[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A939VMA4EVN7GSK0JGETCD":3,"skill-same:01M7A939VMA4EVN7GSK0JGETCD":87},{"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":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":42,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M7A939VMA4EVN7GSK0JGETCD","amc-run-sample-calibration",null,"Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.","themusebook\u002Fskills","themusebook","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F349927247?v=4","01M7A5C1RV5S3V5FF6ZACVDNRN","musebook","01M7A5C1SFC3KRZAXNN60XJ7KM",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Famc-run-sample-calibration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"amc-run-sample-calibration\"\ndescription: \"Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.\"\nowner: \"NVIDIA CORPORATION\"\nservice: \"auto-magic-calib\"\nversion: \"1.0.0\"\nreviewed: \"2026-04-28\"\nlicense: \"Apache-2.0\"\ndata_classification: public\nmetadata:\n  tags: [amc, calibration, sample, rest-api, validation, python]\n---\n\n# Skill: Calibrate Sample Dataset\n\n## When to Use This Skill\n\nActivate this skill when the user wants to sanity-check a running AMC stack with the bundled sample dataset. Typical prompts:\n\n- \"test the sample dataset\" \u002F \"run sample calibration\"\n- \"verify AMC install\"\n- \"launch and test\" (chain with `amc-setup-calibration-stack` if the MS isn't already running)\n\n**Do NOT use this skill when:**\n\n- The user references their own video paths (e.g. `\u002Fdata\u002Fvideos\u002F`, `cam_*.mp4` not from the bundled zip) — route to `amc-run-video-calibration`. This skill is exclusively for `assets\u002Fsdg_08_2_sample_data_010926.zip`.\n\nPrerequisite: AMC microservice running on a port in 8000-8009. If no backend is detected, delegate to `amc-setup-calibration-stack` first.\n\nIf execution cannot proceed in the current environment (no backend, missing sample data, etc.), surface the blocker AND describe the expected workflow + API sequence concisely so the user understands what will run once prerequisites are met. Do not fabricate calibration outputs, evaluation metrics, or trajectories.\n\n## Overview\n\nRun a full calibration on the bundled sample dataset (`sdg_08_2_sample_data_010926.zip`, 4 synthetic warehouse cameras with ground truth) against a running AutoMagicCalib microservice. Useful for verifying that a freshly-launched stack works end-to-end before throwing real data at it.\n\nThe sample includes GT, so the run produces evaluation metrics (L2 distance, reprojection error) — no calibration parameter tuning needed.\n\n## Prerequisites\n\n- [ ] AMC microservice running (follow `skills\u002Famc-setup-calibration-stack\u002FSKILL.md` if not)\n- [ ] Sample zip present at `assets\u002Fsdg_08_2_sample_data_010926.zip`\n- [ ] Python 3 with `requests` available, or use the Swagger UI path below\n  - The bundled script self-heals: if `requests` is missing it creates a throwaway venv under `${TMPDIR:-\u002Ftmp}\u002Famc-sample-test-venv` (nothing written to the repo)\n  - If `python3 -m venv` itself fails with `ensurepip not available`: `sudo apt install -y python3-venv python3-pip`\n\n## Instructions\n\n**\"launch AMC and test sample dataset\" (or similar):**\n\n1. Run `skills\u002Famc-setup-calibration-stack\u002FSKILL.md` first.\n2. Wait for `\u002Fv1\u002Fready` to return OK.\n3. Extract sample data (snippet below) — idempotent, safe to re-run.\n4. Run the bundled script in [Run Script](#run-script).