[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M790NNET45FW8APNNWF5VJVR":3,"skill-same:01M790NNET45FW8APNNWF5VJVR":71},{"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},"01M790NNET45FW8APNNWF5VJVR","model-customization",null,"Customize MMSegmentation models, registries, projects, checkpoints, and model-complexity checks.","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\u002Fmmsegmentation\u002Fsub-skills\u002Fmodel-customization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-customization\ndescription: \"Customize MMSegmentation models, registries, projects,\n  checkpoints, and model-complexity checks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Model Customization\n\nUse this sub-skill when extending MMSegmentation with custom model components, choosing or adapting model zoo configs, validating registry wiring, converting checkpoints, or explaining model-complexity\u002Fdeployment caveats.\n\n## Scope\n\nThis sub-skill covers:\n\n- MMSegmentation model architecture: segmentors, data preprocessors, backbones, necks, decode heads, auxiliary heads, losses, metrics, optimizers, and schedulers.\n- Registry usage through `mmseg.registry` and legacy builder aliases exposed from `mmseg.models`.\n- Custom components implemented in-tree, in project packages, or in external Python packages imported by config.\n- Model zoo\u002Fconfig selection, optional projects, checkpoint conversion planning, model publishing, and FLOPs\u002Fparameter caveats.\n\nUse sibling skills instead for:\n\n- Dataset layout, transforms, palettes, and evaluators beyond metric registration: `data-configuration`.\n- Launching train\u002Ftest jobs, distributed runners, and result reporting: `training-evaluation`.\n- Runtime inference APIs, visualization, or serving: `inference`.\n\n## Fast Routing\n\n- Need to understand what can be customized or which built-ins exist? Read [model-components](references\u002Fmodel-components.md).\n- Need to add a custom backbone, decode head, loss, metric, optimizer, scheduler, or project package? Read [customization-recipes](references\u002Fcustomization-recipes.md).\n- Need to adapt pretrained weights, publish a checkpoint, or explain why a conversion is unsafe? Read [checkpoint-conversion](references\u002Fcheckpoint-conversion.md).\n- Need to debug `KeyError`, `custom_imports`, `default_scope`, shape mismatch, optional dependency, FLOPs, or MMCV-op failures? Read [troubleshooting](references\u002Ftroubleshooting.md).\n- Need to check whether a type is registered after importing optional modules? Run [inspect_registry.py](scripts\u002Finspect_registry.py).\n\n## Default Workflow\n\n1. Identify the target extension point: `MODELS` for segmentors\u002Fbackbones\u002Fnecks\u002Fheads\u002Flosses\u002Fdata preprocessors, `METRICS` for evaluators, `OPTIMIZERS` or `OPTIM_WRAPPER_CONSTRUCTORS` for optimizer behavior, and `PARAM_SCHEDULERS` for schedulers.\n2. Confirm the component is imported before config build: either import it from the package `__init__.py` path or add `custom_imports = dict(imports=[...], allow_failed_imports=False)` to the config.\n3. Keep `default_scope = 'mmseg'` unless intentionally composing registries from another OpenMMLab package.\n4. Smoke-check registry visibility with `scripts\u002Finspect_registry.py` before debugging model math.\n5. Build or instantiate the smallest safe config first, then run a tiny forward\u002Floss test before launching training.\n6. Treat checkpoint conversion and FLOPs as verification tasks, not guarantees: both depend on exact source checkpoint schemas, target key names, optional dependencies, and supported operators.\n\n## Guardrails\n\n- Prefer `mmseg.registry.MODELS.build(...)` for new guidance; legacy `build_backbone`, `build_head`, `build_loss`, and `build_segmentor` still exist but warn that `MODELS.build()` is preferred.\n- Register custom model classes with `@MODELS.register_module()` and custom metrics with `@METRICS.register_module()`.\n- A config `type='MyType'` only works after Python imports the module that runs the registration decorator.\n- Do not promise that a source checkpoint can be loaded or converted unless key mapping, tensor shapes, class counts, and optional dependency versions are checked.\n- Do not treat FLOPs as paper-ready without verifying unsupported ops, post-processing omissions, input shape, and head support.\n","# Model Customization\n\nUse this sub-skill when extending MMSegmentation with custom model components, choosing or adapting model zoo configs, validating registry wiring, converting checkpoints, or explaining model-complexity\u002Fdeployment caveats.\n\n## Scope\n\nThis sub-skill covers:\n\n- MMSegmentation model architecture: segmentors, data preprocessors, backbones, necks, decode heads, auxiliary heads, losses, metrics, optimizers, and schedulers.