are CV-only)\ndocker ps --format '{{.Names}}' | grep -qx vss-behavior-analytics && echo \"mode=CV\"\n\n# VLM real-time mode (no CV pipeline; vss-rtvi-vlm still runs)\ndocker ps --format '{{.Names}}' | grep -qx vss-behavior-analytics || \\\n  docker ps --format '{{.Names}}' | grep -qx vss-rtvi-vlm && echo \"mode=VLM\"\n```\n\nIf `vss-behavior-analytics` is present → **CV mode** (which also has `vss-rtvi-vlm`).\nIf only `vss-rtvi-vlm` is present (and no CV pipeline) → **VLM mode**.\nIf neither matches, the alerts profile is not deployed — direct the user to the `vss-deploy-profile` skill.\n\nAlternative signal (preferred when `docker ps` isn't accessible): check the profile's `generated.env`:\n\n```bash\ngrep -E '^MODE=' deploy\u002Fdocker\u002Fdeveloper-profiles\u002Fdev-profile-alerts\u002Fgenerated.env\n# MODE=2d_cv   → CV mode (full superset)\n# MODE=2d_vlm  → VLM real-time mode (vss-rtvi-vlm only; no vss-rtvi-cv)\n```\n\n---\n\n## Step 2 — Route by Deployed Mode\n\n| Deployed mode | User asks about… | Action |\n|---|---|---|\n| **VLM real-time** | Slack webhook setup\u002Fstatus\u002Ftest\u002Fstop | **Workflow E** — `references\u002Falert-notify.md` |\n| **VLM real-time** | rule CRUD, or a realtime alert on a sensor with a detection condition, or stop\u002Fdelete a named alert (by `alert_type`\u002Fcondition or rule ID) | **Workflow D** — `references\u002Falert-subscriptions.md` (incl. two-step stop\u002Fconfirm) |\n| **CV verification** | subscription\u002Frule CRUD or Slack\u002Fnotification setup | Refuse — see canonical refusal text below |\n| **CV or VLM** | generic start\u002Fstop monitoring **without** a detection condition | **Workflow B (VLM)** — call the VSS Agent; `rtvi-vlm` runs in both modes |\n| **CV or VLM** | incident lookup \u002F *what happened* (recent alerts, time-range, casual \"any alerts today?\") | **Workflow C (Query)** — works on both; **always run the query, never answer from memory** |\n| **CV** | static CV alert onboarding \u002F verdict-prompt customization | **Workflow A (CV)** — onboard RTSP via `vss-manage-video-io-storage`; pipeline auto-picks it up |\n| **VLM** | a CV \u002F behavior-analytics \u002F PPE-rule alert needing the static CV pipeline | **Redeployment required** — confirm first, then `vss-deploy-profile -m verification` |\n\n**Always confirm before triggering a redeploy.** A mode switch stops all currently-running monitoring and restarts services.\n\n### Intent precedence (first match wins)\n\n1. **Workflow E (Slack)** — Slack-specific keywords (`slack`, `webhook` + `slack`, `bot token`, `slack channel`). `notify` alone is **not** sufficient.\n2. **Workflow D (Subscriptions)** — sensor **plus** a detection condition, rule CRUD keywords (`rule`, `subscription`, rule ID), **or stopping\u002Fdeleting a named alert by type\u002Fcondition** (\"stop the PPE alert\", \"delete the collision rule\"). A named `alert_type`\u002Fcondition = an existing **rule** → D's two-step stop protocol (`GET \u002Fapi\u002Fv1\u002Frealtime` → yes\u002Fno confirm → delete), never Workflow B.\n3. **Workflow B (VLM monitoring)** — generic start\u002Fstop on a sensor with **no** detection condition and **no** alert-type qualifier (\"start\u002Fstop real-time alert for sensor X\"). A stop that names a type (\"stop the **PPE** alert\") is a rule stop → Workflow D.\n4. **Workflow C (Query)** — incident lookup \u002F *what happened* (`show\u002Flist incidents`, `recent alerts`, time-range queries, **and casual \"any alerts…?\" \u002F \"any alerts so far today?\" \u002F \"what's been triggered?\" phrasings**). Bare `alerts` (without `rule`\u002F`subscription`\u002F`active rules`) means **incidents** → Workflow C, never Workflow D.\n5. **Workflow A (CV)** — CV deployment handling for anything not matched above.\n\n> **`alerts` vs `alert rules` (C vs D) — pick exactly one, never both:**\n> *what happened \u002F has been triggered* (incidents) → **Workflow C**\n> (`POST \u002Fgenerate` or `GET \u002Fapi\u002Fv1\u002Frealtime\u002Fincidents`). *What\n> rules\u002Fsubscriptions are configured or active* → **Workflow D** (the\n> **bare** `GET \u002Fapi\u002Fv1\u002Frealtime`, no `\u002Fincidents`). Bare `alerts` =\n> incidents (C); `alert rules` \u002F `subscriptions` \u002F `active rules` =\n> inventory (D). Never answer from memory; run the one correct call —\n> full endpoint detail in Workflow C below.\n\n**Disambiguation (B vs D):** if a sensor is named with start\u002Fmonitor language but the detection condition is unclear, ask:\n> *\"Do you want me to (a) create a persistent alert rule on Alert Bridge that keeps running until you delete it, or (b) start a one-time monitoring session via the VSS Agent?\"*\n\n**Stop routing (B vs D):** \"Stop the **&lt;type&gt;** alert\" (names an `alert_type`\u002Fcondition like PPE, collision, fire) = stop a **subscription rule** → **Workflow D** (find via `GET \u002Fapi\u002Fv1\u002Frealtime`, then the two-step stop\u002Fconfirm protocol in `references\u002Falert-subscriptions.md`; do **not** call `POST \u002Fgenerate`). A bare \"stop real-time alert \u002F stop monitoring on &lt;sensor&gt;\" with **no** type qualifier = Workflow B.