[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CSZ8PHZDFAAR6Y7QSQDF5K":3,"skill-same:01M7CSZ8PHZDFAAR6Y7QSQDF5K":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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7CSZ8PHZDFAAR6Y7QSQDF5K","vss-generate-video-calibration",null,"Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Not for non-AMC calibration or runtime analytics.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vss-generate-video-calibration\ndescription: Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Not for non-AMC calibration or runtime analytics.\nlicense: Apache-2.0\nmetadata:\n  version: \"3.2.0\"\n  github-url: \"https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Fvideo-search-and-summarization\"\n  tags: \"nvidia blueprint operational\"\n---\n## Purpose\n\nRun AutoMagicCalib end-to-end on local files, RTSP streams, or the bundled sample dataset and (when needed) deploy the AMC microservice.\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\nWorked end-to-end examples are kept under `evals\u002F` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow `curl` blocks below. Run a Tier-3 evaluation with `nv-base validate \u003Cthis-skill-dir> --agent-eval` to replay them.\n\n## Limitations\n\n- Requires the matching VSS profile \u002F microservice to be deployed and reachable from the caller.\n- NGC-hosted models and NIMs may be subject to rate-limits, GPU memory requirements, and license restrictions.\n- Concurrency, GPU memory, and storage limits depend on the host hardware and the profile's compose file.\n\n## Troubleshooting\n\n- **Error**: REST call returns connection refused. **Cause**: target microservice not running. **Solution**: probe `\u002Fdocs` or `\u002Fhealth`; redeploy via `vss-deploy-profile` or the matching `vss-deploy-*` skill.\n- **Error**: HTTP 401\u002F403 from NGC pulls. **Cause**: missing\u002Fexpired `NGC_CLI_API_KEY`. **Solution**: `docker login nvcr.io` and re-export the key before retrying.\n- **Error**: container OOM or model fails to load. **Cause**: insufficient GPU memory for the selected profile. **Solution**: switch to a smaller variant or free GPUs via `docker compose down`.\n\n# VSS Generate Video Calibration\n\nRun AutoMagicCalib over one of three input sources and drive the calibration through the microservice REST API. The input-resolution work differs per source; everything from `verify_project` onward is identical and lives in this file. Pick the right input-mode reference and pair it with the [Shared Calibration Tail](#shared-calibration-tail) below.\n\n## Input Routing\n\nMatch the user's request to a mode, then load that mode's reference for input collection, mode-specific API calls, and the full Python script.\n\n| User says \u002F has | Mode | Reference |\n|---|---|---|\n| \"launch AMC\" \u002F \"deploy auto-calibration\" \u002F \"set up auto-magic-calib\" \u002F \"start AMC microservice\" | `deploy` | [`references\u002Fdeploy-auto-calibration-service.md`](references\u002Fdeploy-auto-calibration-service.md) |\n| \"calibrate my videos\" \u002F \"calibrate from video files\" \u002F local `cam_*.mp4` files | `videos` | [`references\u002Fvideos.md`](references\u002Fvideos.md) |\n| \"calibrate RTSP streams\" \u002F \"calibrate from live cameras\" \u002F live RTSP URLs | `rtsp` | [`references\u002Frtsp.md`](references\u002Frtsp.md) |\n| \"test sample dataset\" \u002F \"verify AMC install\" \u002F \"launch and test\" | `sample-dataset` | [`references\u002Fsample-dataset.md`](references\u002Fsample-dataset.md) |\n\n**Disambiguation rule:** if the user is asking to launch \u002F deploy \u002F set up AMC (no calibration verb) → `deploy`. If they provide RTSP URLs → `rtsp`. If they mention local files \u002F a videos directory → `videos`. If they ask to verify install or test the bundled sample → `sample-dataset`. Combined intents (e.g. \"launch AMC and calibrate my videos\") → walk `deploy` first, then the calibration mode. When ambiguous, ask via `AskUserQuestion`.\n\n## Prerequisites (shared across calibration modes)\n\n- AMC microservice + UI running. If not, walk [`references\u002Fdeploy-auto-calibration-service.md`](references\u002Fdeploy-auto-calibration-service.md) first.\n- Microservice reachable at `http:\u002F\u002F\u003CHOST_IP>:${VSS_AUTO_CALIBRATION_PORT:-8010}\u002Fv1\u002Fready` → `{\"code\":0,...}`.