[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794WR9ZKGC983MTD7SW11GX":3,"skill-same:01M794WR9ZKGC983MTD7SW11GX":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},"01M794WR9ZKGC983MTD7SW11GX","model-construction",null,"Construct Keras segmentation models with Segmentation Models architectures, backbones, preprocessing, and input validation.","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\u002Fsegmentation-models\u002Fsub-skills\u002Fmodel-construction\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-construction\ndescription: \"Construct Keras segmentation models with Segmentation Models\n  architectures, backbones, preprocessing, and input validation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Model Construction\n\nUse this sub-skill when a task asks how to instantiate or diagnose Segmentation Models Keras models: choosing an architecture, selecting a backbone, configuring `input_shape`, `classes`, `activation`, `encoder_weights`, `encoder_freeze`, preprocessing, and constructor-specific validation.\n\nDo not use this sub-skill for loss\u002Fmetric math or full training loops. Route losses and metrics to `losses-metrics`; route optimizer\u002Ffit utilities, `set_trainable`, and `set_regularization` to `training-utilities`.\n\n## Operating checklist\n\n1. **Select the framework before import.** In modern TensorFlow environments prefer TensorFlow Keras:\n\n   ```python\n   import os\n   os.environ[\"SM_FRAMEWORK\"] = \"tf.keras\"  # or \"keras\"\n   import segmentation_models as sm\n   ```\n\n   `sm.set_framework(\"tf.keras\")` and `sm.set_framework(\"keras\")` exist, but objects should be created only after the intended framework has been selected.\n\n2. **Choose task outputs.** For binary segmentation use `classes=1, activation=\"sigmoid\"`. For mutually exclusive multiclass segmentation use a channel per class (often classes plus background) with `activation=\"softmax\"`. For independent multi-label masks use multiple channels with `activation=\"sigmoid\"`.\n\n3. **Choose architecture\u002Fbackbone.** See `references\u002Fbackbones-and-architectures.md` for the supported names and selection guidance.\n\n4. **Configure preprocessing by backbone.** Use `preprocess_input = sm.get_preprocessing(backbone_name)` and apply it to image tensors produced for the same backbone.\n\n5. **Choose input shape safely.** `Unet`, `Linknet`, and `FPN` can use dynamic spatial dimensions such as `(None, None, 3)`, but actual image height\u002Fwidth should normally be divisible by 32. `PSPNet` requires concrete height\u002Fwidth divisible by `6 * downsample_factor`.\n\n6. **Avoid accidental network downloads.** `encoder_weights=\"imagenet\"` may download pretrained encoder weights and expects RGB-compatible input. For smoke tests, offline builds, grayscale, multispectral, or arbitrary channel counts, use `encoder_weights=None` or map non-RGB inputs to 3 channels before the model.\n\n7. **Smoke-check unusual configs.** Use `scripts\u002Fmodel_constructor_smoke.py` for a safe constructor check; it defaults to `encoder_weights=None` and does not run prediction unless `--predict` is passed.\n\n## Key references\n\n- `references\u002Fapi-reference.md` — constructor signatures, defaults, framework and preprocessing examples.\n- `references\u002Fbackbones-and-architectures.md` — architecture\u002Fbackbone trade-offs and supported names.\n- `references\u002Ftroubleshooting.md` — common constructor\u002Fimport\u002Fshape failures and recoveries.\n- `scripts\u002Fmodel_constructor_smoke.py` — CLI smoke script for offline model-construction checks.\n","# Model Construction\n\nUse this sub-skill when a task asks how to instantiate or diagnose Segmentation Models Keras models: choosing an architecture, selecting a backbone, configuring `input_shape`, `classes`, `activation`, `encoder_weights`, `encoder_freeze`, preprocessing, and constructor-specific validation.\n\nDo not use this sub-skill for loss\u002Fmetric math or full training loops. Route losses and metrics to `losses-metrics`; route optimizer\u002Ffit utilities, `set_trainable`, and `set_regularization` to `training-utilities`.\n\n## Operating checklist\n\n1. **Select the framework before import.** In modern TensorFlow environments prefer TensorFlow Keras:\n\n   ```python\n   import os\n   os.environ[\"SM_FRAMEWORK\"] = \"tf.keras\"  # or \"keras\"\n   import segmentation_models as sm\n   ```\n\n   `sm.set_framework(\"tf.keras\")` and `sm.set_framework(\"keras\")` exist, but objects should be created only after the intended framework has been selected.\n\n2. **Choose task outputs.** For binary segmentation use `classes=1, activation=\"sigmoid\"`. For mutually exclusive multiclass segmentation use a channel per class (often classes plus background) with `activation=\"softmax\"`. For independent multi-label masks use multiple channels with `activation=\"sigmoid\"`.\n\n3. **Choose architecture\u002Fbackbone.** See `references\u002Fbackbones-and-architectures.md` for the supported names and selection guidance.\n\n4. **Configure preprocessing by backbone.** Use `preprocess_input = sm.get_preprocessing(backbone_name)` and apply it to image tensors produced for the same backbone.\n\n5. **Choose input shape safely.** `Unet`, `Linknet`, and `FPN` can use dynamic spatial dimensions such as `(None, None, 3)`, but actual image height\u002Fwidth should normally be divisible by 32. `PSPNet` requires concrete height\u002Fwidth divisible by `6 * downsample_factor`.\n\n6. **Avoid accidental network downloads.** `encoder_weights=\"imagenet\"` may download pretrained encoder weights and expects RGB-compatible input. For smoke tests, offline builds, grayscale, multispectral, or arbitrary channel counts, use `encoder_weights=None` or map non-RGB inputs to 3 channels before the model.\n\n7. **Smoke-check unusual configs.** Use `scripts\u002Fmodel_constructor_smoke.py` for a safe constructor check; it defaults to `encoder_weights=None` and does not run prediction unless `--predict` is passed.\n\n## Key references\n\n- `references\u002Fapi-reference.md` — constructor signatures, defaults, framework and preprocessing examples.\n- `references\u002Fbackbones-and-architectures.md` — architecture\u002Fbackbone trade-offs and supported names.\n- `references\u002Ftroubleshooting.md` — common constructor\u002Fimport\u002Fshape failures and recoveries.\n- `scripts\u002Fmodel_constructor_smoke.py` — CLI smoke script for offline model-construction checks.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fsegmentation-models\u002Fsub-skills\u002Fmodel-construction",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 model-construction",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill model-construction",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill model-construction","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegmentation-models\u002Fsub-skills\u002Fmodel-construction\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",7960,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegmentation-models\u002Fsub-skills\u002Fmodel-construction\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fbackbones-and-architectures.md",6317,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegmentation-models\u002Fsub-skills\u002Fmodel-construction\u002Freferences\u002Fbackbones-and-architectures.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",7324,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegmentation-models\u002Fsub-skills\u002Fmodel-construction\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fmodel_constructor_smoke.py","SCRIPT","脚本",7818,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegmentation-models\u002Fsub-skills\u002Fmodel-construction\u002Fscripts\u002Fmodel_constructor_smoke.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",[],[]]