\n\nIf a prompt mixes workflows (\"start monitoring and send to Slack\"), ask one clarifying question to split execution order.\n\n### CV-mode refusal text for D and E intents\n\nWhen the deployed mode is CV verification and the user asks for an alert-subscription or Slack\u002Fnotification intent, refuse with this message verbatim:\n\n> \"Alert subscriptions and Slack notifications are only supported in VLM real-time mode. Your current deployment is `\u003CCV verification | not deployed>`. To use these features, redeploy with `\u002Fvss-deploy-profile -p alerts -m real-time` (note: switching tears down current CV monitoring).\"\n\nNo auto-redeploy. The user decides whether to switch modes.\n\n---\n\n## Prereq for Either Mode: Sensor Must Be in VIOS\n\nBoth modes require the camera registered in VIOS first (via the `vss-manage-video-io-storage` skill):\n\n- RTSP URL \u002F IP camera → add it with `POST \u002Fsensor\u002Fadd` (that skill's Section 6); record the `sensorId` \u002F name.\n- Named existing sensor → confirm it appears in `GET \u002Fsensor\u002Flist` before proceeding.\n\nOn **CV**, adding the RTSP is the *entire* onboarding step (pipeline auto-picks it up). On **VLM**, it is a prerequisite to Workflow B.\n\n---\n\n## The Agent `\u002Fgenerate` Endpoint\n\nAll VLM-flow actions and all query actions go through the VSS Agent's natural-language endpoint:\n\n```bash\nAGENT=\"http:\u002F\u002F\u003CAGENT_ENDPOINT>\"   # default http:\u002F\u002Flocalhost:8000 on the alerts profile\n\ncurl -s -X POST \"$AGENT\u002Fgenerate\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"input_message\": \"\u003Cnatural-language request>\"}' | jq .\n```\n\n**Endpoint resolution:** use the agent endpoint from the active VSS deployment context. If unavailable, ask the user. Do not discover via filesystem.\n\n**Availability check:** `curl -sf --connect-timeout 5 \"$AGENT\u002Fdocs\"`.\n\nDo not call the `rtvi-vlm` microservice endpoints directly — always go through the agent. The agent internally dispatches to `rtvi_vlm_alert`, `rtvi_prompt_gen`, and `video_analytics_mcp.get_incidents`.\n\n---\n\n## Workflow A — CV Mode (`-m verification` \u002F `MODE=2d_cv`)\n\nCV alerts are **deployment-driven, not request-driven** — there is no agent\ncall to \"create\" one.\n\n1. Check if the sensor is in VIOS via `vss-manage-video-io-storage`'s `GET \u002Fsensor\u002Flist` (idempotent — don't blindly `POST \u002Fsensor\u002Fadd`).\n2. If missing, onboard via that skill's `POST \u002Fsensor\u002Fadd`. The CV pipeline auto-picks up the stream once registered and online.\n3. Confirm online: `curl -s \"http:\u002F\u002F\u003CVST_ENDPOINT>\u002Fvst\u002Fapi\u002Fv1\u002Fsensor\u002F\u003CsensorId>\u002Fstatus\" | jq .`\n4. Alerts land in Elasticsearch (Behavior Analytics → `alert-bridge` verification per `alert_type_config.json`). Query with **Workflow C**.\n\nA static-CV-pipeline alert on a VLM-only deployment is a mode mismatch — see the routing table above.\n\n---\n\n## Workflow B — VLM Real-time Monitoring (CV or VLM mode)\n\nGeneric start \u002F stop intents through the VSS Agent for a named sensor\nwithout a detection condition (if a condition is present, route to\nWorkflow D). `rtvi-vlm` runs in both modes.\n\n```bash\n# start: input_message = \"Start real-time alert for sensor \u003Cid>\"\n# stop:  input_message = \"Stop real-time alert for sensor \u003Cid>\"\ncurl -s -X POST \"$AGENT\u002Fgenerate\" -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"input_message\": \"\u003Cstart|stop> real-time alert for sensor \u003Cid>\"}' | jq .\n```\n\nUnder the hood: `rtvi_prompt_gen` → `rtvi_vlm_alert action=\"start\"`.\nEvery chunk is captioned; a chunk whose VLM response contains `yes`\u002F`true`\n(case-insensitive) publishes an incident to `mdx-vlm-incidents`. Prompts\nmust force a Yes\u002FNo answer. A static-CV-pipeline request on a VLM-only\ndeployment is a mode mismatch — see the routing table.\n\n---\n\n## Workflow D — Alert Subscriptions (VLM real-time mode only)\n\nCreate \u002F list \u002F delete persistent realtime alert rules on Alert Bridge.\nRoute here when the prompt has rule keywords (`rule`, `subscription`, a rule\nID) **or** when it pairs a specific sensor with a specific detection\ncondition (e.g. \"Set up a realtime alert on warehouse-dock-1 for PPE\nviolations\", \"Watch sensor entrance-1 for tailgating\", \"Stop rule\n496aebd1-…\").\n\n**Not here:** generic start\u002Fstop without a condition (→ Workflow B) or Slack\noperations (→ Workflow E).\n\nLoad and follow `references\u002Falert-subscriptions.md` as the authoritative\nplaybook for subscription CRUD. VLM real-time mode only; refuse with the\ncanonical refusal text on CV.\n\n---\n\n## Workflow E — Slack Notifications (VLM real-time mode only)\n\nUse when the user **explicitly mentions Slack or the webhook relay** (start\u002Fstop webhook server, check status\u002Fhealth, send a test message, set Slack channel\u002Ftoken). The word `notify` alone is **not** enough.\n\n> **`alert-notify` (port 9090) ≠ `vss-alert-bridge` (`\u002Fapi\u002Fv1\u002Frealtime`).**\n> Do NOT touch `vss-alert-bridge` for Slack ops.