\n- Projects directory writable by the container user. If you didn't just deploy (so Step 5 of the deploy reference hasn't run), confirm the write test in [`references\u002Fdeploy-auto-calibration-service.md` § Step 5](references\u002Fdeploy-auto-calibration-service.md#step-5--confirm-the-projects-directory-is-writable) — otherwise the first `create_project` returns `[Errno 13] Permission denied`.\n- Python 3 with `requests` installed (each input-mode reference includes a self-healing venv fallback for direct runs).\n\nMode-specific prerequisites (VIOS for `rtsp`, sample zip for `sample-dataset`) live in the respective references.\n\n## Shared Calibration Tail\n\nThe verify → calibrate → poll → results sequence is identical regardless of input mode. After the mode-specific reference has uploaded videos \u002F ingested RTSP clips \u002F uploaded the bundled sample, run this tail.\n\n### Step A — Verify Project\n\n```\nPOST \u002Fv1\u002Fverify_project\u002F\u003Cproject_id>\n```\n\nResponse: `{\"project_state\": \"READY\"}` — must be `READY` before calibrating. If not READY, re-check that videos + alignment + layout are present (either via API or via UI manual alignment).\n\n### Step B — Start Calibration\n\n**Confirm the plan before calibrating.** Whether the settings file and detector were auto-detected or asked, present a short summary and confirm via `AskUserQuestion` before the `POST \u002Fcalibrate`. The resolved values are the defaults, so confirming is one click — but the user can switch the detector or skip an auto-detected settings file. Summarize:\n\n- **Detector** — `resnet` or `transformer` (the value to be sent).\n- **Calibration settings** — the file being applied (path), or default parameters (with the option to tune them in the UI first — see below).\n- **Optional overrides** — ground-truth zip and focal lengths, if any.\n\nThe sample-dataset install-check run uses a fixed `resnet` and can proceed without this confirmation.\n\n```\nPOST \u002Fv1\u002Fcalibrate\u002F\u003Cproject_id>\nContent-Type: application\u002Fjson\n\n{\"detector_type\": \"resnet\"}   # or \"transformer\"\n```\n\n`detector_type` is a separate `\u002Fcalibrate` parameter — **not** consumed by `\u002Fv1\u002Fconfig\u002F\u003Cid>`. If the user provided a calibration settings file, parse it for `\"detector\"` \u002F `\"detector_type\"` and use that value. If the file doesn't specify one, the default (`resnet`) is the value shown in the confirmation above — the user can switch it there before calibrating. If there's no settings file at all, ask the user via `AskUserQuestion`:\n\n- `resnet` — default, fast.\n- `transformer` — slower, better under heavy occlusion.\n\nUI Step 3 (Parameters) does NOT cover detector choice; never assume the user picked one in the UI.\n\n**Also when there's no settings file, ask whether to tune the calibration parameters first** (`AskUserQuestion`):\n\n- **Proceed with the default parameters** — well-suited to typical warehouse scenes; recommended unless the user has specific tuning in mind.\n- **Adjust parameters in the UI first** — open the project, go to Step 3: Parameters, change values, and click Save; then continue.\n\nWait for the user's choice — and, if they choose to tune, for them to confirm they've Saved — before calling `\u002Fcalibrate`.\n\n### Step C — Poll for Completion\n\n```\nGET \u002Fv1\u002Fget_project_info\u002F\u003Cproject_id>\n```\n\nPoll every 10 s. `project_info.project_state`:\n\n| State | Meaning |\n|---|---|\n| `RUNNING` | Calibration in progress |\n| `COMPLETED` | Finished |\n| `ERROR` | Failed — pull log via `GET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cid>\u002Flog` |\n\nWhen calibration starts, surface the project ID, the UI URL (`http:\u002F\u002F\u003CHOST_IP>:${VSS_AUTO_CALIBRATION_UI_PORT:-5000}`), and the log endpoint so the user can watch progress while the run proceeds. During `RUNNING`, emit a progress line at least once a minute with elapsed time so a long run doesn't look stalled. On `ERROR`, fetch and show the last lines of `GET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cid>\u002Flog` before stopping. Live logs can also be streamed via `GET \u002Fv1\u002Fcalibrate\u002F\u003Cproject_id>\u002Flog\u002F\u003Ctype>\u002Fstream`.\n\nTypical time: **10–60 min** (your-own videos), **10–30 min** (bundled sample).\n\n### Step D — Results\n\n```\nGET \u002Fv1\u002Fget_project_info\u002F\u003Cproject_id>                    # project state\nGET \u002Fv1\u002Fresult\u002F\u003Cproject_id>\u002Fevaluation_statistics        # only if GT uploaded\nGET \u002Fv1\u002Fresult\u002F\u003Cproject_id>\u002Foverlay_image                # visual overlay (PNG)\nGET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cproject_id>\u002Flog                   # calibration log\n```\n\nEvaluation response includes `Average L2 distance(m)` and `Average reprojection error 0(px)`. Evaluation metrics are produced **only when a ground-truth `GT.zip` was uploaded** — a missing `evaluation_statistics` result is normal otherwise and is not the end of result reporting.