\n- Registry usage through `mmseg.registry` and legacy builder aliases exposed from `mmseg.models`.\n- Custom components implemented in-tree, in project packages, or in external Python packages imported by config.\n- Model zoo\u002Fconfig selection, optional projects, checkpoint conversion planning, model publishing, and FLOPs\u002Fparameter caveats.\n\nUse sibling skills instead for:\n\n- Dataset layout, transforms, palettes, and evaluators beyond metric registration: `data-configuration`.\n- Launching train\u002Ftest jobs, distributed runners, and result reporting: `training-evaluation`.\n- Runtime inference APIs, visualization, or serving: `inference`.\n\n## Fast Routing\n\n- Need to understand what can be customized or which built-ins exist? Read [model-components](references\u002Fmodel-components.md).\n- Need to add a custom backbone, decode head, loss, metric, optimizer, scheduler, or project package? Read [customization-recipes](references\u002Fcustomization-recipes.md).\n- Need to adapt pretrained weights, publish a checkpoint, or explain why a conversion is unsafe? Read [checkpoint-conversion](references\u002Fcheckpoint-conversion.md).\n- Need to debug `KeyError`, `custom_imports`, `default_scope`, shape mismatch, optional dependency, FLOPs, or MMCV-op failures? Read [troubleshooting](references\u002Ftroubleshooting.md).\n- Need to check whether a type is registered after importing optional modules? Run [inspect_registry.py](scripts\u002Finspect_registry.py).\n\n## Default Workflow\n\n1. Identify the target extension point: `MODELS` for segmentors\u002Fbackbones\u002Fnecks\u002Fheads\u002Flosses\u002Fdata preprocessors, `METRICS` for evaluators, `OPTIMIZERS` or `OPTIM_WRAPPER_CONSTRUCTORS` for optimizer behavior, and `PARAM_SCHEDULERS` for schedulers.\n2. Confirm the component is imported before config build: either import it from the package `__init__.py` path or add `custom_imports = dict(imports=[...], allow_failed_imports=False)` to the config.\n3. Keep `default_scope = 'mmseg'` unless intentionally composing registries from another OpenMMLab package.\n4. Smoke-check registry visibility with `scripts\u002Finspect_registry.py` before debugging model math.\n5. Build or instantiate the smallest safe config first, then run a tiny forward\u002Floss test before launching training.\n6. Treat checkpoint conversion and FLOPs as verification tasks, not guarantees: both depend on exact source checkpoint schemas, target key names, optional dependencies, and supported operators.\n\n## Guardrails\n\n- Prefer `mmseg.registry.MODELS.build(...)` for new guidance; legacy `build_backbone`, `build_head`, `build_loss`, and `build_segmentor` still exist but warn that `MODELS.build()` is preferred.\n- Register custom model classes with `@MODELS.register_module()` and custom metrics with `@METRICS.register_module()`.\n- A config `type='MyType'` only works after Python imports the module that runs the registration decorator.\n- Do not promise that a source checkpoint can be loaded or converted unless key mapping, tensor shapes, class counts, and optional dependency versions are checked.\n- Do not treat FLOPs as paper-ready without verifying unsupported ops, post-processing omissions, input shape, and head support.\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\u002Fmmsegmentation\u002Fsub-skills\u002Fmodel-customization",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 model-customization",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill model-customization",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill model-customization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmmsegmentation\u002Fsub-skills\u002Fmodel-customization\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcheckpoint-conversion.md","REFERENCE","参考文档",6087,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmmsegmentation\u002Fsub-skills\u002Fmodel-customization\u002Freferences\u002Fcheckpoint-conversion.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcustomization-recipes.md",10161,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmmsegmentation\u002Fsub-skills\u002Fmodel-customization\u002Freferences\u002Fcustomization-recipes.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fmodel-components.md",8127,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmmsegmentation\u002Fsub-skills\u002Fmodel-customization\u002Freferences\u002Fmodel-components.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",7480,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmmsegmentation\u002Fsub-skills\u002Fmodel-customization\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Finspect_registry.py","SCRIPT","脚本",6498,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmmsegmentation\u002Fsub-skills\u002Fmodel-customization\u002Fscripts\u002Finspect_registry.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]