[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78AXWFPF5C5C6S40JKMQG5P":3,"skill-same:01M78AXWFPF5C5C6S40JKMQG5P":99},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":14,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M78AXWFPF5C5C6S40JKMQG5P","vss-deploy-video-embedding",null,"Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `\u002Fv1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis\u002FKafka\u002FOTel integration, common failure modes, and teardown.","Solizardking\u002Ftrain2earn","Solizardking","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108096810?v=4","01M786KDB10AYV042N0F9BD5B5","Clawd","01M786KDC5C3NPE4W44C5641EZ",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vss-deploy-video-embedding\ndescription: >\n  Use this skill when deploying, operating, or integrating the VSS 3.2 GA\n  RT-Embed Video Embedding microservice. Covers Docker Compose bring-up,\n  GPU and storage prerequisites, the `\u002Fv1` REST API (file uploads,\n  text and video embeddings, live RTSP streams, health and metrics),\n  Redis\u002FKafka\u002FOTel integration, common failure modes, and teardown.\nlicense: Apache-2.0\nmetadata:\n  version: \"3.2.0\"\n  github-url: \"https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Fvideo-search-and-summarization\"\n  tags: \"nvidia blueprint operational deployment\"\n---\n\n# VSS Video Embedding (RT-Embed)\n\nUse this skill when you need to:\n\n- Deploy the VSS Video Embedding microservice from a Docker Compose file.\n- Generate text or video embeddings against the Cosmos-Embed1-448p model.\n- Embed an uploaded file, an HTTP\u002FS3\u002Ffile\u002Fdata URL, or a live RTSP stream.\n- Wire the service into a VSS deployment alongside Redis, Kafka, and OpenTelemetry.\n- Triage readiness, model-download, GPU, or stream-reconnection failures.\n\n**Trigger phrases:** `vss-deploy-video-embedding`, `RT-Embed`, `rtvi-embed`, `video embedding service`, `Cosmos-Embed1`, `embed live stream`, `embed video file`, `generate video embeddings`, `text embedding for video search`.\n\n## Service Snapshot\n\n- **VSS 3.2 GA skill:** `vss-deploy-video-embedding`.\n- **Legacy 3.1 name:** RT-Embed.\n- **Compose service:** `rtvi-embed`.\n- **Container name:** `vss-rtvi-embed`.\n- **Image:** `nvcr.io\u002Fnvidia\u002Fvss-core\u002Fvss-rt-embed` (override with `RTVI_EMBED_IMAGE`).\n- **Default tag:** `3.2.0` (override with `RTVI_EMBED_TAG`).\n- **Profile:** `bp_developer_search_2d`.\n- **Container port:** `8000` (host-side `${RTVI_EMBED_PORT}`).\n- **Default model:** `cosmos-embed1-448p` from `nvidia\u002FCosmos-Embed1-448p`.\n- **Health endpoint:** `GET \u002Fv1\u002Fready`.\n- **Healthcheck startup grace:** `1200s` (20 minutes) on first boot.\n\n## Prerequisites\n\nBefore bringing the service up:\n\n1. NVIDIA driver + NVIDIA Container Toolkit installed; default runtime set to `nvidia`.\n2. Docker Engine and Docker Compose plugin recent enough to support `${VAR:+value}` conditional volume substitution.\n3. `docker login nvcr.io` completed with `$oauthtoken` and a valid NGC API key.\n4. Host environment provides at minimum: `RTVI_EMBED_PORT`, `VSS_DATA_DIR`, `NGC_API_KEY`, and optionally `HF_TOKEN` to avoid Hugging Face 429 rate-limit errors during the Cosmos-Embed1 weights download.\n5. Free disk space for persistent caches: `rtvi-hf-cache`, `rtvi-ngc-model-cache`, `rtvi-triton-model-repo` (multi-GB).\n\nSee `references\u002Fdeploy-vss-deploy-video-embedding.md` for the full prerequisite list and `references\u002Fenvironment.md` for the variable matrix.\n\n## Deploy\n\nFor **standalone RT-Embed**, work from the service directory:\n\n```bash\ncd \"{{repo_root}}\u002Fdeploy\u002Fdocker\u002Fservices\u002Frtvi\u002Frtvi-embed\"\n```\n\nDo **not** use `\u002Fvss-deploy-profile` or `scripts\u002Fdev-profile.sh` for this standalone deployment.\n\nFor agent-driven validation, never let `sudo` prompt interactively. Before any\nprivileged ownership or Docker operation, use the non-interactive guard in\n[`references\u002Fdeploy-vss-deploy-video-embedding.md`](references\u002Fdeploy-vss-deploy-video-embedding.md)\nand [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md): prefer plain\n`docker`; otherwise use `sudo -n docker`; if `sudo -n` fails, stop with the exact\nmanual command for the host owner instead of retrying with interactive sudo or\nweakening permissions.\n\nSet a minimal standalone environment before `docker compose up`. If `sudo -n chown`\nfails, stop before `docker compose up` and ask the host owner to run the printed\ncommand.\n\n```bash\nexport RTVI_EMBED_PORT=8017\nexport VSS_DATA_DIR=\"${VSS_DATA_DIR:-$(pwd)\u002F.standalone-data}\"\nexport NGC_API_KEY=\"\u003Cyour-ngc-api-key>\"\nexport HOST_IP=\"$(hostname -I | awk '{print $1}')\"\nexport HF_TOKEN=\"${HF_TOKEN:-}\"  # optional, but recommended to avoid HF 429s\nexport RTVI_EMBED_KAFKA_ENABLED=false\nexport ENABLE_REDIS_ERROR_MESSAGES=false\n# Prepare VST clip-storage host dir; use `sudo -n` for ownership fixes.