\n\nAfter `COMPLETED`, always give the user a way to review the result for that exact project, regardless of whether metrics exist:\n\n- **UI** — `http:\u002F\u002F\u003CHOST_IP>:${VSS_AUTO_CALIBRATION_UI_PORT:-5000}`; open the project, then the Results page to view the overlay.\n- **Overlay image on disk** — `${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\u002Fproject_\u003Cid>\u002Foutput\u002Fmulti_view_results\u002FBA_output\u002Fresults_ba_scaled_world\u002Foverlay_img_*.png` (single-camera projects use `output\u002Fsingle_view_results\u002Fcam_00\u002Fverification_map_overlay.png`).\n- **Project files** — `${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\u002Fproject_\u003Cid>\u002F`.\n\n### Step E — (Optional) VGGT Refinement\n\nOnly if `vggt_state == \"READY\"` in project info (VGGT model must be staged — see [`references\u002Fdeploy-auto-calibration-service.md`](references\u002Fdeploy-auto-calibration-service.md) Step 2):\n\n```\nPOST \u002Fv1\u002Fvggt\u002Fcalibrate\u002F\u003Cproject_id>\nGET  \u002Fv1\u002Fget_project_info\u002F\u003Cproject_id>                    # poll vggt_state\nGET  \u002Fv1\u002Fvggt_results\u002F\u003Cproject_id>\u002Fevaluation_statistics  # VGGT metrics\n```\n\n## Settings File + Detector Pattern\n\nOptional across all three modes. When the user provides a JSON settings file (typically exported from UI Step 3 Download), POST it verbatim:\n\n```\nPOST \u002Fv1\u002Fconfig\u002F\u003Cproject_id>\nContent-Type: application\u002Fjson\n\n\u003Cfile contents, posted as-is>\n```\n\nThe file replaces what the user would otherwise tune in UI Step 3 (rectification, bundle-adjustment, evaluation knobs, detector, …). After a successful POST, **also** parse the file for `\"detector\"` \u002F `\"detector_type\"` — if it's `\"resnet\"` or `\"transformer\"`, use that value for the `\u002Fcalibrate` call in Step B (detector is a separate API parameter, not consumed by `\u002Fconfig`).\n\nNon-2xx is surfaced — do not silently fall back. Skip this call entirely if the user chose the UI-fallback path.\n\n## UI Fallback Pattern\n\nWhen alignment \u002F layout files aren't on disk, direct the user to the appropriate AMC UI step:\n\n- **Settings missing** → \"Open UI project `\u003Cproject_id>`, go to **Step 3: Parameters**, tune via the settings dialog (or accept defaults), click Save.\" **Also**: before the `\u002Fcalibrate` call, ask the user via `AskUserQuestion` whether to use the `resnet` or `transformer` detector — Step 3 doesn't cover detector choice.\n- **Layout missing** → \"Open UI project `\u003Cproject_id>`, go to **Step 2: Video Configuration**, upload `layout.png` only (do NOT re-upload videos — they're already attached via API\u002FRTSP), click Save.\"\n- **Alignment missing** → \"Open UI project `\u003Cproject_id>`, go to **Step 4: Alignment**, either upload `alignment_data.json` or mark correspondence points on the layout, click Save.\"\n\nWait for user confirmation. For alignment\u002Flayout, verify on disk before continuing:\n\n```bash\n# Project state lives under $VSS_APPS_DIR\u002Fservices\u002Fauto-calibration\u002Fprojects\n# (the path bind-mounted into the MS container in\n#  deploy\u002Fdocker\u002Fservices\u002Fauto-calibration\u002Fms\u002Fcompose.yml).\nHOST_PROJECTS=\"${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\"\n\nls \"$HOST_PROJECTS\u002Fproject_\u003Cproject_id>\u002Fmanual_adjustment\u002F\"\n# Expected: alignment_data.json, layout.png\n```\n\n## Success Criteria\n\n- `project_state == \"COMPLETED\"` after polling.\n- If manual alignment was used: `${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\u002Fproject_\u003Cid>\u002Fmanual_adjustment\u002F` contains `alignment_data.json` + `layout.png`.\n- If GT was uploaded: evaluation returns typical thresholds (`Average L2 distance(m)` \u003C 1.5, `Average reprojection error 0(px)` \u003C 5 for your data; \u003C 10 for the bundled sample).\n- No `ERROR` state.