\n5. Report final metrics + UI URL for manual inspection.\n6. VGGT refinement is attempted by default when the project reports `vggt_state: READY`; otherwise the script explains that VGGT setup is optional and can be enabled later for refinement.\n\n**\"test sample dataset\" (MS already running):**\n\n1. Detect backend: scan ports 8000–8009 for a `\u002Fv1\u002Fready` response.\n2. If none → point to the setup skill.\n3. Extract sample data if not already cached.\n4. Run the bundled script.\n5. Report metrics.\n\n### Detect Running Backend\n\n```bash\nMS_PORT=\"\"\nfor port in {8000..8009}; do\n  if curl -s \"http:\u002F\u002Flocalhost:$port\u002Fv1\u002Fready\" | grep -q '\"code\":0'; then\n    MS_PORT=$port; break\n  fi\ndone\n[ -z \"$MS_PORT\" ] && { echo \"No running backend. Run amc-setup-calibration-stack skill first.\"; exit 1; }\necho \"Backend on port $MS_PORT\"\n```\n\n### Locate + Extract Sample Data (idempotent)\n\n```bash\nexport REPO_ROOT=$(git rev-parse --show-toplevel)\n\nSAMPLE_ZIP=\"$REPO_ROOT\u002Fassets\u002Fsdg_08_2_sample_data_010926.zip\"\n[ -f \"$SAMPLE_ZIP\" ] || { echo \"Sample zip not found at $SAMPLE_ZIP\"; exit 1; }\n\n# Cache directory next to the zip.\nSAMPLE_DIR=\"$(dirname \"$SAMPLE_ZIP\")\u002F.cache\u002Fsdg_08_2_sample_data_010926\"\n\nif [ ! -d \"$SAMPLE_DIR\" ]; then\n  mkdir -p \"$SAMPLE_DIR\"\n  unzip -q \"$SAMPLE_ZIP\" -d \"$SAMPLE_DIR\"\nfi\nls \"$SAMPLE_DIR\"\n# Expected (possibly inside a wrapper folder): alignment_data\u002F  GT.zip  videos\u002F\n```\n\n## Run Script\n\nRun `scripts\u002Frun_sample_calibration.py` from the `auto-magic-calib` repo root, or set `REPO_ROOT=\u002Fpath\u002Fto\u002Fauto-magic-calib`. The script reads `compose\u002F.env` for the backend port, accepts `BASE_URL`, `MS_PORT`, `SAMPLE_DIR`, and `RUN_VGGT` overrides, creates a fresh project each run, attempts VGGT when ready, and prints the NGC warehouse dataset note at the end.\n\n## Alternative: Swagger UI Walkthrough\n\n> **Agent shortcut**: if the user explicitly requested a Swagger UI walkthrough (or said \"no Python\"), emit the table below and stop — do not invoke shell tooling, read other sections, or run the bundled Python script.\n\nThe microservice exposes an interactive OpenAPI UI at **`http:\u002F\u002F\u003CHOST_IP>:\u003CMS_PORT>\u002Fdocs`**. If you prefer clicking through the API by hand:\n\n1. Open `http:\u002F\u002F\u003CHOST_IP>:\u003CMS_PORT>\u002Fdocs` in a browser.\n2. Unzip `sdg_08_2_sample_data_010926.zip` into a cache directory next to it.\n3. Execute these endpoints **in order**, copying the `project_id` from step 1 into subsequent paths:\n\n   | # | Endpoint | Body \u002F Files |\n   |---|---|---|\n   | 1 | `POST \u002Fv1\u002Fcreate_project` | `project_name`: any string |\n   | 2 | `POST \u002Fv1\u002Fupload_video_files\u002F{project_id}` | `files`: upload all 4 `videos\u002Fcam_0*.mp4` **sorted by name** |\n   | 3 | `POST \u002Fv1\u002Fupload_alignment\u002F{project_id}` | `alignment_file`: `alignment_data\u002Falignment_data.json` |\n   | 4 | `POST \u002Fv1\u002Fupload_layout\u002F{project_id}` | `layout_file`: `alignment_data\u002Flayout.png` |\n   | 5 | `POST \u002Fv1\u002Fupload_gt_file\u002F{project_id}` | `gt_file`: `GT.zip` |\n   | 6 | `POST \u002Fv1\u002Fverify_project\u002F{project_id}` | — (expect `project_state: READY`) |\n   | 7 | `POST \u002Fv1\u002Fcalibrate\u002F{project_id}` | JSON: `{\"detector_type\": \"resnet\"}` |\n   | 8 | `GET \u002Fv1\u002Fget_project_info\u002F{project_id}` | Refresh