\n\nRoutes here: \"Set up Slack notifications\", \"Check if alert-notify is running\", \"Send a test alert to Slack\". Does **not** route here: \"Notify me when someone enters the zone\" (→ D\u002FB), \"Alert and notify on my phone\" (ambiguous — ask).\n\nLoad and follow `references\u002Falert-notify.md`. Code lives in `scripts\u002Falert-notify\u002F`. VLM real-time mode only.\n\n---\n\n## Workflow C — Query \u002F List Alerts (works on either mode)\n\nBoth CV- and VLM-generated alerts land in Elasticsearch and are\nqueryable via the agent's `video_analytics_mcp.get_incidents` tool. POST\nnatural-language requests to `$AGENT\u002Fgenerate` — \"Show me recent alerts\nfor sensor X\", \"List confirmed alerts from the last hour\", \"Show\ncollision incidents from Camera_02 between `\u003CISO>` and `\u003CISO>`\".\n\n**Casual phrasings route here too.** Questions like \"Any alerts so far\ntoday?\", \"Any alerts today?\", \"What's been triggered?\", or \"Anything\ndetected lately?\" are incident queries — issue a `POST \u002Fgenerate` (e.g.\n`{\"input_message\": \"List alerts from today\"}`) and summarize the result.\n**Never answer these from memory and never reply \"no alerts\" without\nrunning the query.** A bare \"alerts\" question is *always* an incident\nlookup (Workflow C), not a subscription-rule listing (Workflow D).\n\n> **Two valid incident endpoints:** (1) `POST \u002Fgenerate` —\n> natural-language questions via the VSS Agent; (2)\n> `GET http:\u002F\u002F\u003CHOST>:9080\u002Fapi\u002Fv1\u002Frealtime\u002Fincidents` — Alert Bridge\n> **incidents** endpoint (params `sensor_id`, `start_time`, `end_time`\n> ISO-8601, `limit`, `offset`; response has `total`, `count`,\n> `incidents[]`). **Prefer (2) for counts\u002Ffiltered lists** — read `total`\n> for \"how many\".\n>\n> ```bash\n> curl -sf \"http:\u002F\u002F\u003CHOST>:9080\u002Fapi\u002Fv1\u002Frealtime\u002Fincidents?sensor_id=\u003CUUID>&start_time=\u003CISO>\" | jq '.total'\n> ```\n>\n> **Do NOT list subscription rules for an incident query.** The **bare**\n> `GET \u002Fapi\u002Fv1\u002Frealtime` (no `\u002Fincidents`) lists *rules* (Workflow D) and\n> is wrong for \"what happened\" — never call\u002Fprobe it or load the Workflow\n> D playbook for an incident query. The `\u002Fincidents` endpoint above is a\n> **different** endpoint and **is** allowed here.\n>\n> **Empty result is a valid answer.** If no incidents match (e.g. a\n> freshly deployed system with no activity yet), report that **none were\n> found \u002F the count is 0** for the requested period and STOP — do not fall\n> back to listing rules or hunting other endpoints.\n\nFor\nricher \u002F non-natural-language filtering (sensor-level, time-series,\ncounts) use the **`vss-query-analytics` skill** (VA-MCP on port 9901).\n\n### Verdict interpretation & CV verifier prompts (CV mode only)\n\nCV alerts carry a VLM verification verdict (`confirmed` \u002F `rejected` \u002F\n`unverified`); VLM real-time incidents have no separate verdict (the\ntrigger is itself a Yes\u002FNo VLM answer). CV-path verifier prompts are\ncustomizable via `alert_type_config.json` (restart `alert-bridge` to\napply). See `references\u002Fcv-verifier-prompts.md` for the verdict table,\nfield meanings, and the prompt-customization rules.\n\n---\n\n## Cross-Skill Links\n\n| Task | Skill |\n|---|---|\n| Deploy, redeploy, or switch alert mode | **`vss-deploy-profile`** — `-p alerts -m {verification,real-time}` |\n| Add an RTSP\u002FIP camera, list sensors, snapshots, clips | **`vss-manage-video-io-storage`** (Section 6 for Add Sensor) |\n| Time-range incident \u002F occupancy \u002F PPE metrics from Elasticsearch | **`vss-query-analytics`** (VA-MCP :9901) |\n| Detailed incident report from an alert | **`vss-generate-video-report`** |\n| Subscriptions \u002F Slack sub-workflows | `references\u002Falert-subscriptions.md`, `references\u002Falert-notify.md` (code in `scripts\u002Falert-notify\u002F`) |\n\n---\n\n## Gotchas\n\n- **`alert-notify` (port 9090) ≠ `vss-alert-bridge`.** Slack ops → Workflow E (`alert-notify`); never route Slack to `vss-alert-bridge`'s `\u002Fapi\u002Fv1\u002Frealtime`.\n- **Workflow scope by mode:** A is CV-only; B and C work on either mode; D and E are VLM real-time only (refuse on CV with the canonical text).\n- **Don't use `vss-rtvi-vlm` as a mode signal** — it runs in both modes. Use `vss-behavior-analytics` (CV-only) or the `MODE` env var.\n- **A mode switch tears down the current deployment** — running VLM streams and un-persisted CV alert state are lost.\n- **Always go through `$AGENT\u002Fgenerate`** — never call `rtvi-vlm` directly. The VLM trigger is a `\"yes\"`\u002F`\"true\"` token match (case-insensitive); `rtvi_prompt_gen` enforces the Yes\u002FNo pattern, so don't hand-craft prompts that break it.\n- **Sensor must already be in VIOS** for either mode (use `vss-manage-video-io-storage` for RTSP-only inputs).\n\nbump:1\n","## Purpose\n\nOperate the VSS alert pipeline (mode detection, Alert-Bridge subscriptions, Slack notifications, queries, camera onboarding, verifier-prompt customization).\n\n## Prerequisites\n\n- Active VSS deployment reachable on `$HOST_IP` (see `vss-deploy-profile` and `references\u002F`).\n- NGC credentials in `$NGC_CLI_API_KEY` and `$NVIDIA_API_KEY` for any image pulls.