\n\n## Key Output Files\n\nUnder `${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\u002Fproject_\u003Cproject_id>\u002F`:\n\n```\nproject_\u003Cproject_id>\u002F\n├── manual_adjustment\u002F\n│   ├── alignment_data.json\n│   └── layout.png\n├── output\u002F\n│   ├── single_view_results\u002Fcam_XX\u002F\n│   │   ├── camInfo_hyper_XX.yaml\n│   │   └── trajDump_Stream_0_3d.txt\n│   ├── multi_view_results\u002FBA_output\u002Fresults_ba\u002F\n│   │   ├── initial\u002FcamInfo_XX.yaml\n│   │   └── refined\u002FcamInfo_XX.yaml          # ← final calibration\n│   └── multi_view_results\u002FBA_output\u002Fresults_ba_scaled_world\u002F\n│       └── overlay_img_XX.png               # ← visual overlay for review\n└── calibration.log\n```\n\n## Cross-cutting Troubleshooting\n\nMode-specific issues live in each reference's own troubleshooting table.\n\n| Issue | Fix |\n|---|---|\n| `verify_project` state not `READY` | Confirm videos uploaded\u002Fingested and alignment + layout are present (either via API or via UI manual alignment). Mode-specific upload steps in the reference. |\n| Manual alignment files missing after UI step | User didn't click Save; also verify `${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\u002Fproject_\u003Cid>\u002Fmanual_adjustment\u002F` exists. |\n| Calibration stuck `RUNNING` > 90 min | `GET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cid>\u002Flog` — usually insufficient tracklets (scene too static). See \"Custom Dataset\" guidelines in root `README.md`. |\n| Immediate `ERROR` state | Check video naming: must be `cam_00.mp4`, `cam_01.mp4`, … contiguous (videos mode) \u002F camera_name labels (RTSP mode). |\n| Low L2 but high reprojection | Provide explicit `focal_length` override during input upload (see videos \u002F rtsp references). |\n| VGGT `INIT`, never `READY` | VGGT model not loaded — see [`references\u002Fdeploy-auto-calibration-service.md`](references\u002Fdeploy-auto-calibration-service.md) Step 2. |\n| Upload timeout | Large videos — bump `timeout=300` to e.g. `600` in the per-mode Python script. |\n| Port scan finds no backend | Backend not running — walk [`references\u002Fdeploy-auto-calibration-service.md`](references\u002Fdeploy-auto-calibration-service.md) first. |\n\n## For Downstream Skills — MV3DT Export\n\nDownstream consumers (e.g. a Multi-View 3D Tracking skill owned by another team) fetch the MV3DT-format calibration output directly from the microservice. This skill returns the `project_id`; the downstream skill calls:\n\n```\nGET \u002Fv1\u002Fresult\u002F{project_id}\u002Fmv3dt_result?result_type=amc\n# Response: application\u002Fzip — mv3dt_output.zip containing transforms.yml\n```\n\nFor VGGT-refined output (only available if VGGT ran to `COMPLETED`, see Step E):\n\n```\nGET \u002Fv1\u002Fresult\u002F{project_id}\u002Fmv3dt_result?result_type=vggt\n# Response: application\u002Fzip — vggt_mv3dt_output.zip\n```\n\nDownstream skill flow:\n1. Call this skill with the user's inputs; capture the printed `project_id`.\n2. Wait for the skill to return (it polls until `COMPLETED` internally).\n3. `GET \u002Fv1\u002Fresult\u002F{project_id}\u002Fmv3dt_result?result_type=amc` — save the ZIP locally.\n4. If VGGT also ran, optionally fetch `?result_type=vggt` for the refined MV3DT.\n\n## Related Skills\n\n- [`vss-manage-video-io-storage`](..\u002Fvss-manage-video-io-storage\u002FSKILL.md) — VIOS API skill; only the `rtsp` calibration mode depends on VIOS being reachable.\n\nRoot `README.md` \"Custom Dataset\" and \"Calibration Workflow (UI)\" sections document input-video guidelines and the UI-driven alternative to this API flow.\n\nbump:1\n","## Purpose\n\nRun AutoMagicCalib end-to-end on local files, RTSP streams, or the bundled sample dataset and (when needed) deploy the AMC microservice.\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\nWorked end-to-end examples are kept under `evals\u002F` (each `*.json` manifest contains a runnable scenario) and inline in the per-workflow `curl` blocks below. Run a Tier-3 evaluation with `nv-base validate \u003Cthis-skill-dir> --agent-eval` to replay them.\n\n## Limitations\n\n- Requires the matching VSS profile \u002F microservice to be deployed and reachable from the caller.\n- NGC-hosted models and NIMs may be subject to rate-limits, GPU memory requirements, and license restrictions.\n- Concurrency, GPU memory, and storage limits depend on the host hardware and the profile's compose file.\n\n## Troubleshooting\n\n- **Error**: REST call returns connection refused. **Cause**: target microservice not running. **Solution**: probe `\u002Fdocs` or `\u002Fhealth`; redeploy via `vss-deploy-profile` or the matching `vss-deploy-*` skill.\n- **Error**: HTTP 401\u002F403 from NGC pulls. **Cause**: missing\u002Fexpired `NGC_CLI_API_KEY`. **Solution**: `docker login nvcr.io` and re-export the key before retrying.