\nCLIP_STORAGE_DIR=\"${VSS_DATA_DIR}\u002Fdata_log\u002Fvst\u002Fclip_storage\"\nmkdir -p \"$CLIP_STORAGE_DIR\"\nif ! sudo -n chown -R 1001:1001 \"$CLIP_STORAGE_DIR\"; then\n  echo \"ERROR: passwordless sudo is unavailable for host-path ownership.\" >&2\n  echo \"Ask the host owner to run: sudo chown -R 1001:1001 \\\"$CLIP_STORAGE_DIR\\\"\" >&2\n  echo \"Do not work around this with chmod 777 or world-writable permissions.\" >&2\n  return 1 2>\u002Fdev\u002Fnull || exit 1\nfi\n```\n\nThis avoids mounting `\u002Fdata_log\u002Fvst\u002Fclip_storage` from filesystem root when `VSS_DATA_DIR` is unset, and prevents startup stalls from missing Kafka\u002FRedis peers in standalone mode.\n\n```bash\n# Bring up the service under the required Compose profile.\ndocker compose -f rtvi-embed-docker-compose.yml \\\n  --profile bp_developer_search_2d up -d rtvi-embed\n```\n\nIf Docker requires elevated privileges, use `sudo -n docker compose ...` and fail\nfast if `sudo -n` reports that a password is required.\n\n```bash\n# Watch logs while the model downloads and Triton repo builds.\ndocker compose -f rtvi-embed-docker-compose.yml logs -f rtvi-embed\n```\n\nFirst-boot startup may take 20 minutes for the Cosmos-Embed1 download and Triton model repository build. Do not shorten the `start_period: 1200s` healthcheck during the first boot or the container will be marked unhealthy while still warming up.\n\n### Verify\n\n```bash\nBASE_URL=\"http:\u002F\u002Flocalhost:${RTVI_EMBED_PORT}\"\n\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fready\"               # 200 when warm.\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fready?detailed=true\" # Component-level status.\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fversion\"\nMODELS_JSON=$(curl -fsS \"$BASE_URL\u002Fv1\u002Fmodels\")\necho \"$MODELS_JSON\"                          # Confirms cosmos-embed1-448p is loaded.\n\nMODEL_ID=\"$(echo \"$MODELS_JSON\" | jq -r '.data[0].id \u002F\u002F empty')\"\ntest -n \"$MODEL_ID\" || { echo \"ERROR: \u002Fv1\u002Fmodels has no model id — wait until \u002Fv1\u002Fready is 200\" >&2; exit 1; }\n```\n\nThe sections below that call the API reuse `$BASE_URL` and `$MODEL_ID` from this block.\n\n## Common Operations\n\n### Generate video embeddings from an uploaded file\n\n```bash\nFILE_ID=$(curl -fsS -X POST \"$BASE_URL\u002Fv1\u002Ffiles\" \\\n  -F purpose=vision \\\n  -F media_type=video \\\n  -F file=@\u002Fpath\u002Fto\u002Fclip.mp4 | jq -r .id)\n\ncurl -fsS -X POST \"$BASE_URL\u002Fv1\u002Fgenerate_video_embeddings\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\n    \\\"id\\\": \\\"$FILE_ID\\\",\n    \\\"model\\\": \\\"$MODEL_ID\\\",\n    \\\"chunk_duration\\\": 60,\n    \\\"chunk_overlap_duration\\\": 10\n  }\"\n```\n\n### Generate text embeddings (for text-to-video search)\n\n```bash\ncurl -fsS -X POST \"$BASE_URL\u002Fv1\u002Fgenerate_text_embeddings\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"text_input\\\":\\\"a forklift moving pallets\\\",\\\"model\\\":\\\"${MODEL_ID}\\\"}\"\n```\n\n### Embed a live RTSP stream\n\nLive streams **require** `stream: true` and `chunk_duration > 0`. A synchronous call returns `400 BadParameters: \"Only streaming output is supported for live-streams\"`, and the `chunk_duration: 0` returned by `streams\u002Fadd` is a placeholder — it must be overridden on the embed request or you get `400 BadParameter: \"chunk_duration must be greater than 0\"`.\n\n`POST \u002Fv1\u002Fstreams\u002Fadd` does **not** deduplicate by `liveStreamUrl` — submitting the same URL twice mints two distinct `stream_id`s. Before adding, call `GET \u002Fv1\u002Fstreams\u002Fget-stream-info` and reuse any existing registration for that URL to avoid orphaned entries.\n\n```bash\nSTREAM_ID=$(curl -fsS -X POST \"$BASE_URL\u002Fv1\u002Fstreams\u002Fadd\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"streams\":[{\"liveStreamUrl\":\"rtsp:\u002F\u002Fhost:port\u002Flive\u002Fvideo\",\"description\":\"camera-001\"}]}' \\\n  | jq -r '.results[0].id')\n\ncurl -N -X POST \"$BASE_URL\u002Fv1\u002Fgenerate_video_embeddings\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Accept: text\u002Fevent-stream\" \\\n  -d \"{\n    \\\"id\\\": \\\"$STREAM_ID\\\",\n    \\\"model\\\": \\\"$MODEL_ID\\\",\n    \\\"stream\\\": true,\n    \\\"chunk_duration\\\": 10,\n    \\\"chunk_overlap_duration\\\": 2\n  }\"\n\n# List registered live streams (use this to recover stream_ids across sessions).\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fstreams\u002Fget-stream-info\"\n\n# Stop embedding for the stream when done (terminates SSE with data: [DONE]).\ncurl -fsS -X DELETE \"$BASE_URL\u002Fv1\u002Fgenerate_video_embeddings\u002F$STREAM_ID\"\n```\n\nSee `references\u002Frest-api.md` for the full endpoint catalog, SSE streaming, and single-stream control-plane patterns.