every ~10 s until `project_state` = `COMPLETED` |\n   | 9 | `GET \u002Fv1\u002Fresult\u002F{project_id}\u002Fevaluation_statistics` | Read L2 distance + reprojection error |\n   | 10 optional | `POST \u002Fv1\u002Fvggt\u002Fcalibrate\u002F{project_id}` then `GET \u002Fv1\u002Fvggt_results\u002F{project_id}\u002Fevaluation_statistics` | Run only when `vggt_state` is `READY`; poll `vggt_state` until `COMPLETED` |\n\nThis is the same sequence the bundled Python script runs, just executed manually. Step 10 is attempted by default when `vggt_state` is `READY`; otherwise it is skipped with setup guidance.\n\n### Status Fields from `get_project_info`\n\n`project_info.project_state` is the AMC calibration lifecycle for the project. Poll it until it reaches `COMPLETED` (or stop on `ERROR`).\n\n`project_info.vggt_state` is a **per-project** VGGT refinement lifecycle, a project-scoped status rather than a direct global service or model-load status. A newly created project can report `vggt_state: \"INIT\"` even when the VGGT model is present and mounted. The expected lifecycle is `INIT` → `READY` after AMC calibration completes → `RUNNING` while VGGT refinement runs → `COMPLETED` (or `ERROR`). Interpret `INIT` on a new or uncalibrated project as normal project state. If AMC calibration is complete and the project remains in a non-ready VGGT state, confirm VGGT setup and model availability with the setup skill checks and service logs.\n\n## Success Criteria\n\n- Project reaches `project_state == \"COMPLETED\"` within ~30 min.\n- `\u002Fv1\u002Fresult\u002F{id}\u002Fevaluation_statistics` returns non-empty `statistics` (GT was uploaded).\n- VGGT either runs to `vggt_state == \"COMPLETED\"` and reports `\u002Fv1\u002Fvggt_results\u002F{id}\u002Fevaluation_statistics`, or is skipped with setup guidance because the project is not `READY` for VGGT.\n- No `ERROR` state encountered.\n\nRepresentative metrics for the sample (yours should be similar):\n\n```\nAverage L2 distance(m)               : \u003C 1.5\nAverage reprojection error 0(px)     : \u003C 10\n```\n\n## Key Output Files (on the server)\n\nResults persist under `$REPO_ROOT\u002Fprojects\u002Fproject_\u003Cproject_id>\u002F`:\n\n```\nprojects\u002Fproject_\u003Cproject_id>\u002F\n├── output\u002F\n│   ├── single_view_results\u002Fcam_XX\u002F\n│   │   ├── camInfo_hyper_XX.yaml\n│   │   └── trajDump_Stream_0_3d.txt\n│   └── multi_view_results\u002FBA_output\u002Fresults_ba\u002Frefined\u002F\n│       └── camInfo_XX.yaml          # ← final calibration (use this)\n└── calibration.log\n```\n\n## Monitoring Progress\n\n```bash\nPROJECT_ID=\u003Cid_from_step_1>\nREPO_ROOT=$(git rev-parse --show-toplevel)\ntail -F --retry \"$REPO_ROOT\u002Fprojects\u002Fproject_${PROJECT_ID}\u002Fcalibration.log\"\n```\n\nOr stream MS logs:\n\n```bash\nREPO_ROOT=$(git rev-parse --show-toplevel)\ndocker compose -f \"$REPO_ROOT\u002Fcompose\u002Fcompose.yml\" logs -f auto-magic-calib-ms\n```\n\n## Troubleshooting\n\n| Issue | Fix |\n|---|---|\n| `requests` not installed | Inside a venv: `python3 -m venv venv && .\u002Fvenv\u002Fbin\u002Fpip install requests`. If `python3 -m venv` fails: `sudo apt install -y python3-venv python3-pip` first |\n| `[2] Uploaded N videos` where N >> 4 | `SAMPLE_DIR` resolved to the repo root (or another over-broad path) and `rglob(\"cam_*.mp4\")` swept stale videos from `.cache\u002F`, `projects\u002F`, etc. Stop the run (`POST \u002Fv1\u002Fstop_calibration\u002F{id}`), delete the project (`DELETE \u002Fv1\u002Fdelete_project\u002F{id}`), set `SAMPLE_DIR` explicitly to the extracted sample dir, re-run. The script anchors on `videos\u002F` and asserts `len(videos) \u003C= 16` to fail loud |\n| `verify_project` returns state `!