[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XZR3JZHS18CEVZKG3XM90":3,"skill-same:01M78XZR3JZHS18CEVZKG3XM90":67},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78XZR3JZHS18CEVZKG3XM90","feature-retrieval",null,"Feature extraction, retrieval descriptors, matching, and HDF5 feature\u002Fmatch formats for hloc.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhierarchical-localization\u002Fsub-skills\u002Ffeature-retrieval\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: feature-retrieval\ndescription: \"Feature extraction, retrieval descriptors, matching, and HDF5\n  feature\u002Fmatch formats for hloc.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Feature Retrieval for Hierarchical-Localization\n\nUse this sub-skill when a task needs `hloc` feature files, global retrieval descriptor files, retrieval pairs, sparse match files, dense LoFTR-derived match files, or guidance for choosing built-in extractor\u002Fmatcher configurations.\n\n## Route here for\n\n- Local feature extraction with `hloc.extract_features.main`, `ImageDataset`, and `extract_features.confs`.\n- Global image retrieval descriptors from the extractor configs `dir`, `netvlad`, `openibl`, or `megaloc`, followed by `hloc.pairs_from_retrieval.main`.\n- Sparse matching with `hloc.match_features.main`, including SuperGlue, LightGlue, nearest-neighbor, and AdaLAM config families.\n- Dense\u002Fsemi-dense matching with `hloc.match_dense.main` and LoFTR config families.\n- HDF5 feature, global descriptor, and match file naming\u002Fschema diagnostics.\n\n## Route elsewhere\n\n- SfM reconstruction, triangulation, pair generation beyond retrieval descriptors, and localization execution: use `..\u002Fmapping-localization\u002F`.\n- Benchmark\u002Fdataset pipeline scripts and large dataset preparation: use `..\u002Fdataset-pipelines\u002F`.\n- Implementing custom extractors\u002Fmatchers or exporting external feature\u002Fmatch files: use `..\u002Fcustom-interop\u002F`.\n\n## Start with these references\n\n1. Read [`references\u002Fapi-and-cli.md`](references\u002Fapi-and-cli.md) for verified signatures, CLI options, exact built-in config names, output naming, and config-family selection.\n2. Read [`references\u002Fhdf5-feature-match-formats.md`](references\u002Fhdf5-feature-match-formats.md) before reading or writing `.h5` feature, global descriptor, or match files.\n3. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when extraction, retrieval, matching, model download, CUDA\u002FCPU, or HDF5 schema errors occur.\n4. Run [`scripts\u002Finspect_hloc_configs.py`](scripts\u002Finspect_hloc_configs.py) in the user's active Python environment to list available installed configs without running neural models.\n\n## Minimal safe patterns\n\n### Extract local features\n\n```python\nfrom pathlib import Path\nfrom hloc import extract_features\n\nimages = Path(\"images\")\noutputs = Path(\"outputs\")\nfeature_conf = extract_features.confs[\"superpoint_aachen\"]\nfeature_path = extract_features.main(feature_conf, images, outputs)\n# Usually: outputs \u002F \"feats-superpoint-n4096-r1024.h5\"\n```\n\n### Extract global descriptors and produce retrieval pairs\n\n```python\nfrom pathlib import Path\nfrom hloc import extract_features, pairs_from_retrieval\n\nimages = Path(\"images\")\noutputs = Path(\"outputs\")\nretrieval_conf = extract_features.confs[\"netvlad\"]\ndescriptor_path = extract_features.main(retrieval_conf, images, outputs)\npairs = outputs \u002F \"pairs-netvlad.txt\"\npairs_from_retrieval.main(descriptor_path, pairs, num_matched=20)\n```\n\n### Match sparse features for a pairs file\n\n```python\nfrom pathlib import Path\nfrom hloc import extract_features, match_features\n\noutputs = Path(\"outputs\")\npairs = outputs \u002F \"pairs-netvlad.txt\"\nfeature_conf = extract_features.confs[\"superpoint_aachen\"]\nmatcher_conf = match_features.confs[\"superglue\"]\nfeature_path = outputs \u002F f\"{feature_conf['output']}.h5\"\nmatch_path = match_features.main(matcher_conf, pairs, feature_conf[\"output\"], outputs)\n# Usually: outputs \u002F \"feats-superpoint-n4096-r1024_matches-superglue_pairs-netvlad.h5\"\n```\n\n### Match with dense LoFTR\n\n```python\nfrom pathlib import Path\nfrom hloc import match_dense\n\nimages = Path(\"images\")\noutputs = Path(\"outputs\")\npairs = outputs \u002F \"pairs-netvlad.txt\"\ndense_conf = match_dense.confs[\"loftr_aachen\"]\nfeatures_path, matches_path = match_dense.main(dense_conf, pairs, images, export_dir=outputs)\n```\n\nDo not assume a feature or match path from memory: compute it from the selected config and pair-file stem, or pass explicit paths via the Python API.\n","# Feature Retrieval for Hierarchical-Localization\n\nUse this sub-skill when a task needs `hloc` feature files, global retrieval descriptor files, retrieval pairs, sparse match files, dense LoFTR-derived match files, or guidance for choosing built-in extractor\u002Fmatcher configurations.\n\n## Route here for\n\n- Local feature extraction with `hloc.extract_features.main`, `ImageDataset`, and `extract_features.confs`.