\n\n## Logs, Metrics, And Status\n\n```bash\ndocker compose -f rtvi-embed-docker-compose.yml ps\ndocker compose -f rtvi-embed-docker-compose.yml logs -f rtvi-embed\ndocker stats vss-rtvi-embed\n\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fmetrics\"          # Prometheus.\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fassets\u002Fstats\"     # Asset storage counts and TTL.\n```\n\nIf `RTVI_EMBED_LOG_DIR` is bound to a host directory, log files are also available at `\u002Fopt\u002Fnvidia\u002Frtvi\u002Flog\u002Frtvi\u002F` on the host.\n\n## Integration Surface\n\n- **Inputs:** REST API on `:${RTVI_EMBED_PORT}` (`POST \u002Fv1\u002Ffiles`, `POST \u002Fv1\u002Fgenerate_text_embeddings`, `POST \u002Fv1\u002Fgenerate_video_embeddings`, live-stream control endpoints).\n- **Outputs:** Synchronous REST responses, optional SSE for chunked video embeddings, optional Kafka messages on the topics named by `RTVI_EMBED_KAFKA_TOPIC` (container `KAFKA_TOPIC`) and `RTVI_EMBED_ERROR_MESSAGE_TOPIC` (container `ERROR_MESSAGE_TOPIC`) when Kafka is enabled (host: `RTVI_EMBED_KAFKA_ENABLED=true`, which Compose maps to container `KAFKA_ENABLED`).\n- **Optional peers:** Redis (`ENABLE_REDIS_ERROR_MESSAGES=true`), Kafka (host: `RTVI_EMBED_KAFKA_ENABLED=true` → container `KAFKA_ENABLED`), OpenTelemetry collector (host: `RTVI_EMBED_ENABLE_OTEL_MONITORING=true` → container `ENABLE_OTEL_MONITORING`).\n\n`references\u002Fintegrate-vss-deploy-video-embedding.md` documents the full integration contract.\n\n## Error Handling\n\nAPI failures return JSON with `code` and `message` fields:\n\n```json\n{\n  \"code\": \"BadParameter\",\n  \"message\": \"chunk_duration must be greater than 0\"\n}\n```\n\nPydantic \u002F OpenAPI validation failures use HTTP `422` with `code: \"InvalidParameters\"` and a field-level `message`.\n\n| Code | Meaning | Common Cause |\n|------|---------|--------------|\n| 400 | Bad Request | Missing `text_input`; unknown `file_id` \u002F `stream_id` \u002F `model`; live stream called without `stream: true`; `chunk_duration: 0` on a live-stream embed request; `chunk_overlap_duration >= chunk_duration` |\n| 401 | Unauthorized | Missing or invalid `Authorization: Bearer \u003Ctoken>` when the deployment enforces auth |\n| 403 | Forbidden | `file:\u002F\u002F` URLs disabled (`FILE_URL_ALLOWED_DIRS` unset) or resolved path outside the allow-list (`code: \"Forbidden\"`) |\n| 409 | Conflict | `DELETE \u002Fv1\u002Ffiles\u002F{file_id}` while the file is in use (`ResourceInUse`); another client already connected to the same live stream (`Conflict`) |\n| 413 | Payload Too Large | Uploaded file or decoded `data:` URI exceeds server size limits |\n| 422 | Unprocessable Entity | Schema validation failure — malformed UUID, wrong multipart field types, invalid enum values; invalid URL format for supported schemes |\n| 429 | Rate Limited | Request rate exceeded — retry with exponential backoff |\n| 500 | Internal Server Error | Unexpected inference or I\u002FO failure — inspect `docker compose -f rtvi-embed-docker-compose.yml logs -f rtvi-embed` |\n| 503 | Service Unavailable | `\u002Fv1\u002Fready` still warming up (model download \u002F Triton repo build); embedding endpoint busy with another file or text query; max live streams reached; CUDA OOM during inference |\n\n**503 on `\u002Fv1\u002Fready` during first boot is expected** until Cosmos-Embed1 finishes downloading and the Triton model repo is built (up to ~20 minutes). Do not treat it as an application error until after the healthcheck `start_period: 1200s` elapses.\n\n**503 on embedding endpoints** with message `\"Server is busy processing another file or text\"` or `\"Server is busy processing another file \u002F live-stream.\"` means the service handles one synchronous embed job at a time — retry with backoff or shard work across instances.\n\nFor endpoint-specific constraints (live-stream SSE requirements, URL schemes, response schemas), see [`references\u002Frest-api.md`](references\u002Frest-api.md). For Compose startup, cache, and permission failures, see [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md).\n\n## Troubleshooting\n\nFor common failure patterns and resolutions, see `references\u002Ftroubleshooting.md`. Frequent issues:\n\n- `\u002Fv1\u002Fready` stuck at 503 → check for missing `NGC_API_KEY`, Hugging Face 429 rate-limit failures during the first-boot model download (set `HF_TOKEN` to avoid), or unreachable Redis\u002FKafka peers when those flags are enabled.\n- Healthcheck flipping unhealthy in the first 20 minutes → restore `start_period: 1200s`.\n- Permission errors on bind-mounted cache directories → `sudo -n chown -R 1001:1001` on the host paths; if passwordless sudo is unavailable, ask the host owner to run the printed command (do not use `chmod 777`).