\n- **Error**: container OOM or model fails to load. **Cause**: insufficient GPU memory for the selected profile. **Solution**: switch to a smaller variant or free GPUs via `docker compose down`.\n\n# VSS Generate Video Calibration\n\nRun AutoMagicCalib over one of three input sources and drive the calibration through the microservice REST API. The input-resolution work differs per source; everything from `verify_project` onward is identical and lives in this file. Pick the right input-mode reference and pair it with the [Shared Calibration Tail](#shared-calibration-tail) below.\n\n## Input Routing\n\nMatch the user's request to a mode, then load that mode's reference for input collection, mode-specific API calls, and the full Python script.\n\n| User says \u002F has | Mode | Reference |\n|---|---|---|\n| \"launch AMC\" \u002F \"deploy auto-calibration\" \u002F \"set up auto-magic-calib\" \u002F \"start AMC microservice\" | `deploy` | [`references\u002Fdeploy-auto-calibration-service.md`](references\u002Fdeploy-auto-calibration-service.md) |\n| \"calibrate my videos\" \u002F \"calibrate from video files\" \u002F local `cam_*.mp4` files | `videos` | [`references\u002Fvideos.md`](references\u002Fvideos.md) |\n| \"calibrate RTSP streams\" \u002F \"calibrate from live cameras\" \u002F live RTSP URLs | `rtsp` | [`references\u002Frtsp.md`](references\u002Frtsp.md) |\n| \"test sample dataset\" \u002F \"verify AMC install\" \u002F \"launch and test\" | `sample-dataset` | [`references\u002Fsample-dataset.md`](references\u002Fsample-dataset.md) |\n\n**Disambiguation rule:** if the user is asking to launch \u002F deploy \u002F set up AMC (no calibration verb) → `deploy`. If they provide RTSP URLs → `rtsp`. If they mention local files \u002F a videos directory → `videos`. If they ask to verify install or test the bundled sample → `sample-dataset`. Combined intents (e.g. \"launch AMC and calibrate my videos\") → walk `deploy` first, then the calibration mode. When ambiguous, ask via `AskUserQuestion`.\n\n## Prerequisites (shared across calibration modes)\n\n- AMC microservice + UI running. If not, walk [`references\u002Fdeploy-auto-calibration-service.md`](references\u002Fdeploy-auto-calibration-service.md) first.\n- Microservice reachable at `http:\u002F\u002F\u003CHOST_IP>:${VSS_AUTO_CALIBRATION_PORT:-8010}\u002Fv1\u002Fready` → `{\"code\":0,...}`.\n- Projects directory writable by the container user. If you didn't just deploy (so Step 5 of the deploy reference hasn't run), confirm the write test in [`references\u002Fdeploy-auto-calibration-service.md` § Step 5](references\u002Fdeploy-auto-calibration-service.md#step-5--confirm-the-projects-directory-is-writable) — otherwise the first `create_project` returns `[Errno 13] Permission denied`.\n- Python 3 with `requests` installed (each input-mode reference includes a self-healing venv fallback for direct runs).\n\nMode-specific prerequisites (VIOS for `rtsp`, sample zip for `sample-dataset`) live in the respective references.\n\n## Shared Calibration Tail\n\nThe verify → calibrate → poll → results sequence is identical regardless of input mode. After the mode-specific reference has uploaded videos \u002F ingested RTSP clips \u002F uploaded the bundled sample, run this tail.\n\n### Step A — Verify Project\n\n```\nPOST \u002Fv1\u002Fverify_project\u002F\u003Cproject_id>\n```\n\nResponse: `{\"project_state\": \"READY\"}` — must be `READY` before calibrating. If not READY, re-check that videos + alignment + layout are present (either via API or via UI manual alignment).\n\n### Step B — Start Calibration\n\n**Confirm the plan before calibrating.** Whether the settings file and detector were auto-detected or asked, present a short summary and confirm via `AskUserQuestion` before the `POST \u002Fcalibrate`. The resolved values are the defaults, so confirming is one click — but the user can switch the detector or skip an auto-detected settings file. Summarize:\n\n- **Detector** — `resnet` or `transformer` (the value to be sent).\n- **Calibration settings** — the file being applied (path), or default parameters (with the option to tune them in the UI first — see below).\n- **Optional overrides** — ground-truth zip and focal lengths, if any.\n\nThe sample-dataset install-check run uses a fixed `resnet` and can proceed without this confirmation.