\n- `curl`, `jq`, and Docker available on the caller.\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` and helper scripts live in `scripts\u002F` — call them via `run_script` when the skill points to a script by name.\n\n## Examples\n\nRunnable end-to-end scenarios live under `evals\u002F` (each `*.json` manifest); inline `curl` blocks appear in each workflow below. Replay with `nv-base validate \u003Cthis-skill-dir> --agent-eval`.\n\n## Limitations\n\nRequires the matching VSS profile\u002Fmicroservice deployed and reachable. NGC-hosted models\u002FNIMs are subject to rate-limits, GPU-memory needs, and license terms; concurrency and storage limits depend on host hardware and the profile's compose file.\n\n## Troubleshooting\n\n- **Connection refused** → microservice not running: probe `\u002Fdocs` or `\u002Fhealth`, redeploy via `vss-deploy-profile`.\n- **HTTP 401\u002F403 on NGC pulls** → missing\u002Fexpired `NGC_CLI_API_KEY`: `docker login nvcr.io` and re-export the key.\n- **OOM \u002F model load failure** → insufficient GPU memory: use a smaller variant or `docker compose down` to free GPUs.\n\n# VSS Alert Management\n\nThe alerts profile runs in one of two modes (chosen at `\u002Fvss-deploy-profile -p alerts -m {verification,real-time}`) — see **The Two Modes** table below. This skill routes by **deployed mode + user intent** (monitoring vs subscription CRUD vs Slack webhook).\n\n## When to Use\n\n- Start\u002Fstop a real-time alert on a sensor (\"Start real-time alert for boxes dropped on warehouse_sample\")\n- Create\u002Flist\u002Fstop realtime subscription rules on Alert Bridge\n- Set up or manage Slack incident notifications\n- List or query detected incidents \u002F alerts; check verdicts (confirmed\u002Frejected\u002Funverified)\n- Add a new camera to the alerts pipeline; customize VLM-verifier prompts (CV mode)\n\n  tools: [webhook]\n---\n\n## Deployment prerequisite\n\nRequires the VSS **alerts** profile on `$HOST_IP` in either `verification` (CV) or `real-time` (VLM) mode.\n\n```bash\n# Either vss-rtvi-cv (CV mode) OR vss-rtvi-vlm (VLM mode) must be present.\ncurl -sf --max-time 5 \"http:\u002F\u002F${HOST_IP}:8000\u002Fdocs\" >\u002Fdev\u002Fnull \\\n  && docker ps --format '{{.Names}}' \\\n     | grep -qE '^(vss-rtvi-cv|vss-rtvi-vlm)$'\n```\n\nIf the probe fails, ask which mode to deploy and hand off to `\u002Fvss-deploy-profile -p alerts -m \u003Cmode>` (decline → stop; pre-authorized autonomous deploy → run directly with `verification` by default). If it passes, detect the mode per Step 1.\n\n---\n\n## The Two Modes (Deploy-Time Choice)\n\n| Mode | Deploy flag | Env (`.env`) | What runs | What is available |\n|---|---|---|---|---|\n| **CV (verification)** | `-m verification` | `MODE=2d_cv` | RT-CV (Grounding DINO) + Behavior Analytics + `alert-bridge` VLM verifier + **`rtvi-vlm`** | **Both** static CV pipeline (Workflow A) **and** dynamic VLM real-time alerts (Workflows B\u002FD) |\n| **VLM (real-time)** | `-m real-time` | `MODE=2d_vlm` | `alert-bridge` + `rtvi-vlm` | **Only** dynamic VLM real-time alerts (Workflows B\u002FD) and `alert-bridge` backend. No static CV pipeline. |\n\n**Switching modes** uses the `vss-deploy-profile` teardown + deploy flow with the other `-m` flag (VLM → CV adds the CV pipeline; CV → VLM tears it down). `rtvi-vlm` runs in both modes.\n\n---\n\n## Step 1 — Detect the Currently Deployed Mode\n\nBefore running any alert workflow, check which mode is live. Use **CV-only** containers as the signal — `vss-rtvi-vlm` is **not** a reliable mode signal because it runs in both modes.\n\n```bash\n# CV verification mode (vss-behavior-analytics + vss-rtvi-cv are CV-only)\ndocker ps --format '{{.Names}}' | grep -qx vss-behavior-analytics && echo \"mode=CV\"\n\n# VLM real-time mode (no CV pipeline; vss-rtvi-vlm still runs)\ndocker ps --format '{{.Names}}' | grep -qx vss-behavior-analytics || \\\n  docker ps --format '{{.Names}}' | grep -qx vss-rtvi-vlm && echo \"mode=VLM\"\n```\n\nIf `vss-behavior-analytics` is present → **CV mode** (which also has `vss-rtvi-vlm`).\nIf only `vss-rtvi-vlm` is present (and no CV pipeline) → **VLM mode**.\nIf neither matches, the alerts profile is not deployed — direct the user to the `vss-deploy-profile` skill.\n\nAlternative signal (preferred when `docker ps` isn't accessible): check the profile's `generated.env`:\n\n```bash\ngrep -E '^MODE=' deploy\u002Fdocker\u002Fdeveloper-profiles\u002Fdev-profile-alerts\u002Fgenerated.env\n# MODE=2d_cv   → CV mode (full superset)\n# MODE=2d_vlm  → VLM real-time mode (vss-rtvi-vlm only; no vss-rtvi-cv)\n```\n\n---\n\n## Step 2 — Route by Deployed Mode\n\n| Deployed mode | User asks about… | Action |\n|---|---|---|\n| **VLM real-time** | Slack webhook setup\u002Fstatus\u002Ftest\u002Fstop | **Workflow E** — `references\u002Falert-notify.md` |\n| **VLM real-time** | rule CRUD, or a realtime alert on a sensor with a detection condition, or stop\u002Fdelete a named alert (by `alert_type`\u002Fcondition or rule ID) | **Workflow D** — `references\u002Falert-subscriptions.md` (incl. two-step stop\u002Fconfirm) |\n| **CV verification** | subscription\u002Frule CRUD or Slack\u002Fnotification setup | Refuse — see canonical refusal text below |\n| **CV or VLM** | generic start\u002Fstop monitoring **without** a detection condition | **Workflow B (VLM)** — call the VSS Agent; `rtvi-vlm` runs in both modes |\n| **CV or VLM** | incident lookup \u002F *what happened* (recent alerts, time-range, casual \"any alerts today?