\n- `sudo` prompts for a password during deploy → use `sudo -n` and fail fast; see `references\u002Ftroubleshooting.md`; never retry with interactive sudo in an agent session.\n\n## Upgrade And Rollback\n\nPin `RTVI_EMBED_IMAGE` \u002F `RTVI_EMBED_TAG`, pull, recreate with `--profile bp_developer_search_2d`, and wait for `\u002Fv1\u002Fready` before cutover. Named volumes persist across image swaps.\n\nFull steps: [Upgrade & Rollback](references\u002Fdeploy-vss-deploy-video-embedding.md#upgrade--rollback).\n\n## Tear Down\n\nStop the standalone stack with `docker compose -f rtvi-embed-docker-compose.yml down`. Use `down -v` only when you intend to destroy named model caches.\n\nFull steps and cache warnings: [Tear Down](references\u002Fdeploy-vss-deploy-video-embedding.md#tear-down).\n\n## References\n\n| File | When to read |\n|---|---|\n| [references\u002FREADME.md](references\u002FREADME.md) | Table of contents for all reference files. |\n| [references\u002Fdeploy-vss-deploy-video-embedding.md](references\u002Fdeploy-vss-deploy-video-embedding.md) | Build Vision Agent deployment reference: image, GPU, storage, startup, prerequisites, known issues. |\n| [references\u002Fintegrate-vss-deploy-video-embedding.md](references\u002Fintegrate-vss-deploy-video-embedding.md) | Build Vision Agent integration reference: peers, inputs\u002Foutputs, env vars, network, example Compose snippet. |\n| [references\u002Frest-api.md](references\u002Frest-api.md) | Full REST endpoint catalog with worked `curl` examples for file uploads, video\u002Ftext embeddings, live streams, and health\u002Fmetrics. |\n| [references\u002Fenvironment.md](references\u002Fenvironment.md) | Complete environment-variable matrix, including host-to-container renames and secret-sensitive variables. |\n| [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) | Operational diagnostics for startup, model\u002Fcache, runtime, and observability issues. |\n\n","# VSS Video Embedding (RT-Embed)\n\nUse this skill when you need to:\n\n- Deploy the VSS Video Embedding microservice from a Docker Compose file.\n- Generate text or video embeddings against the Cosmos-Embed1-448p model.\n- Embed an uploaded file, an HTTP\u002FS3\u002Ffile\u002Fdata URL, or a live RTSP stream.\n- Wire the service into a VSS deployment alongside Redis, Kafka, and OpenTelemetry.\n- Triage readiness, model-download, GPU, or stream-reconnection failures.\n\n**Trigger phrases:** `vss-deploy-video-embedding`, `RT-Embed`, `rtvi-embed`, `video embedding service`, `Cosmos-Embed1`, `embed live stream`, `embed video file`, `generate video embeddings`, `text embedding for video search`.\n\n## Service Snapshot\n\n- **VSS 3.2 GA skill:** `vss-deploy-video-embedding`.\n- **Legacy 3.1 name:** RT-Embed.\n- **Compose service:** `rtvi-embed`.\n- **Container name:** `vss-rtvi-embed`.\n- **Image:** `nvcr.io\u002Fnvidia\u002Fvss-core\u002Fvss-rt-embed` (override with `RTVI_EMBED_IMAGE`).\n- **Default tag:** `3.2.0` (override with `RTVI_EMBED_TAG`).\n- **Profile:** `bp_developer_search_2d`.\n- **Container port:** `8000` (host-side `${RTVI_EMBED_PORT}`).\n- **Default model:** `cosmos-embed1-448p` from `nvidia\u002FCosmos-Embed1-448p`.\n- **Health endpoint:** `GET \u002Fv1\u002Fready`.\n- **Healthcheck startup grace:** `1200s` (20 minutes) on first boot.\n\n## Prerequisites\n\nBefore bringing the service up:\n\n1. NVIDIA driver + NVIDIA Container Toolkit installed; default runtime set to `nvidia`.\n2. Docker Engine and Docker Compose plugin recent enough to support `${VAR:+value}` conditional volume substitution.\n3. `docker login nvcr.io` completed with `$oauthtoken` and a valid NGC API key.\n4. Host environment provides at minimum: `RTVI_EMBED_PORT`, `VSS_DATA_DIR`, `NGC_API_KEY`, and optionally `HF_TOKEN` to avoid Hugging Face 429 rate-limit errors during the Cosmos-Embed1 weights download.\n5. Free disk space for persistent caches: `rtvi-hf-cache`, `rtvi-ngc-model-cache`, `rtvi-triton-model-repo` (multi-GB).\n\nSee `references\u002Fdeploy-vss-deploy-video-embedding.md` for the full prerequisite list and `references\u002Fenvironment.md` for the variable matrix.\n\n## Deploy\n\nFor **standalone RT-Embed**, work from the service directory:\n\n```bash\ncd \"{{repo_root}}\u002Fdeploy\u002Fdocker\u002Fservices\u002Frtvi\u002Frtvi-embed\"\n```\n\nDo **not** use `\u002Fvss-deploy-profile` or `scripts\u002Fdev-profile.sh` for this standalone deployment.\n\nFor agent-driven validation, never let `sudo` prompt interactively. Before any\nprivileged ownership or Docker operation, use the non-interactive guard in\n[`references\u002Fdeploy-vss-deploy-video-embedding.md`](references\u002Fdeploy-vss-deploy-video-embedding.md)\nand [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md): prefer plain\n`docker`; otherwise use `sudo -n docker`; if `sudo -n` fails, stop with the exact\nmanual command for the host owner instead of retrying with interactive sudo or\nweakening permissions.