= READY` | Confirm all 4 videos + alignment + layout + GT uploaded; inspect `GET \u002Fv1\u002Fget_project_info\u002F{id}` response |\n| Sample not extracted | `unzip \u003Crepo_root>\u002Fassets\u002Fsdg_08_2_sample_data_010926.zip -d \u003Crepo_root>\u002Fassets\u002F.cache\u002Fsdg_08_2_sample_data_010926\u002F` |\n| `cam_*.mp4` glob finds 0 files | Check wrapper-folder depth: `find \u003Csample_dir> -name \"cam_*.mp4\"` |\n| Calibration times out (>60 min) | Check `calibration.log` for \"insufficient tracklets\"; see root `README.md` guidelines on input videos |\n| Upload returns 413 | Raise server upload limit, or split files (sample files are \u003C200 MB total so this is unusual) |\n| Port scan finds no backend | Backend not running — run `amc-setup-calibration-stack` skill |\n\n## Additional Sample Dataset\n\nThe root `README.md` also documents `nv_warehouse_032326.zip`, a real-world warehouse dataset available from NGC. Download it with `ngc registry resource download-version \"nvidia\u002Famc-nv-warehouse\"`; then use `amc-run-video-calibration`, upload `nv_warehouse_config.json` in the config step, and run with the `transformer` detector. It does not include ground-truth data.\n\n## Related Skills\n\n- `skills\u002Famc-setup-calibration-stack\u002FSKILL.md` — launch MS + UI (prerequisite).\n- `skills\u002Famc-run-video-calibration\u002FSKILL.md` — run calibration on your own pre-recorded MP4s.\n\nRoot `README.md` \"Sample Data Setup\" and \"Calibration Workflow (UI)\" sections cover the human-oriented path through the same sample.\n\n\u003C!-- signing marker -->\n","# Skill: Calibrate Sample Dataset\n\n## When to Use This Skill\n\nActivate this skill when the user wants to sanity-check a running AMC stack with the bundled sample dataset. Typical prompts:\n\n- \"test the sample dataset\" \u002F \"run sample calibration\"\n- \"verify AMC install\"\n- \"launch and test\" (chain with `amc-setup-calibration-stack` if the MS isn't already running)\n\n**Do NOT use this skill when:**\n\n- The user references their own video paths (e.g. `\u002Fdata\u002Fvideos\u002F`, `cam_*.mp4` not from the bundled zip) — route to `amc-run-video-calibration`. This skill is exclusively for `assets\u002Fsdg_08_2_sample_data_010926.zip`.\n\nPrerequisite: AMC microservice running on a port in 8000-8009. If no backend is detected, delegate to `amc-setup-calibration-stack` first.\n\nIf execution cannot proceed in the current environment (no backend, missing sample data, etc.), surface the blocker AND describe the expected workflow + API sequence concisely so the user understands what will run once prerequisites are met. Do not fabricate calibration outputs, evaluation metrics, or trajectories.\n\n## Overview\n\nRun a full calibration on the bundled sample dataset (`sdg_08_2_sample_data_010926.zip`, 4 synthetic warehouse cameras with ground truth) against a running AutoMagicCalib microservice. Useful for verifying that a freshly-launched stack works end-to-end before throwing real data at it.\n\nThe sample includes GT, so the run produces evaluation metrics (L2 distance, reprojection error) — no calibration parameter tuning needed.