[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7967MWK719F9QSM8JPCPM91":3,"skill-same:01M7967MWK719F9QSM8JPCPM91":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M7967MWK719F9QSM8JPCPM91","dataset-and-assets",null,"Prepare, validate, and troubleshoot tf-faster-rcnn dataset folders, registry names, roidb caches, pretrained checkpoints, ImageNet initialization weights, and output\u002Ftensorboard artifact paths without downloads or training.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftf-faster-rcnn\u002Fsub-skills\u002Fdataset-and-assets\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dataset-and-assets\ndescription: \"Prepare, validate, and troubleshoot tf-faster-rcnn dataset\n  folders, registry names, roidb caches, pretrained checkpoints, ImageNet\n  initialization weights, and output\u002Ftensorboard artifact paths without\n  downloads or training.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# dataset-and-assets\n\nUse this sub-skill when a future Researcher needs to place or validate VOC\u002FCOCO data, understand dataset registry names, reason about `roidb` and `data\u002Fcache`, place pretrained Faster R-CNN checkpoints or ImageNet initialization weights, or locate generated output and TensorBoard artifacts for `tf-faster-rcnn`.\n\nDo **not** use this sub-skill for dependency installation, Cython\u002FCUDA build failures, TensorFlow compatibility, or NMS extension import errors; route those to `installation-and-configuration`. Do **not** include or construct training\u002Ftest\u002Fdemo commands here; route command construction and runtime choices to `training-and-evaluation` or `inference-and-demo`.\n\n## Operating inputs\n\n- A checkout root, referenced below as `\u003Crepo-root>`.\n- An intended dataset family: PASCAL VOC, COCO, the bundled `data\u002Fdemo` images, pretrained Faster R-CNN checkpoint assets, and\u002For ImageNet initialization weights.\n- Whether the user wants a read-only validation of paths or instructions for arranging existing local\u002Fdownloaded assets. Never download from this sub-skill without explicit user approval; the bundled validator performs no network access.\n\n## Exact dataset registry keys\n\n`lib\u002Fdatasets\u002Ffactory.py` registers 23 keys. Use these exact strings for `--imdb` values and for roidb\u002Fcache names:\n\n- VOC 2007: `voc_2007_train`, `voc_2007_val`, `voc_2007_trainval`, `voc_2007_test`\n- VOC 2012: `voc_2012_train`, `voc_2012_val`, `voc_2012_trainval`, `voc_2012_test`\n- VOC 2007 difficult-inclusive variants: `voc_2007_train_diff`, `voc_2007_val_diff`, `voc_2007_trainval_diff`, `voc_2007_test_diff`\n- VOC 2012 difficult-inclusive variants: `voc_2012_train_diff`, `voc_2012_val_diff`, `voc_2012_trainval_diff`, `voc_2012_test_diff`\n- COCO 2014: `coco_2014_train`, `coco_2014_val`, `coco_2014_minival`, `coco_2014_valminusminival`, `coco_2014_trainval`\n- COCO 2015: `coco_2015_test`, `coco_2015_test-dev`\n\n`voc_2007_trainval+voc_2012_trainval` and `coco_2014_train+coco_2014_valminusminival` are not registry keys accepted directly by `get_imdb`; they are combined training-set strings split by `tools\u002Ftrainval_net.py`. Route command use of those combined strings to `training-and-evaluation`.\n\n## Asset workflow\n\n1. Establish `\u003Crepo-root>` and treat `\u003Crepo-root>\u002Fdata` as `cfg.DATA_DIR`.\n2. Pick the registry key(s) or source-supported combined training string needed by the downstream task.\n3. Validate the intended layout with the bundled script:\n\n   ```bash\n   python \u003Cskill-dir>\u002Fscripts\u002Fvalidate_layout.py --repo-root \u003Crepo-root> --check voc\n   python \u003Cskill-dir>\u002Fscripts\u002Fvalidate_layout.py --repo-root \u003Crepo-root> --check coco\n   python \u003Cskill-dir>\u002Fscripts\u002Fvalidate_layout.py --repo-root \u003Crepo-root> --check demo-model\n   python \u003Cskill-dir>\u002Fscripts\u002Fvalidate_layout.py --repo-root \u003Crepo-root> --check imagenet\n   ```\n\n   Omit `--check` to run all layout checks. The script reports deterministic JSON and exits nonzero when required expected paths for the selected check are absent.