\n- Global image retrieval descriptors from the extractor configs `dir`, `netvlad`, `openibl`, or `megaloc`, followed by `hloc.pairs_from_retrieval.main`.\n- Sparse matching with `hloc.match_features.main`, including SuperGlue, LightGlue, nearest-neighbor, and AdaLAM config families.\n- Dense\u002Fsemi-dense matching with `hloc.match_dense.main` and LoFTR config families.\n- HDF5 feature, global descriptor, and match file naming\u002Fschema diagnostics.\n\n## Route elsewhere\n\n- SfM reconstruction, triangulation, pair generation beyond retrieval descriptors, and localization execution: use `..\u002Fmapping-localization\u002F`.\n- Benchmark\u002Fdataset pipeline scripts and large dataset preparation: use `..\u002Fdataset-pipelines\u002F`.\n- Implementing custom extractors\u002Fmatchers or exporting external feature\u002Fmatch files: use `..\u002Fcustom-interop\u002F`.\n\n## Start with these references\n\n1. Read [`references\u002Fapi-and-cli.md`](references\u002Fapi-and-cli.md) for verified signatures, CLI options, exact built-in config names, output naming, and config-family selection.\n2. Read [`references\u002Fhdf5-feature-match-formats.md`](references\u002Fhdf5-feature-match-formats.md) before reading or writing `.h5` feature, global descriptor, or match files.\n3. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when extraction, retrieval, matching, model download, CUDA\u002FCPU, or HDF5 schema errors occur.\n4. Run [`scripts\u002Finspect_hloc_configs.py`](scripts\u002Finspect_hloc_configs.py) in the user's active Python environment to list available installed configs without running neural models.\n\n## Minimal safe patterns\n\n### Extract local features\n\n```python\nfrom pathlib import Path\nfrom hloc import extract_features\n\nimages = Path(\"images\")\noutputs = Path(\"outputs\")\nfeature_conf = extract_features.confs[\"superpoint_aachen\"]\nfeature_path = extract_features.main(feature_conf, images, outputs)\n# Usually: outputs \u002F \"feats-superpoint-n4096-r1024.h5\"\n```\n\n### Extract global descriptors and produce retrieval pairs\n\n```python\nfrom pathlib import Path\nfrom hloc import extract_features, pairs_from_retrieval\n\nimages = Path(\"images\")\noutputs = Path(\"outputs\")\nretrieval_conf = extract_features.confs[\"netvlad\"]\ndescriptor_path = extract_features.main(retrieval_conf, images, outputs)\npairs = outputs \u002F \"pairs-netvlad.txt\"\npairs_from_retrieval.main(descriptor_path, pairs, num_matched=20)\n```\n\n### Match sparse features for a pairs file\n\n```python\nfrom pathlib import Path\nfrom hloc import extract_features, match_features\n\noutputs = Path(\"outputs\")\npairs = outputs \u002F \"pairs-netvlad.txt\"\nfeature_conf = extract_features.confs[\"superpoint_aachen\"]\nmatcher_conf = match_features.confs[\"superglue\"]\nfeature_path = outputs \u002F f\"{feature_conf['output']}.h5\"\nmatch_path = match_features.main(matcher_conf, pairs, feature_conf[\"output\"], outputs)\n# Usually: outputs \u002F \"feats-superpoint-n4096-r1024_matches-superglue_pairs-netvlad.h5\"\n```\n\n### Match with dense LoFTR\n\n```python\nfrom pathlib import Path\nfrom hloc import match_dense\n\nimages = Path(\"images\")\noutputs = Path(\"outputs\")\npairs = outputs \u002F \"pairs-netvlad.txt\"\ndense_conf = match_dense.confs[\"loftr_aachen\"]\nfeatures_path, matches_path = match_dense.main(dense_conf, pairs, images, export_dir=outputs)\n```\n\nDo not assume a feature or match path from memory: compute it from the selected config and pair-file stem, or pass explicit paths via the Python API.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fhierarchical-localization\u002Fsub-skills\u002Ffeature-retrieval",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill feature-retrieval",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill feature-retrieval",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill feature-retrieval","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhierarchical-localization\u002Fsub-skills\u002Ffeature-retrieval\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-and-cli.md","REFERENCE","参考文档",17000,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhierarchical-localization\u002Fsub-skills\u002Ffeature-retrieval\u002Freferences\u002Fapi-and-cli.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fhdf5-feature-match-formats.md",9041,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhierarchical-localization\u002Fsub-skills\u002Ffeature-retrieval\u002Freferences\u002Fhdf5-feature-match-formats.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",10707,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhierarchical-localization\u002Fsub-skills\u002Ffeature-retrieval\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Finspect_hloc_configs.py","SCRIPT","脚本",7175,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhierarchical-localization\u002Fsub-skills\u002Ffeature-retrieval\u002Fscripts\u002Finspect_hloc_configs.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]