[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M790TYD7E2SWNVJCWTGC8VHE":3,"skill-same:01M790TYD7E2SWNVJCWTGC8VHE":85},{"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},"01M790TYD7E2SWNVJCWTGC8VHE","bundle-config",null,"Work with MONAI Bundle configuration syntax, metadata\u002Fspec files, ConfigParser, ConfigWorkflow, Bundle CLI commands, verification, export, and package-style bundle workflows.","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\u002Fmonai\u002Fsub-skills\u002Fbundle-config\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bundle-config\ndescription: \"Work with MONAI Bundle configuration syntax, metadata\u002Fspec files,\n  ConfigParser, ConfigWorkflow, Bundle CLI commands, verification, export, and\n  package-style bundle workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# MONAI Bundle Config\n\nUse this sub-skill when the task involves `monai.bundle`, `python -m monai.bundle`, Bundle JSON\u002FYAML config syntax, metadata\u002Fspec files, `ConfigParser`, `BundleWorkflow`, `ConfigWorkflow`, CLI overrides, verification, export, or reproducible package-style bundle workflows.\n\nDo not use this sub-skill for Auto3DSeg orchestration that generates bundles; route those tasks to `apps-auto3dseg`. For Bundle component internals, route model definitions to the model sub-skill, transforms and datasets to the data\u002Ftransforms sub-skills, and training loop objects to the training sub-skill.\n\n## Fast Routing\n\n- Read `references\u002Fconfig-syntax.md` when authoring, merging, overriding, or debugging Bundle JSON\u002FYAML with `_target_`, `@`, `%`, `$`, nested ids, and `ConfigParser`.\n- Read `references\u002Fcli-reference.md` when invoking `python -m monai.bundle`, selecting commands, preparing CLI overrides, validating metadata\u002Fnetwork I\u002FO, exporting checkpoints, downloading large files, or pushing bundles.\n- Read `references\u002Ftroubleshooting.md` when Bundle parsing, CLI startup, verification, export, path, optional dependency, or network\u002Fdownload behavior fails.\n- Run `scripts\u002Fmonai_bundle_smoke.py --help` when checking what the bundled smoke script can do without touching external data or repository source files.\n- Run `scripts\u002Fmonai_bundle_smoke.py parse-inline` when confirming the installed MONAI Bundle parser can instantiate a tiny object graph and apply an override.\n- Run `scripts\u002Fmonai_bundle_smoke.py build-tiny-bundle --output \u003Cdir>` when a temporary self-contained Bundle directory is useful for experimentation.\n- Use `templates\u002Ftiny-bundle\u002F` as a copyable minimal Bundle skeleton when a user asks for example bundle files rather than a generated temporary directory.\n\n## Common Workflows\n\n1. For config authoring, start with `references\u002Fconfig-syntax.md`, keep top-level ids meaningful, use `_target_` for instantiable Python objects, and prefer simple `@` references over complex `$` expressions.\n2. For Bundle CLI work, ensure Python Fire is installed, run command help as `python -m monai.bundle \u003Ccommand> -- --help`, and quote shell-sensitive ids such as `network_def#spatial_dims`.\n3. For verification, use `verify_metadata` for schema-backed metadata and `verify_net_in_out` only when the config network can run safely on the requested device with fake tensor input.\n4. For export, require an existing checkpoint, config file, and compatible optional export dependencies before using `ckpt_export`, `onnx_export`, or `trt_export`.\n5. For reproducible workflows, prefer `run_workflow`\u002F`create_workflow` with explicit `config_file`, `meta_file`, `workflow_type`, and overrides instead of relying on current working directory defaults.\n\n## Safety Defaults\n\n- Treat download, Hub push, and large-file commands as network\u002Fcredential operations; ask before running them unless the user explicitly requested network publishing or downloads.\n- Do not claim optional IO\u002Fexport\u002Ftracking\u002FHPO dependencies are installed unless the current environment proves it.\n- Avoid absolute local paths in reusable instructions; use placeholders such as `\u003Cbundle_dir>`, `\u003Cconfig_file>`, and `\u003Ccheckpoint.pt>`.\n- Keep generated Bundle examples small, CPU-safe, and based on installed `monai`, `torch`, and `numpy` APIs.\n","# MONAI Bundle Config\n\nUse this sub-skill when the task involves `monai.bundle`, `python -m monai.bundle`, Bundle JSON\u002FYAML config syntax, metadata\u002Fspec files, `ConfigParser`, `BundleWorkflow`, `ConfigWorkflow`, CLI overrides, verification, export, or reproducible package-style bundle workflows.\n\nDo not use this sub-skill for Auto3DSeg orchestration that generates bundles; route those tasks to `apps-auto3dseg`. For Bundle component internals, route model definitions to the model sub-skill, transforms and datasets to the data\u002Ftransforms sub-skills, and training loop objects to the training sub-skill.\n\n## Fast Routing\n\n- Read `references\u002Fconfig-syntax.md` when authoring, merging, overriding, or debugging Bundle JSON\u002FYAML with `_target_`, `@`, `%`, `$`, nested ids, and `ConfigParser`.\n- Read `references\u002Fcli-reference.md` when invoking `python -m monai.bundle`, selecting commands, preparing CLI overrides, validating metadata\u002Fnetwork I\u002FO, exporting checkpoints, downloading large files, or pushing bundles.\n- Read `references\u002Ftroubleshooting.md` when Bundle parsing, CLI startup, verification, export, path, optional dependency, or network\u002Fdownload behavior fails.