\n\nSet a minimal standalone environment before `docker compose up`. If `sudo -n chown`\nfails, stop before `docker compose up` and ask the host owner to run the printed\ncommand.\n\n```bash\nexport RTVI_EMBED_PORT=8017\nexport VSS_DATA_DIR=\"${VSS_DATA_DIR:-$(pwd)\u002F.standalone-data}\"\nexport NGC_API_KEY=\"\u003Cyour-ngc-api-key>\"\nexport HOST_IP=\"$(hostname -I | awk '{print $1}')\"\nexport HF_TOKEN=\"${HF_TOKEN:-}\"  # optional, but recommended to avoid HF 429s\nexport RTVI_EMBED_KAFKA_ENABLED=false\nexport ENABLE_REDIS_ERROR_MESSAGES=false\n# Prepare VST clip-storage host dir; use `sudo -n` for ownership fixes.\nCLIP_STORAGE_DIR=\"${VSS_DATA_DIR}\u002Fdata_log\u002Fvst\u002Fclip_storage\"\nmkdir -p \"$CLIP_STORAGE_DIR\"\nif ! sudo -n chown -R 1001:1001 \"$CLIP_STORAGE_DIR\"; then\n  echo \"ERROR: passwordless sudo is unavailable for host-path ownership.\" >&2\n  echo \"Ask the host owner to run: sudo chown -R 1001:1001 \\\"$CLIP_STORAGE_DIR\\\"\" >&2\n  echo \"Do not work around this with chmod 777 or world-writable permissions.\" >&2\n  return 1 2>\u002Fdev\u002Fnull || exit 1\nfi\n```\n\nThis avoids mounting `\u002Fdata_log\u002Fvst\u002Fclip_storage` from filesystem root when `VSS_DATA_DIR` is unset, and prevents startup stalls from missing Kafka\u002FRedis peers in standalone mode.\n\n```bash\n# Bring up the service under the required Compose profile.\ndocker compose -f rtvi-embed-docker-compose.yml \\\n  --profile bp_developer_search_2d up -d rtvi-embed\n```\n\nIf Docker requires elevated privileges, use `sudo -n docker compose ...` and fail\nfast if `sudo -n` reports that a password is required.\n\n```bash\n# Watch logs while the model downloads and Triton repo builds.\ndocker compose -f rtvi-embed-docker-compose.yml logs -f rtvi-embed\n```\n\nFirst-boot startup may take 20 minutes for the Cosmos-Embed1 download and Triton model repository build. Do not shorten the `start_period: 1200s` healthcheck during the first boot or the container will be marked unhealthy while still warming up.\n\n### Verify\n\n```bash\nBASE_URL=\"http:\u002F\u002Flocalhost:${RTVI_EMBED_PORT}\"\n\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fready\"               # 200 when warm.\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fready?detailed=true\" # Component-level status.\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fversion\"\nMODELS_JSON=$(curl -fsS \"$BASE_URL\u002Fv1\u002Fmodels\")\necho \"$MODELS_JSON\"                          # Confirms cosmos-embed1-448p is loaded.\n\nMODEL_ID=\"$(echo \"$MODELS_JSON\" | jq -r '.data[0].id \u002F\u002F empty')\"\ntest -n \"$MODEL_ID\" || { echo \"ERROR: \u002Fv1\u002Fmodels has no model id — wait until \u002Fv1\u002Fready is 200\" >&2; exit 1; }\n```\n\nThe sections below that call the API reuse `$BASE_URL` and `$MODEL_ID` from this block.\n\n## Common Operations\n\n### Generate video embeddings from an uploaded file\n\n```bash\nFILE_ID=$(curl -fsS -X POST \"$BASE_URL\u002Fv1\u002Ffiles\" \\\n  -F purpose=vision \\\n  -F media_type=video \\\n  -F file=@\u002Fpath\u002Fto\u002Fclip.mp4 | jq -r .id)\n\ncurl -fsS -X POST \"$BASE_URL\u002Fv1\u002Fgenerate_video_embeddings\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\n    \\\"id\\\": \\\"$FILE_ID\\\",\n    \\\"model\\\": \\\"$MODEL_ID\\\",\n    \\\"chunk_duration\\\": 60,\n    \\\"chunk_overlap_duration\\\": 10\n  }\"\n```\n\n### Generate text embeddings (for text-to-video search)\n\n```bash\ncurl -fsS -X POST \"$BASE_URL\u002Fv1\u002Fgenerate_text_embeddings\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d \"{\\\"text_input\\\":\\\"a forklift moving pallets\\\",\\\"model\\\":\\\"${MODEL_ID}\\\"}\"\n```\n\n### Embed a live RTSP stream\n\nLive streams **require** `stream: true` and `chunk_duration > 0`. A synchronous call returns `400 BadParameters: \"Only streaming output is supported for live-streams\"`, and the `chunk_duration: 0` returned by `streams\u002Fadd` is a placeholder — it must be overridden on the embed request or you get `400 BadParameter: \"chunk_duration must be greater than 0\"`.\n\n`POST \u002Fv1\u002Fstreams\u002Fadd` does **not** deduplicate by `liveStreamUrl` — submitting the same URL twice mints two distinct `stream_id`s. Before adding, call `GET \u002Fv1\u002Fstreams\u002Fget-stream-info` and reuse any existing registration for that URL to avoid orphaned entries.\n\n```bash\nSTREAM_ID=$(curl -fsS -X POST \"$BASE_URL\u002Fv1\u002Fstreams\u002Fadd\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"streams\":[{\"liveStreamUrl\":\"rtsp:\u002F\u002Fhost:port\u002Flive\u002Fvideo\",\"description\":\"camera-001\"}]}' \\\n  | jq -r '.results[0].id')\n\ncurl -N -X POST \"$BASE_URL\u002Fv1\u002Fgenerate_video_embeddings\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Accept: text\u002Fevent-stream\" \\\n  -d \"{\n    \\\"id\\\": \\\"$STREAM_ID\\\",\n    \\\"model\\\": \\\"$MODEL_ID\\\",\n    \\\"stream\\\": true,\n    \\\"chunk_duration\\\": 10,\n    \\\"chunk_overlap_duration\\\": 2\n  }\"\n\n# List registered live streams (use this to recover stream_ids across sessions).