\n\n```\nPOST \u002Fv1\u002Fcalibrate\u002F\u003Cproject_id>\nContent-Type: application\u002Fjson\n\n{\"detector_type\": \"resnet\"}   # or \"transformer\"\n```\n\n`detector_type` is a separate `\u002Fcalibrate` parameter — **not** consumed by `\u002Fv1\u002Fconfig\u002F\u003Cid>`. If the user provided a calibration settings file, parse it for `\"detector\"` \u002F `\"detector_type\"` and use that value. If the file doesn't specify one, the default (`resnet`) is the value shown in the confirmation above — the user can switch it there before calibrating. If there's no settings file at all, ask the user via `AskUserQuestion`:\n\n- `resnet` — default, fast.\n- `transformer` — slower, better under heavy occlusion.\n\nUI Step 3 (Parameters) does NOT cover detector choice; never assume the user picked one in the UI.\n\n**Also when there's no settings file, ask whether to tune the calibration parameters first** (`AskUserQuestion`):\n\n- **Proceed with the default parameters** — well-suited to typical warehouse scenes; recommended unless the user has specific tuning in mind.\n- **Adjust parameters in the UI first** — open the project, go to Step 3: Parameters, change values, and click Save; then continue.\n\nWait for the user's choice — and, if they choose to tune, for them to confirm they've Saved — before calling `\u002Fcalibrate`.\n\n### Step C — Poll for Completion\n\n```\nGET \u002Fv1\u002Fget_project_info\u002F\u003Cproject_id>\n```\n\nPoll every 10 s. `project_info.project_state`:\n\n| State | Meaning |\n|---|---|\n| `RUNNING` | Calibration in progress |\n| `COMPLETED` | Finished |\n| `ERROR` | Failed — pull log via `GET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cid>\u002Flog` |\n\nWhen calibration starts, surface the project ID, the UI URL (`http:\u002F\u002F\u003CHOST_IP>:${VSS_AUTO_CALIBRATION_UI_PORT:-5000}`), and the log endpoint so the user can watch progress while the run proceeds. During `RUNNING`, emit a progress line at least once a minute with elapsed time so a long run doesn't look stalled. On `ERROR`, fetch and show the last lines of `GET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cid>\u002Flog` before stopping. Live logs can also be streamed via `GET \u002Fv1\u002Fcalibrate\u002F\u003Cproject_id>\u002Flog\u002F\u003Ctype>\u002Fstream`.\n\nTypical time: **10–60 min** (your-own videos), **10–30 min** (bundled sample).\n\n### Step D — Results\n\n```\nGET \u002Fv1\u002Fget_project_info\u002F\u003Cproject_id>                    # project state\nGET \u002Fv1\u002Fresult\u002F\u003Cproject_id>\u002Fevaluation_statistics        # only if GT uploaded\nGET \u002Fv1\u002Fresult\u002F\u003Cproject_id>\u002Foverlay_image                # visual overlay (PNG)\nGET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cproject_id>\u002Flog                   # calibration log\n```\n\nEvaluation response includes `Average L2 distance(m)` and `Average reprojection error 0(px)`. Evaluation metrics are produced **only when a ground-truth `GT.zip` was uploaded** — a missing `evaluation_statistics` result is normal otherwise and is not the end of result reporting.\n\nAfter `COMPLETED`, always give the user a way to review the result for that exact project, regardless of whether metrics exist:\n\n- **UI** — `http:\u002F\u002F\u003CHOST_IP>:${VSS_AUTO_CALIBRATION_UI_PORT:-5000}`; open the project, then the Results page to view the overlay.\n- **Overlay image on disk** — `${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\u002Fproject_\u003Cid>\u002Foutput\u002Fmulti_view_results\u002FBA_output\u002Fresults_ba_scaled_world\u002Foverlay_img_*.png` (single-camera projects use `output\u002Fsingle_view_results\u002Fcam_00\u002Fverification_map_overlay.png`).\n- **Project files** — `${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\u002Fproject_\u003Cid>\u002F`.\n\n### Step E — (Optional) VGGT Refinement\n\nOnly if `vggt_state == \"READY\"` in project info (VGGT model must be staged — see [`references\u002Fdeploy-auto-calibration-service.md`](references\u002Fdeploy-auto-calibration-service.md) Step 2):\n\n```\nPOST \u002Fv1\u002Fvggt\u002Fcalibrate\u002F\u003Cproject_id>\nGET  \u002Fv1\u002Fget_project_info\u002F\u003Cproject_id>                    # poll vggt_state\nGET  \u002Fv1\u002Fvggt_results\u002F\u003Cproject_id>\u002Fevaluation_statistics  # VGGT metrics\n```\n\n## Settings File + Detector Pattern\n\nOptional across all three modes. When the user provides a JSON settings file (typically exported from UI Step 3 Download), POST it verbatim:\n\n```\nPOST \u002Fv1\u002Fconfig\u002F\u003Cproject_id>\nContent-Type: application\u002Fjson\n\n\u003Cfile contents, posted as-is>\n```\n\nThe file replaces what the user would otherwise tune in UI Step 3 (rectification, bundle-adjustment, evaluation knobs, detector, …). After a successful POST, **also** parse the file for `\"detector\"` \u002F `\"detector_type\"` — if it's `\"resnet\"` or `\"transformer\"`, use that value for the `\u002Fcalibrate` call in Step B (detector is a separate API parameter, not consumed by `\u002Fconfig`).