\n\n## Prerequisites\n\n- [ ] AMC microservice running (follow `skills\u002Famc-setup-calibration-stack\u002FSKILL.md` if not)\n- [ ] Sample zip present at `assets\u002Fsdg_08_2_sample_data_010926.zip`\n- [ ] Python 3 with `requests` available, or use the Swagger UI path below\n  - The bundled script self-heals: if `requests` is missing it creates a throwaway venv under `${TMPDIR:-\u002Ftmp}\u002Famc-sample-test-venv` (nothing written to the repo)\n  - If `python3 -m venv` itself fails with `ensurepip not available`: `sudo apt install -y python3-venv python3-pip`\n\n## Instructions\n\n**\"launch AMC and test sample dataset\" (or similar):**\n\n1. Run `skills\u002Famc-setup-calibration-stack\u002FSKILL.md` first.\n2. Wait for `\u002Fv1\u002Fready` to return OK.\n3. Extract sample data (snippet below) — idempotent, safe to re-run.\n4. Run the bundled script in [Run Script](#run-script).\n5. Report final metrics + UI URL for manual inspection.\n6. VGGT refinement is attempted by default when the project reports `vggt_state: READY`; otherwise the script explains that VGGT setup is optional and can be enabled later for refinement.\n\n**\"test sample dataset\" (MS already running):**\n\n1. Detect backend: scan ports 8000–8009 for a `\u002Fv1\u002Fready` response.\n2. If none → point to the setup skill.\n3. Extract sample data if not already cached.\n4. Run the bundled script.\n5. Report metrics.\n\n### Detect Running Backend\n\n```bash\nMS_PORT=\"\"\nfor port in {8000..8009}; do\n  if curl -s \"http:\u002F\u002Flocalhost:$port\u002Fv1\u002Fready\" | grep -q '\"code\":0'; then\n    MS_PORT=$port; break\n  fi\ndone\n[ -z \"$MS_PORT\" ] && { echo \"No running backend. Run amc-setup-calibration-stack skill first.\"; exit 1; }\necho \"Backend on port $MS_PORT\"\n```\n\n### Locate + Extract Sample Data (idempotent)\n\n```bash\nexport REPO_ROOT=$(git rev-parse --show-toplevel)\n\nSAMPLE_ZIP=\"$REPO_ROOT\u002Fassets\u002Fsdg_08_2_sample_data_010926.zip\"\n[ -f \"$SAMPLE_ZIP\" ] || { echo \"Sample zip not found at $SAMPLE_ZIP\"; exit 1; }\n\n# Cache directory next to the zip.\nSAMPLE_DIR=\"$(dirname \"$SAMPLE_ZIP\")\u002F.cache\u002Fsdg_08_2_sample_data_010926\"\n\nif [ ! -d \"$SAMPLE_DIR\" ]; then\n  mkdir -p \"$SAMPLE_DIR\"\n  unzip -q \"$SAMPLE_ZIP\" -d \"$SAMPLE_DIR\"\nfi\nls \"$SAMPLE_DIR\"\n# Expected (possibly inside a wrapper folder): alignment_data\u002F  GT.zip  videos\u002F\n```\n\n## Run Script\n\nRun `scripts\u002Frun_sample_calibration.py` from the `auto-magic-calib` repo root, or set `REPO_ROOT=\u002Fpath\u002Fto\u002Fauto-magic-calib`. The script reads `compose\u002F.env` for the backend port, accepts `BASE_URL`, `MS_PORT`, `SAMPLE_DIR`, and `RUN_VGGT` overrides, creates a fresh project each run, attempts VGGT when ready, and prints the NGC warehouse dataset note at the end.\n\n## Alternative: Swagger UI Walkthrough\n\n> **Agent shortcut**: if the user explicitly requested a Swagger UI walkthrough (or said \"no Python\"), emit the table below and stop — do not invoke shell tooling, read other sections, or run the bundled Python script.\n\nThe microservice exposes an interactive OpenAPI UI at **`http:\u002F\u002F\u003CHOST_IP>:\u003CMS_PORT>\u002Fdocs`**. If you prefer clicking through the API by hand:\n\n1. Open `http:\u002F\u002F\u003CHOST_IP>:\u003CMS_PORT>\u002Fdocs` in a browser.\n2. Unzip `sdg_08_2_sample_data_010926.zip` into a cache directory next to it.