\n4. If data annotations or image-set files changed, remove stale `data\u002Fcache\u002F\u003Cimdb-name>_gt_roidb.pkl` files before the next dataset constructor run.\n5. For pretrained checkpoint placement and output\u002FTensorBoard path reasoning, use `references\u002Fmodel-artifacts.md`.\n\n## Reference map\n\n- `references\u002Fdata-layouts.md`: VOC\u002FCOCO folder contracts, exact registry keys, image-name patterns, `roidb` dict fields, cache semantics, and safe validation examples.\n- `references\u002Fmodel-artifacts.md`: pretrained Faster R-CNN checkpoint layout, `data\u002Fimagenet_weights` naming, snapshot sidecars, demo-model symlink layout, and output\u002FTensorBoard path formulas.\n- `references\u002Ftroubleshooting.md`: common missing-path, stale-cache, split-file, checkpoint-sidecar, and route-to-other-sub-skill decisions.\n- `scripts\u002Fvalidate_layout.py`: safe stdlib-only path\u002Fname validator; no imports from the legacy repo, no downloads, no dataset parsing, no TensorFlow execution.\n\n## Guardrails\n\n- Do not run `data\u002Fscripts\u002Ffetch_faster_rcnn_models.sh` automatically. It downloads a large archive and depends on an old external server.\n- Do not assert full COCO\u002FVOC data correctness from path checks alone; this sub-skill validates expected paths and names, not annotation content.\n- Do not treat CUDA\u002FNVCC\u002FTensorFlow errors as dataset problems. Route install\u002Fbuild\u002Fbackend failures to `installation-and-configuration`.\n- Do not generate training\u002Ftest commands in this sub-skill. Route commands, iterations, config overrides, snapshots, resume behavior, and benchmark evaluation to `training-and-evaluation`.\n","# dataset-and-assets\n\nUse this sub-skill when a future Researcher needs to place or validate VOC\u002FCOCO data, understand dataset registry names, reason about `roidb` and `data\u002Fcache`, place pretrained Faster R-CNN checkpoints or ImageNet initialization weights, or locate generated output and TensorBoard artifacts for `tf-faster-rcnn`.\n\nDo **not** use this sub-skill for dependency installation, Cython\u002FCUDA build failures, TensorFlow compatibility, or NMS extension import errors; route those to `installation-and-configuration`. Do **not** include or construct training\u002Ftest\u002Fdemo commands here; route command construction and runtime choices to `training-and-evaluation` or `inference-and-demo`.\n\n## Operating inputs\n\n- A checkout root, referenced below as `\u003Crepo-root>`.\n- An intended dataset family: PASCAL VOC, COCO, the bundled `data\u002Fdemo` images, pretrained Faster R-CNN checkpoint assets, and\u002For ImageNet initialization weights.\n- Whether the user wants a read-only validation of paths or instructions for arranging existing local\u002Fdownloaded assets. Never download from this sub-skill without explicit user approval; the bundled validator performs no network access.\n\n## Exact dataset registry keys\n\n`lib\u002Fdatasets\u002Ffactory.py` registers 23 keys. Use these exact strings for `--imdb` values and for roidb\u002Fcache names:\n\n- VOC 2007: `voc_2007_train`, `voc_2007_val`, `voc_2007_trainval`, `voc_2007_test`\n- VOC 2012: `voc_2012_train`, `voc_2012_val`, `voc_2012_trainval`, `voc_2012_test`\n- VOC 2007 difficult-inclusive variants: `voc_2007_train_diff`, `voc_2007_val_diff`, `voc_2007_trainval_diff`, `voc_2007_test_diff`\n- VOC 2012 difficult-inclusive variants: `voc_2012_train_diff`, `voc_2012_val_diff`, `voc_2012_trainval_diff`, `voc_2012_test_diff`\n- COCO 2014: `coco_2014_train`, `coco_2014_val`, `coco_2014_minival`, `coco_2014_valminusminival`, `coco_2014_trainval`\n- COCO 2015: `coco_2015_test`, `coco_2015_test-dev`\n\n`voc_2007_trainval+voc_2012_trainval` and `coco_2014_train+coco_2014_valminusminival` are not registry keys accepted directly by `get_imdb`; they are combined training-set strings split by `tools\u002Ftrainval_net.py`. Route command use of those combined strings to `training-and-evaluation`.