\n\nNon-2xx is surfaced — do not silently fall back. Skip this call entirely if the user chose the UI-fallback path.\n\n## UI Fallback Pattern\n\nWhen alignment \u002F layout files aren't on disk, direct the user to the appropriate AMC UI step:\n\n- **Settings missing** → \"Open UI project `\u003Cproject_id>`, go to **Step 3: Parameters**, tune via the settings dialog (or accept defaults), click Save.\" **Also**: before the `\u002Fcalibrate` call, ask the user via `AskUserQuestion` whether to use the `resnet` or `transformer` detector — Step 3 doesn't cover detector choice.\n- **Layout missing** → \"Open UI project `\u003Cproject_id>`, go to **Step 2: Video Configuration**, upload `layout.png` only (do NOT re-upload videos — they're already attached via API\u002FRTSP), click Save.\"\n- **Alignment missing** → \"Open UI project `\u003Cproject_id>`, go to **Step 4: Alignment**, either upload `alignment_data.json` or mark correspondence points on the layout, click Save.\"\n\nWait for user confirmation. For alignment\u002Flayout, verify on disk before continuing:\n\n```bash\n# Project state lives under $VSS_APPS_DIR\u002Fservices\u002Fauto-calibration\u002Fprojects\n# (the path bind-mounted into the MS container in\n#  deploy\u002Fdocker\u002Fservices\u002Fauto-calibration\u002Fms\u002Fcompose.yml).\nHOST_PROJECTS=\"${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\"\n\nls \"$HOST_PROJECTS\u002Fproject_\u003Cproject_id>\u002Fmanual_adjustment\u002F\"\n# Expected: alignment_data.json, layout.png\n```\n\n## Success Criteria\n\n- `project_state == \"COMPLETED\"` after polling.\n- If manual alignment was used: `${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\u002Fproject_\u003Cid>\u002Fmanual_adjustment\u002F` contains `alignment_data.json` + `layout.png`.\n- If GT was uploaded: evaluation returns typical thresholds (`Average L2 distance(m)` \u003C 1.5, `Average reprojection error 0(px)` \u003C 5 for your data; \u003C 10 for the bundled sample).\n- No `ERROR` state.\n\n## Key Output Files\n\nUnder `${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\u002Fproject_\u003Cproject_id>\u002F`:\n\n```\nproject_\u003Cproject_id>\u002F\n├── manual_adjustment\u002F\n│   ├── alignment_data.json\n│   └── layout.png\n├── output\u002F\n│   ├── single_view_results\u002Fcam_XX\u002F\n│   │   ├── camInfo_hyper_XX.yaml\n│   │   └── trajDump_Stream_0_3d.txt\n│   ├── multi_view_results\u002FBA_output\u002Fresults_ba\u002F\n│   │   ├── initial\u002FcamInfo_XX.yaml\n│   │   └── refined\u002FcamInfo_XX.yaml          # ← final calibration\n│   └── multi_view_results\u002FBA_output\u002Fresults_ba_scaled_world\u002F\n│       └── overlay_img_XX.png               # ← visual overlay for review\n└── calibration.log\n```\n\n## Cross-cutting Troubleshooting\n\nMode-specific issues live in each reference's own troubleshooting table.\n\n| Issue | Fix |\n|---|---|\n| `verify_project` state not `READY` | Confirm videos uploaded\u002Fingested and alignment + layout are present (either via API or via UI manual alignment). Mode-specific upload steps in the reference. |\n| Manual alignment files missing after UI step | User didn't click Save; also verify `${VSS_APPS_DIR}\u002Fservices\u002Fauto-calibration\u002Fprojects\u002Fproject_\u003Cid>\u002Fmanual_adjustment\u002F` exists. |\n| Calibration stuck `RUNNING` > 90 min | `GET \u002Fv1\u002Famc\u002Fcalibrate\u002F\u003Cid>\u002Flog` — usually insufficient tracklets (scene too static). See \"Custom Dataset\" guidelines in root `README.md`. |\n| Immediate `ERROR` state | Check video naming: must be `cam_00.mp4`, `cam_01.mp4`, … contiguous (videos mode) \u002F camera_name labels (RTSP mode). |\n| Low L2 but high reprojection | Provide explicit `focal_length` override during input upload (see videos \u002F rtsp references). |\n| VGGT `INIT`, never `READY` | VGGT model not loaded — see [`references\u002Fdeploy-auto-calibration-service.md`](references\u002Fdeploy-auto-calibration-service.md) Step 2. |\n| Upload timeout | Large videos — bump `timeout=300` to e.g. `600` in the per-mode Python script. |\n| Port scan finds no backend | Backend not running — walk [`references\u002Fdeploy-auto-calibration-service.md`](references\u002Fdeploy-auto-calibration-service.md) first. |\n\n## For Downstream Skills — MV3DT Export\n\nDownstream consumers (e.g. a Multi-View 3D Tracking skill owned by another team) fetch the MV3DT-format calibration output directly from the microservice. This skill returns the `project_id`; the downstream skill calls:\n\n```\nGET \u002Fv1\u002Fresult\u002F{project_id}\u002Fmv3dt_result?result_type=amc\n# Response: application\u002Fzip — mv3dt_output.zip containing transforms.yml\n```\n\nFor VGGT-refined output (only available if VGGT ran to `COMPLETED`, see Step E):\n\n```\nGET \u002Fv1\u002Fresult\u002F{project_id}\u002Fmv3dt_result?result_type=vggt\n# Response: application\u002Fzip — vggt_mv3dt_output.zip\n```\n\nDownstream skill flow:\n1. Call this skill with the user's inputs; capture the printed `project_id`.\n2. Wait for the skill to return (it polls until `COMPLETED` internally).\n3. `GET \u002Fv1\u002Fresult\u002F{project_id}\u002Fmv3dt_result?result_type=amc` — save the ZIP locally.\n4. If VGGT also ran, optionally fetch `?result_type=vggt` for the refined MV3DT.\n\n## Related Skills\n\n- [`vss-manage-video-io-storage`](..\u002Fvss-manage-video-io-storage\u002FSKILL.md) — VIOS API skill; only the `rtsp` calibration mode depends on VIOS being reachable.\n\nRoot `README.md` \"Custom Dataset\" and \"Calibration Workflow (UI)\" sections document input-video guidelines and the UI-driven alternative to this API flow.\n\nbump:1\n",{"name":5,"license":15,"metadata":24,"description":7},{"tags":25,"version":26,"github-url":27},"nvidia blueprint operational","3.2.0","https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Fvideo-search-and-summarization","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill vss-generate-video-calibration",{"tool":43,"command":44},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill vss-generate-video-calibration",{"tool":46,"command":47},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill vss-generate-video-calibration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\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",5857,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002FBENCHMARK.md",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002Fauto-calibration.json",11883,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002Fevals\u002Fauto-calibration.json",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"evals\u002Fevals.json",4533,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002Fevals\u002Fevals.json",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fcalibration-tail.md",4100,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002Freferences\u002Fcalibration-tail.md",{"path":70,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fcommon-steps.md",1378,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002Freferences\u002Fcommon-steps.md",{"path":74,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fdeploy-auto-calibration-service.md",20343,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002Freferences\u002Fdeploy-auto-calibration-service.md",{"path":78,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Frtsp.md",16778,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002Freferences\u002Frtsp.md",{"path":82,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fsample-dataset.md",16750,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002Freferences\u002Fsample-dataset.md",{"path":86,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fvideos.md",13224,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002Freferences\u002Fvideos.md",{"path":90,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":91,"sourceHtmlUrl":92},"skill-card.md",4043,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002Fskill-card.md",{"path":94,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":97,"sourceHtmlUrl":98},"skill.oms.sig","OTHER","其他",6293,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills\u002Fskills\u002Fvss-generate-video-calibration\u002Fskill.oms.sig",[100,108,115,122,129,136],{"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},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\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":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":104,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":104,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":104,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":104,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]