\") | **Workflow C (Query)** — works on both; **always run the query, never answer from memory** |\n| **CV** | static CV alert onboarding \u002F verdict-prompt customization | **Workflow A (CV)** — onboard RTSP via `vss-manage-video-io-storage`; pipeline auto-picks it up |\n| **VLM** | a CV \u002F behavior-analytics \u002F PPE-rule alert needing the static CV pipeline | **Redeployment required** — confirm first, then `vss-deploy-profile -m verification` |\n\n**Always confirm before triggering a redeploy.** A mode switch stops all currently-running monitoring and restarts services.\n\n### Intent precedence (first match wins)\n\n1. **Workflow E (Slack)** — Slack-specific keywords (`slack`, `webhook` + `slack`, `bot token`, `slack channel`). `notify` alone is **not** sufficient.\n2. **Workflow D (Subscriptions)** — sensor **plus** a detection condition, rule CRUD keywords (`rule`, `subscription`, rule ID), **or stopping\u002Fdeleting a named alert by type\u002Fcondition** (\"stop the PPE alert\", \"delete the collision rule\"). A named `alert_type`\u002Fcondition = an existing **rule** → D's two-step stop protocol (`GET \u002Fapi\u002Fv1\u002Frealtime` → yes\u002Fno confirm → delete), never Workflow B.\n3. **Workflow B (VLM monitoring)** — generic start\u002Fstop on a sensor with **no** detection condition and **no** alert-type qualifier (\"start\u002Fstop real-time alert for sensor X\"). A stop that names a type (\"stop the **PPE** alert\") is a rule stop → Workflow D.\n4. **Workflow C (Query)** — incident lookup \u002F *what happened* (`show\u002Flist incidents`, `recent alerts`, time-range queries, **and casual \"any alerts…?\" \u002F \"any alerts so far today?\" \u002F \"what's been triggered?\" phrasings**). Bare `alerts` (without `rule`\u002F`subscription`\u002F`active rules`) means **incidents** → Workflow C, never Workflow D.\n5. **Workflow A (CV)** — CV deployment handling for anything not matched above.\n\n> **`alerts` vs `alert rules` (C vs D) — pick exactly one, never both:**\n> *what happened \u002F has been triggered* (incidents) → **Workflow C**\n> (`POST \u002Fgenerate` or `GET \u002Fapi\u002Fv1\u002Frealtime\u002Fincidents`). *What\n> rules\u002Fsubscriptions are configured or active* → **Workflow D** (the\n> **bare** `GET \u002Fapi\u002Fv1\u002Frealtime`, no `\u002Fincidents`). Bare `alerts` =\n> incidents (C); `alert rules` \u002F `subscriptions` \u002F `active rules` =\n> inventory (D). Never answer from memory; run the one correct call —\n> full endpoint detail in Workflow C below.\n\n**Disambiguation (B vs D):** if a sensor is named with start\u002Fmonitor language but the detection condition is unclear, ask:\n> *\"Do you want me to (a) create a persistent alert rule on Alert Bridge that keeps running until you delete it, or (b) start a one-time monitoring session via the VSS Agent?\"*\n\n**Stop routing (B vs D):** \"Stop the **&lt;type&gt;** alert\" (names an `alert_type`\u002Fcondition like PPE, collision, fire) = stop a **subscription rule** → **Workflow D** (find via `GET \u002Fapi\u002Fv1\u002Frealtime`, then the two-step stop\u002Fconfirm protocol in `references\u002Falert-subscriptions.md`; do **not** call `POST \u002Fgenerate`). A bare \"stop real-time alert \u002F stop monitoring on &lt;sensor&gt;\" with **no** type qualifier = Workflow B.\n\nIf a prompt mixes workflows (\"start monitoring and send to Slack\"), ask one clarifying question to split execution order.\n\n### CV-mode refusal text for D and E intents\n\nWhen the deployed mode is CV verification and the user asks for an alert-subscription or Slack\u002Fnotification intent, refuse with this message verbatim:\n\n> \"Alert subscriptions and Slack notifications are only supported in VLM real-time mode. Your current deployment is `\u003CCV verification | not deployed>`. To use these features, redeploy with `\u002Fvss-deploy-profile -p alerts -m real-time` (note: switching tears down current CV monitoring).\"\n\nNo auto-redeploy. The user decides whether to switch modes.\n\n---\n\n## Prereq for Either Mode: Sensor Must Be in VIOS\n\nBoth modes require the camera registered in VIOS first (via the `vss-manage-video-io-storage` skill):\n\n- RTSP URL \u002F IP camera → add it with `POST \u002Fsensor\u002Fadd` (that skill's Section 6); record the `sensorId` \u002F name.\n- Named existing sensor → confirm it appears in `GET \u002Fsensor\u002Flist` before proceeding.\n\nOn **CV**, adding the RTSP is the *entire* onboarding step (pipeline auto-picks it up). On **VLM**, it is a prerequisite to Workflow B.\n\n---\n\n## The Agent `\u002Fgenerate` Endpoint\n\nAll VLM-flow actions and all query actions go through the VSS Agent's natural-language endpoint:\n\n```bash\nAGENT=\"http:\u002F\u002F\u003CAGENT_ENDPOINT>\"   # default http:\u002F\u002Flocalhost:8000 on the alerts profile\n\ncurl -s -X POST \"$AGENT\u002Fgenerate\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"input_message\": \"\u003Cnatural-language request>\"}' | jq .