\n3. Execute these endpoints **in order**, copying the `project_id` from step 1 into subsequent paths:\n\n   | # | Endpoint | Body \u002F Files |\n   |---|---|---|\n   | 1 | `POST \u002Fv1\u002Fcreate_project` | `project_name`: any string |\n   | 2 | `POST \u002Fv1\u002Fupload_video_files\u002F{project_id}` | `files`: upload all 4 `videos\u002Fcam_0*.mp4` **sorted by name** |\n   | 3 | `POST \u002Fv1\u002Fupload_alignment\u002F{project_id}` | `alignment_file`: `alignment_data\u002Falignment_data.json` |\n   | 4 | `POST \u002Fv1\u002Fupload_layout\u002F{project_id}` | `layout_file`: `alignment_data\u002Flayout.png` |\n   | 5 | `POST \u002Fv1\u002Fupload_gt_file\u002F{project_id}` | `gt_file`: `GT.zip` |\n   | 6 | `POST \u002Fv1\u002Fverify_project\u002F{project_id}` | — (expect `project_state: READY`) |\n   | 7 | `POST \u002Fv1\u002Fcalibrate\u002F{project_id}` | JSON: `{\"detector_type\": \"resnet\"}` |\n   | 8 | `GET \u002Fv1\u002Fget_project_info\u002F{project_id}` | Refresh every ~10 s until `project_state` = `COMPLETED` |\n   | 9 | `GET \u002Fv1\u002Fresult\u002F{project_id}\u002Fevaluation_statistics` | Read L2 distance + reprojection error |\n   | 10 optional | `POST \u002Fv1\u002Fvggt\u002Fcalibrate\u002F{project_id}` then `GET \u002Fv1\u002Fvggt_results\u002F{project_id}\u002Fevaluation_statistics` | Run only when `vggt_state` is `READY`; poll `vggt_state` until `COMPLETED` |\n\nThis is the same sequence the bundled Python script runs, just executed manually. Step 10 is attempted by default when `vggt_state` is `READY`; otherwise it is skipped with setup guidance.\n\n### Status Fields from `get_project_info`\n\n`project_info.project_state` is the AMC calibration lifecycle for the project. Poll it until it reaches `COMPLETED` (or stop on `ERROR`).\n\n`project_info.vggt_state` is a **per-project** VGGT refinement lifecycle, a project-scoped status rather than a direct global service or model-load status. A newly created project can report `vggt_state: \"INIT\"` even when the VGGT model is present and mounted. The expected lifecycle is `INIT` → `READY` after AMC calibration completes → `RUNNING` while VGGT refinement runs → `COMPLETED` (or `ERROR`). Interpret `INIT` on a new or uncalibrated project as normal project state. If AMC calibration is complete and the project remains in a non-ready VGGT state, confirm VGGT setup and model availability with the setup skill checks and service logs.\n\n## Success Criteria\n\n- Project reaches `project_state == \"COMPLETED\"` within ~30 min.\n- `\u002Fv1\u002Fresult\u002F{id}\u002Fevaluation_statistics` returns non-empty `statistics` (GT was uploaded).\n- VGGT either runs to `vggt_state == \"COMPLETED\"` and reports `\u002Fv1\u002Fvggt_results\u002F{id}\u002Fevaluation_statistics`, or is skipped with setup guidance because the project is not `READY` for VGGT.\n- No `ERROR` state encountered.\n\nRepresentative metrics for the sample (yours should be similar):\n\n```\nAverage L2 distance(m)               : \u003C 1.5\nAverage reprojection error 0(px)     : \u003C 10\n```\n\n## Key Output Files (on the server)\n\nResults persist under `$REPO_ROOT\u002Fprojects\u002Fproject_\u003Cproject_id>\u002F`:\n\n```\nprojects\u002Fproject_\u003Cproject_id>\u002F\n├── output\u002F\n│   ├── single_view_results\u002Fcam_XX\u002F\n│   │   ├── camInfo_hyper_XX.yaml\n│   │   └── trajDump_Stream_0_3d.txt\n│   └── multi_view_results\u002FBA_output\u002Fresults_ba\u002Frefined\u002F\n│       └── camInfo_XX.yaml          # ← final calibration (use this)\n└── calibration.log\n```\n\n## Monitoring Progress\n\n```bash\nPROJECT_ID=\u003Cid_from_step_1>\nREPO_ROOT=$(git rev-parse --show-toplevel)\ntail -F --retry \"$REPO_ROOT\u002Fprojects\u002Fproject_${PROJECT_ID}\u002Fcalibration.log\"\n```\n\nOr stream MS logs:\n\n```bash\nREPO_ROOT=$(git rev-parse --show-toplevel)\ndocker compose -f \"$REPO_ROOT\u002Fcompose\u002Fcompose.yml\" logs -f auto-magic-calib-ms\n```\n\n## Troubleshooting\n\n| Issue | Fix |\n|---|---|\n| `requests` not installed | Inside a venv: `python3 -m venv venv && .