\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fstreams\u002Fget-stream-info\"\n\n# Stop embedding for the stream when done (terminates SSE with data: [DONE]).\ncurl -fsS -X DELETE \"$BASE_URL\u002Fv1\u002Fgenerate_video_embeddings\u002F$STREAM_ID\"\n```\n\nSee `references\u002Frest-api.md` for the full endpoint catalog, SSE streaming, and single-stream control-plane patterns.\n\n## Logs, Metrics, And Status\n\n```bash\ndocker compose -f rtvi-embed-docker-compose.yml ps\ndocker compose -f rtvi-embed-docker-compose.yml logs -f rtvi-embed\ndocker stats vss-rtvi-embed\n\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fmetrics\"          # Prometheus.\ncurl -fsS \"$BASE_URL\u002Fv1\u002Fassets\u002Fstats\"     # Asset storage counts and TTL.\n```\n\nIf `RTVI_EMBED_LOG_DIR` is bound to a host directory, log files are also available at `\u002Fopt\u002Fnvidia\u002Frtvi\u002Flog\u002Frtvi\u002F` on the host.\n\n## Integration Surface\n\n- **Inputs:** REST API on `:${RTVI_EMBED_PORT}` (`POST \u002Fv1\u002Ffiles`, `POST \u002Fv1\u002Fgenerate_text_embeddings`, `POST \u002Fv1\u002Fgenerate_video_embeddings`, live-stream control endpoints).\n- **Outputs:** Synchronous REST responses, optional SSE for chunked video embeddings, optional Kafka messages on the topics named by `RTVI_EMBED_KAFKA_TOPIC` (container `KAFKA_TOPIC`) and `RTVI_EMBED_ERROR_MESSAGE_TOPIC` (container `ERROR_MESSAGE_TOPIC`) when Kafka is enabled (host: `RTVI_EMBED_KAFKA_ENABLED=true`, which Compose maps to container `KAFKA_ENABLED`).\n- **Optional peers:** Redis (`ENABLE_REDIS_ERROR_MESSAGES=true`), Kafka (host: `RTVI_EMBED_KAFKA_ENABLED=true` → container `KAFKA_ENABLED`), OpenTelemetry collector (host: `RTVI_EMBED_ENABLE_OTEL_MONITORING=true` → container `ENABLE_OTEL_MONITORING`).\n\n`references\u002Fintegrate-vss-deploy-video-embedding.md` documents the full integration contract.\n\n## Error Handling\n\nAPI failures return JSON with `code` and `message` fields:\n\n```json\n{\n  \"code\": \"BadParameter\",\n  \"message\": \"chunk_duration must be greater than 0\"\n}\n```\n\nPydantic \u002F OpenAPI validation failures use HTTP `422` with `code: \"InvalidParameters\"` and a field-level `message`.\n\n| Code | Meaning | Common Cause |\n|------|---------|--------------|\n| 400 | Bad Request | Missing `text_input`; unknown `file_id` \u002F `stream_id` \u002F `model`; live stream called without `stream: true`; `chunk_duration: 0` on a live-stream embed request; `chunk_overlap_duration >= chunk_duration` |\n| 401 | Unauthorized | Missing or invalid `Authorization: Bearer \u003Ctoken>` when the deployment enforces auth |\n| 403 | Forbidden | `file:\u002F\u002F` URLs disabled (`FILE_URL_ALLOWED_DIRS` unset) or resolved path outside the allow-list (`code: \"Forbidden\"`) |\n| 409 | Conflict | `DELETE \u002Fv1\u002Ffiles\u002F{file_id}` while the file is in use (`ResourceInUse`); another client already connected to the same live stream (`Conflict`) |\n| 413 | Payload Too Large | Uploaded file or decoded `data:` URI exceeds server size limits |\n| 422 | Unprocessable Entity | Schema validation failure — malformed UUID, wrong multipart field types, invalid enum values; invalid URL format for supported schemes |\n| 429 | Rate Limited | Request rate exceeded — retry with exponential backoff |\n| 500 | Internal Server Error | Unexpected inference or I\u002FO failure — inspect `docker compose -f rtvi-embed-docker-compose.yml logs -f rtvi-embed` |\n| 503 | Service Unavailable | `\u002Fv1\u002Fready` still warming up (model download \u002F Triton repo build); embedding endpoint busy with another file or text query; max live streams reached; CUDA OOM during inference |\n\n**503 on `\u002Fv1\u002Fready` during first boot is expected** until Cosmos-Embed1 finishes downloading and the Triton model repo is built (up to ~20 minutes). Do not treat it as an application error until after the healthcheck `start_period: 1200s` elapses.\n\n**503 on embedding endpoints** with message `\"Server is busy processing another file or text\"` or `\"Server is busy processing another file \u002F live-stream.\"` means the service handles one synchronous embed job at a time — retry with backoff or shard work across instances.\n\nFor endpoint-specific constraints (live-stream SSE requirements, URL schemes, response schemas), see [`references\u002Frest-api.md`](references\u002Frest-api.md). For Compose startup, cache, and permission failures, see [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md).