\n```\n\n**Endpoint resolution:** use the agent endpoint from the active VSS deployment context. If unavailable, ask the user. Do not discover via filesystem.\n\n**Availability check:** `curl -sf --connect-timeout 5 \"$AGENT\u002Fdocs\"`.\n\nDo not call the `rtvi-vlm` microservice endpoints directly — always go through the agent. The agent internally dispatches to `rtvi_vlm_alert`, `rtvi_prompt_gen`, and `video_analytics_mcp.get_incidents`.\n\n---\n\n## Workflow A — CV Mode (`-m verification` \u002F `MODE=2d_cv`)\n\nCV alerts are **deployment-driven, not request-driven** — there is no agent\ncall to \"create\" one.\n\n1. Check if the sensor is in VIOS via `vss-manage-video-io-storage`'s `GET \u002Fsensor\u002Flist` (idempotent — don't blindly `POST \u002Fsensor\u002Fadd`).\n2. If missing, onboard via that skill's `POST \u002Fsensor\u002Fadd`. The CV pipeline auto-picks up the stream once registered and online.\n3. Confirm online: `curl -s \"http:\u002F\u002F\u003CVST_ENDPOINT>\u002Fvst\u002Fapi\u002Fv1\u002Fsensor\u002F\u003CsensorId>\u002Fstatus\" | jq .`\n4. Alerts land in Elasticsearch (Behavior Analytics → `alert-bridge` verification per `alert_type_config.json`). Query with **Workflow C**.\n\nA static-CV-pipeline alert on a VLM-only deployment is a mode mismatch — see the routing table above.\n\n---\n\n## Workflow B — VLM Real-time Monitoring (CV or VLM mode)\n\nGeneric start \u002F stop intents through the VSS Agent for a named sensor\nwithout a detection condition (if a condition is present, route to\nWorkflow D). `rtvi-vlm` runs in both modes.\n\n```bash\n# start: input_message = \"Start real-time alert for sensor \u003Cid>\"\n# stop:  input_message = \"Stop real-time alert for sensor \u003Cid>\"\ncurl -s -X POST \"$AGENT\u002Fgenerate\" -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"input_message\": \"\u003Cstart|stop> real-time alert for sensor \u003Cid>\"}' | jq .\n```\n\nUnder the hood: `rtvi_prompt_gen` → `rtvi_vlm_alert action=\"start\"`.\nEvery chunk is captioned; a chunk whose VLM response contains `yes`\u002F`true`\n(case-insensitive) publishes an incident to `mdx-vlm-incidents`. Prompts\nmust force a Yes\u002FNo answer. A static-CV-pipeline request on a VLM-only\ndeployment is a mode mismatch — see the routing table.\n\n---\n\n## Workflow D — Alert Subscriptions (VLM real-time mode only)\n\nCreate \u002F list \u002F delete persistent realtime alert rules on Alert Bridge.\nRoute here when the prompt has rule keywords (`rule`, `subscription`, a rule\nID) **or** when it pairs a specific sensor with a specific detection\ncondition (e.g. \"Set up a realtime alert on warehouse-dock-1 for PPE\nviolations\", \"Watch sensor entrance-1 for tailgating\", \"Stop rule\n496aebd1-…\").\n\n**Not here:** generic start\u002Fstop without a condition (→ Workflow B) or Slack\noperations (→ Workflow E).\n\nLoad and follow `references\u002Falert-subscriptions.md` as the authoritative\nplaybook for subscription CRUD. VLM real-time mode only; refuse with the\ncanonical refusal text on CV.\n\n---\n\n## Workflow E — Slack Notifications (VLM real-time mode only)\n\nUse when the user **explicitly mentions Slack or the webhook relay** (start\u002Fstop webhook server, check status\u002Fhealth, send a test message, set Slack channel\u002Ftoken). The word `notify` alone is **not** enough.\n\n> **`alert-notify` (port 9090) ≠ `vss-alert-bridge` (`\u002Fapi\u002Fv1\u002Frealtime`).**\n> Do NOT touch `vss-alert-bridge` for Slack ops.\n\nRoutes here: \"Set up Slack notifications\", \"Check if alert-notify is running\", \"Send a test alert to Slack\". Does **not** route here: \"Notify me when someone enters the zone\" (→ D\u002FB), \"Alert and notify on my phone\" (ambiguous — ask).\n\nLoad and follow `references\u002Falert-notify.md`. Code lives in `scripts\u002Falert-notify\u002F`. VLM real-time mode only.\n\n---\n\n## Workflow C — Query \u002F List Alerts (works on either mode)\n\nBoth CV- and VLM-generated alerts land in Elasticsearch and are\nqueryable via the agent's `video_analytics_mcp.get_incidents` tool. POST\nnatural-language requests to `$AGENT\u002Fgenerate` — \"Show me recent alerts\nfor sensor X\", \"List confirmed alerts from the last hour\", \"Show\ncollision incidents from Camera_02 between `\u003CISO>` and `\u003CISO>`\".\n\n**Casual phrasings route here too.** Questions like \"Any alerts so far\ntoday?\", \"Any alerts today?\", \"What's been triggered?\", or \"Anything\ndetected lately?\" are incident queries — issue a `POST \u002Fgenerate` (e.g.\n`{\"input_message\": \"List alerts from today\"}`) and summarize the result.\n**Never answer these from memory and never reply \"no alerts\" without\nrunning the query.** A bare \"alerts\" question is *always* an incident\nlookup (Workflow C), not a subscription-rule listing (Workflow D).\n\n> **Two valid incident endpoints:** (1) `POST \u002Fgenerate` —\n> natural-language questions via the VSS Agent; (2)\n> `GET http:\u002F\u002F\u003CHOST>:9080\u002Fapi\u002Fv1\u002Frealtime\u002Fincidents` — Alert Bridge\n> **incidents** endpoint (params `sensor_id`, `start_time`, `end_time`\n> ISO-8601, `limit`, `offset`; response has `total`, `count`,\n> `incidents[]`). **Prefer (2) for counts\u002Ffiltered lists** — read `total`\n> for \"how many\".