\u002Fvenv\u002Fbin\u002Fpip install requests`. If `python3 -m venv` fails: `sudo apt install -y python3-venv python3-pip` first |\n| `[2] Uploaded N videos` where N >> 4 | `SAMPLE_DIR` resolved to the repo root (or another over-broad path) and `rglob(\"cam_*.mp4\")` swept stale videos from `.cache\u002F`, `projects\u002F`, etc. Stop the run (`POST \u002Fv1\u002Fstop_calibration\u002F{id}`), delete the project (`DELETE \u002Fv1\u002Fdelete_project\u002F{id}`), set `SAMPLE_DIR` explicitly to the extracted sample dir, re-run. The script anchors on `videos\u002F` and asserts `len(videos) \u003C= 16` to fail loud |\n| `verify_project` returns state `!= READY` | Confirm all 4 videos + alignment + layout + GT uploaded; inspect `GET \u002Fv1\u002Fget_project_info\u002F{id}` response |\n| Sample not extracted | `unzip \u003Crepo_root>\u002Fassets\u002Fsdg_08_2_sample_data_010926.zip -d \u003Crepo_root>\u002Fassets\u002F.cache\u002Fsdg_08_2_sample_data_010926\u002F` |\n| `cam_*.mp4` glob finds 0 files | Check wrapper-folder depth: `find \u003Csample_dir> -name \"cam_*.mp4\"` |\n| Calibration times out (>60 min) | Check `calibration.log` for \"insufficient tracklets\"; see root `README.md` guidelines on input videos |\n| Upload returns 413 | Raise server upload limit, or split files (sample files are \u003C200 MB total so this is unusual) |\n| Port scan finds no backend | Backend not running — run `amc-setup-calibration-stack` skill |\n\n## Additional Sample Dataset\n\nThe root `README.md` also documents `nv_warehouse_032326.zip`, a real-world warehouse dataset available from NGC. Download it with `ngc registry resource download-version \"nvidia\u002Famc-nv-warehouse\"`; then use `amc-run-video-calibration`, upload `nv_warehouse_config.json` in the config step, and run with the `transformer` detector. It does not include ground-truth data.\n\n## Related Skills\n\n- `skills\u002Famc-setup-calibration-stack\u002FSKILL.md` — launch MS + UI (prerequisite).\n- `skills\u002Famc-run-video-calibration\u002FSKILL.md` — run calibration on your own pre-recorded MP4s.\n\nRoot `README.md` \"Sample Data Setup\" and \"Calibration Workflow (UI)\" sections cover the human-oriented path through the same sample.\n\n\u003C!-- signing marker -->\n",{"name":5,"owner":24,"license":15,"service":25,"version":26,"metadata":27,"reviewed":35,"description":7,"data_classification":36},"NVIDIA CORPORATION","auto-magic-calib","1.0.0",{"tags":28},[29,30,31,32,33,34],"amc","calibration","sample","rest-api","validation","python","2026-04-28","public","main","1c523aba5cdf867a79f078847075492d7778092a","skills\u002Fnvidia\u002Famc-run-sample-calibration",1,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills","https:\u002F\u002Fskills.x402.wtf","https:\u002F\u002Fgithub.com\u002Fthemusebook","https:\u002F\u002Fmusebook.trade","The official Github of musebook","2026-11-02 23:42:26",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add themusebook\u002Fskills --skill amc-run-sample-calibration",{"tool":53,"command":54},"bunx","bunx skills add themusebook\u002Fskills --skill amc-run-sample-calibration",{"tool":56,"command":57},"pnpm","pnpm dlx skills add themusebook\u002Fskills --skill