\n\n## Troubleshooting\n\nFor common failure patterns and resolutions, see `references\u002Ftroubleshooting.md`. Frequent issues:\n\n- `\u002Fv1\u002Fready` stuck at 503 → check for missing `NGC_API_KEY`, Hugging Face 429 rate-limit failures during the first-boot model download (set `HF_TOKEN` to avoid), or unreachable Redis\u002FKafka peers when those flags are enabled.\n- Healthcheck flipping unhealthy in the first 20 minutes → restore `start_period: 1200s`.\n- Permission errors on bind-mounted cache directories → `sudo -n chown -R 1001:1001` on the host paths; if passwordless sudo is unavailable, ask the host owner to run the printed command (do not use `chmod 777`).\n- `sudo` prompts for a password during deploy → use `sudo -n` and fail fast; see `references\u002Ftroubleshooting.md`; never retry with interactive sudo in an agent session.\n\n## Upgrade And Rollback\n\nPin `RTVI_EMBED_IMAGE` \u002F `RTVI_EMBED_TAG`, pull, recreate with `--profile bp_developer_search_2d`, and wait for `\u002Fv1\u002Fready` before cutover. Named volumes persist across image swaps.\n\nFull steps: [Upgrade & Rollback](references\u002Fdeploy-vss-deploy-video-embedding.md#upgrade--rollback).\n\n## Tear Down\n\nStop the standalone stack with `docker compose -f rtvi-embed-docker-compose.yml down`. Use `down -v` only when you intend to destroy named model caches.\n\nFull steps and cache warnings: [Tear Down](references\u002Fdeploy-vss-deploy-video-embedding.md#tear-down).\n\n## References\n\n| File | When to read |\n|---|---|\n| [references\u002FREADME.md](references\u002FREADME.md) | Table of contents for all reference files. |\n| [references\u002Fdeploy-vss-deploy-video-embedding.md](references\u002Fdeploy-vss-deploy-video-embedding.md) | Build Vision Agent deployment reference: image, GPU, storage, startup, prerequisites, known issues. |\n| [references\u002Fintegrate-vss-deploy-video-embedding.md](references\u002Fintegrate-vss-deploy-video-embedding.md) | Build Vision Agent integration reference: peers, inputs\u002Foutputs, env vars, network, example Compose snippet. |\n| [references\u002Frest-api.md](references\u002Frest-api.md) | Full REST endpoint catalog with worked `curl` examples for file uploads, video\u002Ftext embeddings, live streams, and health\u002Fmetrics. |\n| [references\u002Fenvironment.md](references\u002Fenvironment.md) | Complete environment-variable matrix, including host-to-container renames and secret-sensitive variables. |\n| [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) | Operational diagnostics for startup, model\u002Fcache, runtime, and observability issues. |\n\n",{"name":5,"license":15,"metadata":24,"description":28},{"tags":25,"version":26,"github-url":27},"nvidia blueprint operational deployment","3.2.0","https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Fvideo-search-and-summarization","Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `\u002Fv1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis\u002FKafka\u002FOTel integration, common failure modes, and teardown.\n","main","86cc27ffd16af6cb85948f1155578e6f3f61cc4c","skillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn","https:\u002F\u002Fgithub.com\u002FSolizardking","https:\u002F\u002Fmusebook.trade","Got a mile high and never came down","2026-10-08 11:52:53",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Solizardking\u002Ftrain2earn --skill vss-deploy-video-embedding",{"tool":43,"command":44},"bunx","bunx skills add Solizardking\u002Ftrain2earn --skill vss-deploy-video-embedding",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Solizardking\u002Ftrain2earn --skill vss-deploy-video-embedding","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002FSKILL.md",true,[51,57,61,65,69,73,77,81,85,89,93],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"BENCHMARK.md","REFERENCE","参考文档",4282,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002FBENCHMARK.md",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002Fevals.json",1517,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002Fevals\u002Fevals.json",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"evals\u002Fstandalone_deploy.json",4146,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002Fevals\u002Fstandalone_deploy.json",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fdeploy-vss-deploy-video-embedding.md",11360,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002Freferences\u002Fdeploy-vss-deploy-video-embedding.md",{"path":70,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fenvironment.md",6398,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002Freferences\u002Fenvironment.md",{"path":74,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fintegrate-vss-deploy-video-embedding.md",16785,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002Freferences\u002Fintegrate-vss-deploy-video-embedding.md",{"path":78,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002FREADME.md",1535,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002Freferences\u002FREADME.md",{"path":82,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Frest-api.md",12895,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002Freferences\u002Frest-api.md",{"path":86,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Ftroubleshooting.md",8792,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002Freferences\u002Ftroubleshooting.md",{"path":90,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":91,"sourceHtmlUrl":92},"skill-card.md",4105,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002Fskill-card.md",{"path":94,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":97,"sourceHtmlUrl":98},"skill.oms.sig","OTHER","其他",6325,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fnvidia\u002Fvss-deploy-video-embedding\u002Fskill.oms.sig",[100,108,116,124,131,139],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":104,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M78B94RSCAKMH1QS79VE6DG9","testing","For testing with Light Protocol programs and clients on localnet, devnet, and mainnet validation.","MIT","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Ftesting\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":104,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M78B81BKY8RX12HETPG8YKWK","qedgen","Formally verify programs by writing Lean 4 proofs. Trigger this skill whenever the user wants to formally verify code, generate Lean 4 proofs, prove properties about algorithms or smart contracts, verify invariants, convert program logic into formal specifications, or anything involving Lean 4 and formal verification. Also trigger when the user mentions \"qedgen\", \"lean proof\", \"formal proof\", \"verify my code\", \"prove correctness\", \"formal verification\", or wants mathematical guarantees about their implementation.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fsolana-formal-verification\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fsolana-formal-verification\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":104,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M78B7Q7C5K54E01DN83A60KG","solana-dev","Use when user asks to \"build a Solana dapp\", \"write an Anchor program\", \"create a token\", \"debug Solana errors\", \"set up wallet connection\", \"test my Solana program\", \"deploy to devnet\", or \"explain Solana concepts\" (rent, accounts, PDAs, CPIs, etc.). Also use for quick on-chain lookups via public RPC + curl — \"what's the balance of \u003Cwallet>\", \"look up transaction \u003Csig>\", \"token balance for \u003Caccount>\", \"check this address on mainnet\u002Fdevnet\". End-to-end Solana development playbook covering wallet connection, Anchor\u002FPinocchio programs, Codama client generation, LiteSVM\u002FMollusk\u002FSurfpool testing, security checklists, and JSON-RPC curl lookups against public clusters. Integrates with the Solana MCP server for live documentation search. Prefers framework-kit (@solana\u002Fclient + @solana\u002Freact-hooks) for UI, wallet-standard-first connection (incl. ConnectorKit), @solana\u002Fkit for client\u002FRPC code, and @solana\u002Fweb3-compat for legacy boundaries.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fsolana-dev\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fsolana-dev\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":104,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":19},"01M78B7HXD6N6GWKSVRQ8F6Q31","solana-common-errors","Diagnose and fix common Solana development errors — GLIBC mismatches, Anchor version conflicts, cargo build-sbf \u002F platform-tools failures, LiteSVM issues, edition2024 crate pins, RPC airdrops, and Anchor 0.29→0.32 migrations. Use when builds fail, Anchor CLI won't install, or CI breaks on Debian\u002FUbuntu.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fsolana-common-errors\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":135,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":19},"01M78B6T7YSYWQ0N4DP40QDXEZ","skill-creator","Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fskill-creator\u002Flicense.txt","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":104,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":19},"01M78B1VFT9X5AND7AE1HZPZGF","phantom-wallet-mcp","Execute wallet operations through the Phantom MCP server. Use when the user wants to interact with their Phantom wallet directly — get addresses, transfer SOL or SPL tokens, buy\u002Fswap tokens, sign transactions, and sign messages across Solana, Ethereum, Bitcoin, and Sui. Requires the @phantom\u002Fmcp-server to be configured as an MCP server.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Ftrain2earn\u002Fblob\u002Fmain\u002Fskillhub\u002Fskills\u002Fphantom-wallet-mcp\u002FSKILL.md",[],[]]