\n>\n> ```bash\n> curl -sf \"http:\u002F\u002F\u003CHOST>:9080\u002Fapi\u002Fv1\u002Frealtime\u002Fincidents?sensor_id=\u003CUUID>&start_time=\u003CISO>\" | jq '.total'\n> ```\n>\n> **Do NOT list subscription rules for an incident query.** The **bare**\n> `GET \u002Fapi\u002Fv1\u002Frealtime` (no `\u002Fincidents`) lists *rules* (Workflow D) and\n> is wrong for \"what happened\" — never call\u002Fprobe it or load the Workflow\n> D playbook for an incident query. The `\u002Fincidents` endpoint above is a\n> **different** endpoint and **is** allowed here.\n>\n> **Empty result is a valid answer.** If no incidents match (e.g. a\n> freshly deployed system with no activity yet), report that **none were\n> found \u002F the count is 0** for the requested period and STOP — do not fall\n> back to listing rules or hunting other endpoints.\n\nFor\nricher \u002F non-natural-language filtering (sensor-level, time-series,\ncounts) use the **`vss-query-analytics` skill** (VA-MCP on port 9901).\n\n### Verdict interpretation & CV verifier prompts (CV mode only)\n\nCV alerts carry a VLM verification verdict (`confirmed` \u002F `rejected` \u002F\n`unverified`); VLM real-time incidents have no separate verdict (the\ntrigger is itself a Yes\u002FNo VLM answer). CV-path verifier prompts are\ncustomizable via `alert_type_config.json` (restart `alert-bridge` to\napply). See `references\u002Fcv-verifier-prompts.md` for the verdict table,\nfield meanings, and the prompt-customization rules.\n\n---\n\n## Cross-Skill Links\n\n| Task | Skill |\n|---|---|\n| Deploy, redeploy, or switch alert mode | **`vss-deploy-profile`** — `-p alerts -m {verification,real-time}` |\n| Add an RTSP\u002FIP camera, list sensors, snapshots, clips | **`vss-manage-video-io-storage`** (Section 6 for Add Sensor) |\n| Time-range incident \u002F occupancy \u002F PPE metrics from Elasticsearch | **`vss-query-analytics`** (VA-MCP :9901) |\n| Detailed incident report from an alert | **`vss-generate-video-report`** |\n| Subscriptions \u002F Slack sub-workflows | `references\u002Falert-subscriptions.md`, `references\u002Falert-notify.md` (code in `scripts\u002Falert-notify\u002F`) |\n\n---\n\n## Gotchas\n\n- **`alert-notify` (port 9090) ≠ `vss-alert-bridge`.** Slack ops → Workflow E (`alert-notify`); never route Slack to `vss-alert-bridge`'s `\u002Fapi\u002Fv1\u002Frealtime`.\n- **Workflow scope by mode:** A is CV-only; B and C work on either mode; D and E are VLM real-time only (refuse on CV with the canonical text).\n- **Don't use `vss-rtvi-vlm` as a mode signal** — it runs in both modes. Use `vss-behavior-analytics` (CV-only) or the `MODE` env var.\n- **A mode switch tears down the current deployment** — running VLM streams and un-persisted CV alert state are lost.\n- **Always go through `$AGENT\u002Fgenerate`** — never call `rtvi-vlm` directly. The VLM trigger is a `\"yes\"`\u002F`\"true\"` token match (case-insensitive); `rtvi_prompt_gen` enforces the Yes\u002FNo pattern, so don't hand-craft prompts that break it.\n- **Sensor must already be in VIOS** for either mode (use `vss-manage-video-io-storage` for RTSP-only inputs).\n\nbump:1\n",{"name":5,"license":15,"version":24,"category":25,"metadata":26,"description":7,"related_skills":31},"1.0.0","development-code",{"tags":27,"author":28,"version":29,"github-url":30},"nvidia blueprint operational","NVIDIA Video Search and Summarization Team \u003Cvss-team@nvidia.com>","3.2.0","https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Fvideo-search-and-summarization",[32],"vss-generate-video-report","main","d591030ef9fb1bbcebed3454aa5c2dcb8d608f69","skills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive","https:\u002F\u002Fai-agent.yyc3.vip\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-13 22:26:14",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill vss-manage-alerts",{"tool":47,"command":48},"bunx","bunx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill vss-manage-alerts",{"tool":50,"command":51},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill vss-manage-alerts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002FSKILL.md",true,[55,61,65,69,73,77,81,85,89,93,99,103,107,111,115,119,123],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"BENCHMARK.md","REFERENCE","参考文档",3420,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002FBENCHMARK.md",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"evals\u002Falerts_vlm_real_time.json",5660,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fevals\u002Falerts_vlm_real_time.json",{"path":66,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":68},"evals\u002Fevals.json",8767,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fevals\u002Fevals.json",{"path":70,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":71,"sourceHtmlUrl":72},"evals\u002Frouting_vlm_c_vs_d.json",2989,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fevals\u002Frouting_vlm_c_vs_d.json",{"path":74,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":75,"sourceHtmlUrl":76},"evals\u002Fsubscriptions_create_phrasings.json",8311,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fevals\u002Fsubscriptions_create_phrasings.json",{"path":78,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":79,"sourceHtmlUrl":80},"evals\u002Fsubscriptions_lifecycle.json",5450,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fevals\u002Fsubscriptions_lifecycle.json",{"path":82,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Falert-notify.md",16768,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Freferences\u002Falert-notify.md",{"path":86,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Falert-subscriptions.md",21713,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Freferences\u002Falert-subscriptions.md",{"path":90,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fcv-verifier-prompts.md",1690,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Freferences\u002Fcv-verifier-prompts.md",{"path":94,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":97,"sourceHtmlUrl":98},"scripts\u002Falert-notify\u002Fincident_utils.py","SCRIPT","脚本",2374,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fscripts\u002Falert-notify\u002Fincident_utils.py",{"path":100,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":101,"sourceHtmlUrl":102},"scripts\u002Falert-notify\u002Fnotifier_base.py",2413,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fscripts\u002Falert-notify\u002Fnotifier_base.py",{"path":104,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":105,"sourceHtmlUrl":106},"scripts\u002Falert-notify\u002Fopen_claw_dashboard_notifier.py",11507,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fscripts\u002Falert-notify\u002Fopen_claw_dashboard_notifier.py",{"path":108,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":109,"sourceHtmlUrl":110},"scripts\u002Falert-notify\u002Frequirements.txt",103,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fscripts\u002Falert-notify\u002Frequirements.txt",{"path":112,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":113,"sourceHtmlUrl":114},"scripts\u002Falert-notify\u002Fserver.py",15838,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fscripts\u002Falert-notify\u002Fserver.py",{"path":116,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":117,"sourceHtmlUrl":118},"scripts\u002Falert-notify\u002Fslack_notifier.py",8348,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fscripts\u002Falert-notify\u002Fslack_notifier.py",{"path":120,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":121,"sourceHtmlUrl":122},"skill-card.md",3964,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fskill-card.md",{"path":124,"resourceType":125,"resourceTypeDesc":126,"sizeBytes":127,"sourceHtmlUrl":128},"skill.oms.sig","OTHER","其他",8349,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fai-ml\u002Fnvidia-skills\u002Fskills\u002Fvss-manage-alerts\u002Fskill.oms.sig",[130,138,145,152,159,167],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":134,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":19},"01M7BTB92RE8MT5YE706QBNDTQ","yingmi-skill","当用户需要查询基金、策略、公告、财经资讯，做资产配置、组合诊断、风险回测、现金流分析，或生成图表、PDF 时，优先使用本 Skill 获取真实数据与可执行能力。","MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fyingmi-skill\u002FSKILL.md",[],[],{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":134,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":19},"01M7BT7ZYR091HPJYEFNWVTEJJ","web-access","所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fweb-access\u002FSKILL.md",[],[],{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":134,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":19},"01M7BT4NKS0DNP8A53M1BGGZR2","tencentmap-map-assistant","腾讯位置服务·地图助手 Skill，一句自然语言调用腾讯地图全套能力，无需开发者账号、开箱即用。提供 AI 旅游攻略、地点搜索（含评分\u002F人均\u002F营业时间）、关键词提示、路线规划（驾车\u002F步行\u002F公交\u002F骑行）、地址解析与逆解析、行政区划、IP 定位、距离计算、天气查询，并可将行程或多 POI 渲染成网页地图。涉及找地点、规划路线、旅游行程、查天气、坐标转换等出行场景时使用。","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Ftencentmap-map-assistant\u002FSKILL.md",[],[],{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":134,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":19},"01M7BSWKV1T5XYYRGV4W4JP88C","skill-scanner","Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描, 检查 skill 安全, audit skill, scan skill, check skill safety, analyze skill, inspect skill, verify skill, skill security, skill supply chain. Do NOT trigger for general agent usage, full system health checks, project debugging, or normal development.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-scanner\u002FSKILL.md",[],[],{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":163,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":19},"01M7BSWGTCFW7F123S4BM4XY6W","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized knowledge, workflows, or tool integrations.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":134,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":19},"01M7BSVV4DH8JK2ZMQSCW25VCD","shader-dev","Comprehensive GLSL shader techniques for creating stunning visual effects — ray marching, SDF modeling, fluid simulation, particle systems, procedural generation, lighting, post-processing, and more.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fshader-dev\u002FSKILL.md",[],[]]