amc-run-sample-calibration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Famc-run-sample-calibration\u002FSKILL.md",true,[61,67,71,77,81],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"BENCHMARK.md","REFERENCE","参考文档",4511,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Famc-run-sample-calibration\u002FBENCHMARK.md",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"evals\u002Fevals.json",5257,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Famc-run-sample-calibration\u002Fevals\u002Fevals.json",{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"scripts\u002Frun_sample_calibration.py","SCRIPT","脚本",9817,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Famc-run-sample-calibration\u002Fscripts\u002Frun_sample_calibration.py",{"path":78,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":79,"sourceHtmlUrl":80},"skill-card.md",3675,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Famc-run-sample-calibration\u002Fskill-card.md",{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"skill.oms.sig","OTHER","其他",4929,"https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Famc-run-sample-calibration\u002Fskill.oms.sig",[88,97,104,111,118,125],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7AB34SPKVSDRRG009PM1CZH","youtube-clipper","YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video","MIT","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7AB18BH6N7KR7939HRNWVMQ","viem-integration","Integrate EVM blockchains using viem. Use when user says \"read blockchain data\", \"send transaction\", \"interact with smart contract\", \"connect to Ethereum\", \"use viem\", \"use wagmi\", \"wallet integration\", \"viem setup\", or mentions blockchain\u002FEVM development with TypeScript.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fviem-integration\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7AB12GHGP48WCNXDQQ9222H","v4-security-foundations","Security-first Uniswap v4 hook development. Use when user mentions \"v4 hooks\", \"hook security\", \"PoolManager\", \"beforeSwap\", \"afterSwap\", or asks about V4 hook best practices, vulnerabilities, or audit requirements.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fv4-security-foundations\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":19},"01M7AB0XM3PSR7V3Q2ZRR0Q0FB","v4-sdk-integration","App-layer SDK guide for building swap and liquidity experiences directly with the Uniswap v4 SDK. Use when user asks about \"v4 sdk\", \"uniswap v4\", \"v4 swap\", \"v4 liquidity\", \"PoolManager\", \"V4Planner\", \"StateView\", \"PositionManager\", \"pool state\", \"v4 position\", \"uniswap sdk\", or when building swap\u002Fliquidity UX directly with SDKs rather than via the Trading API.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fv4-sdk-integration\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":19},"01M7AB0SGA93ASA588DJW4P9WT","v4-hook-generator","Generate Uniswap v4 hook contracts via OpenZeppelin MCP. Use when building custom swap logic, async swaps, hook-owned liquidity, custom curves, dynamic fees, MEV protection, limit orders, or oracle hooks.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fv4-hook-generator\u002FSKILL.md",[],[],{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":19},"01M7AAZYH75H4CS03WSW2EZ8DM","testing","For testing with Light Protocol programs and clients on localnet, devnet, and mainnet validation.","https:\u002F\u002Fgithub.com\u002Fthemusebook\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftesting\u002FSKILL.md",[],[]]