\n- Run `scripts\u002Fmonai_bundle_smoke.py --help` when checking what the bundled smoke script can do without touching external data or repository source files.\n- Run `scripts\u002Fmonai_bundle_smoke.py parse-inline` when confirming the installed MONAI Bundle parser can instantiate a tiny object graph and apply an override.\n- Run `scripts\u002Fmonai_bundle_smoke.py build-tiny-bundle --output \u003Cdir>` when a temporary self-contained Bundle directory is useful for experimentation.\n- Use `templates\u002Ftiny-bundle\u002F` as a copyable minimal Bundle skeleton when a user asks for example bundle files rather than a generated temporary directory.\n\n## Common Workflows\n\n1. For config authoring, start with `references\u002Fconfig-syntax.md`, keep top-level ids meaningful, use `_target_` for instantiable Python objects, and prefer simple `@` references over complex `$` expressions.\n2. For Bundle CLI work, ensure Python Fire is installed, run command help as `python -m monai.bundle \u003Ccommand> -- --help`, and quote shell-sensitive ids such as `network_def#spatial_dims`.\n3. For verification, use `verify_metadata` for schema-backed metadata and `verify_net_in_out` only when the config network can run safely on the requested device with fake tensor input.\n4. For export, require an existing checkpoint, config file, and compatible optional export dependencies before using `ckpt_export`, `onnx_export`, or `trt_export`.\n5. For reproducible workflows, prefer `run_workflow`\u002F`create_workflow` with explicit `config_file`, `meta_file`, `workflow_type`, and overrides instead of relying on current working directory defaults.\n\n## Safety Defaults\n\n- Treat download, Hub push, and large-file commands as network\u002Fcredential operations; ask before running them unless the user explicitly requested network publishing or downloads.\n- Do not claim optional IO\u002Fexport\u002Ftracking\u002FHPO dependencies are installed unless the current environment proves it.\n- Avoid absolute local paths in reusable instructions; use placeholders such as `\u003Cbundle_dir>`, `\u003Cconfig_file>`, and `\u003Ccheckpoint.pt>`.\n- Keep generated Bundle examples small, CPU-safe, and based on installed `monai`, `torch`, and `numpy` APIs.\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\u002Fmonai\u002Fsub-skills\u002Fbundle-config",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 bundle-config",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill bundle-config",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill bundle-config","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmonai\u002Fsub-skills\u002Fbundle-config\u002FSKILL.md",[47,53,57,61,67,71,75,79],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcli-reference.md","REFERENCE","参考文档",10231,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmonai\u002Fsub-skills\u002Fbundle-config\u002Freferences\u002Fcli-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fconfig-syntax.md",9056,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmonai\u002Fsub-skills\u002Fbundle-config\u002Freferences\u002Fconfig-syntax.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",9266,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmonai\u002Fsub-skills\u002Fbundle-config\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fmonai_bundle_smoke.py","SCRIPT","脚本",7013,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmonai\u002Fsub-skills\u002Fbundle-config\u002Fscripts\u002Fmonai_bundle_smoke.py",{"path":68,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":69,"sourceHtmlUrl":70},"templates\u002Ftiny-bundle\u002Fconfigs\u002Finference.json",259,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmonai\u002Fsub-skills\u002Fbundle-config\u002Ftemplates\u002Ftiny-bundle\u002Fconfigs\u002Finference.json",{"path":72,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":73,"sourceHtmlUrl":74},"templates\u002Ftiny-bundle\u002Fconfigs\u002Fmetadata.json",1191,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmonai\u002Fsub-skills\u002Fbundle-config\u002Ftemplates\u002Ftiny-bundle\u002Fconfigs\u002Fmetadata.json",{"path":76,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":77,"sourceHtmlUrl":78},"templates\u002Ftiny-bundle\u002Fdocs\u002FREADME.md",339,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmonai\u002Fsub-skills\u002Fbundle-config\u002Ftemplates\u002Ftiny-bundle\u002Fdocs\u002FREADME.md",{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"templates\u002Ftiny-bundle\u002FLICENSE","LICENSE","许可证",34,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmonai\u002Fsub-skills\u002Fbundle-config\u002Ftemplates\u002Ftiny-bundle\u002FLICENSE",[86,93,100,107,114,121],{"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},"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":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},"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":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},"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":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},"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":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"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":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"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",[],[]]