\n\n## Asset workflow\n\n1. Establish `\u003Crepo-root>` and treat `\u003Crepo-root>\u002Fdata` as `cfg.DATA_DIR`.\n2. Pick the registry key(s) or source-supported combined training string needed by the downstream task.\n3. Validate the intended layout with the bundled script:\n\n   ```bash\n   python \u003Cskill-dir>\u002Fscripts\u002Fvalidate_layout.py --repo-root \u003Crepo-root> --check voc\n   python \u003Cskill-dir>\u002Fscripts\u002Fvalidate_layout.py --repo-root \u003Crepo-root> --check coco\n   python \u003Cskill-dir>\u002Fscripts\u002Fvalidate_layout.py --repo-root \u003Crepo-root> --check demo-model\n   python \u003Cskill-dir>\u002Fscripts\u002Fvalidate_layout.py --repo-root \u003Crepo-root> --check imagenet\n   ```\n\n   Omit `--check` to run all layout checks. The script reports deterministic JSON and exits nonzero when required expected paths for the selected check are absent.\n4. If data annotations or image-set files changed, remove stale `data\u002Fcache\u002F\u003Cimdb-name>_gt_roidb.pkl` files before the next dataset constructor run.\n5. For pretrained checkpoint placement and output\u002FTensorBoard path reasoning, use `references\u002Fmodel-artifacts.md`.\n\n## Reference map\n\n- `references\u002Fdata-layouts.md`: VOC\u002FCOCO folder contracts, exact registry keys, image-name patterns, `roidb` dict fields, cache semantics, and safe validation examples.\n- `references\u002Fmodel-artifacts.md`: pretrained Faster R-CNN checkpoint layout, `data\u002Fimagenet_weights` naming, snapshot sidecars, demo-model symlink layout, and output\u002FTensorBoard path formulas.\n- `references\u002Ftroubleshooting.md`: common missing-path, stale-cache, split-file, checkpoint-sidecar, and route-to-other-sub-skill decisions.\n- `scripts\u002Fvalidate_layout.py`: safe stdlib-only path\u002Fname validator; no imports from the legacy repo, no downloads, no dataset parsing, no TensorFlow execution.\n\n## Guardrails\n\n- Do not run `data\u002Fscripts\u002Ffetch_faster_rcnn_models.sh` automatically. It downloads a large archive and depends on an old external server.\n- Do not assert full COCO\u002FVOC data correctness from path checks alone; this sub-skill validates expected paths and names, not annotation content.\n- Do not treat CUDA\u002FNVCC\u002FTensorFlow errors as dataset problems. Route install\u002Fbuild\u002Fbackend failures to `installation-and-configuration`.\n- Do not generate training\u002Ftest commands in this sub-skill. Route commands, iterations, config overrides, snapshots, resume behavior, and benchmark evaluation to `training-and-evaluation`.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Ftf-faster-rcnn\u002Fsub-skills\u002Fdataset-and-assets",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill dataset-and-assets",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill dataset-and-assets",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill dataset-and-assets","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftf-faster-rcnn\u002Fsub-skills\u002Fdataset-and-assets\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdata-layouts.md","REFERENCE","参考文档",8041,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftf-faster-rcnn\u002Fsub-skills\u002Fdataset-and-assets\u002Freferences\u002Fdata-layouts.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmodel-artifacts.md",7003,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftf-faster-rcnn\u002Fsub-skills\u002Fdataset-and-assets\u002Freferences\u002Fmodel-artifacts.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4594,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftf-faster-rcnn\u002Fsub-skills\u002Fdataset-and-assets\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fvalidate_layout.py","SCRIPT","脚本",11249,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftf-faster-rcnn\u002Fsub-skills\u002Fdataset-and-assets\u002Fscripts\u002Fvalidate_layout.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]