[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M793WSTKNZPYMSAD9G5VAQN7":3,"skill-same:01M793WSTKNZPYMSAD9G5VAQN7":79},{"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},"01M793WSTKNZPYMSAD9G5VAQN7","quark0-darts",null,"Use the original DARTS research code for differentiable architecture search, CNN\u002FRNN genotypes, CIFAR\u002FImageNet\u002FPTB\u002FWT2 workflows, and legacy PyTorch troubleshooting.","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\u002Fquark0-darts\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: quark0-darts\ndescription: \"Use the original DARTS research code for differentiable\n  architecture search, CNN\u002FRNN genotypes, CIFAR\u002FImageNet\u002FPTB\u002FWT2 workflows, and\n  legacy PyTorch troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# DARTS\n\nUse this repo skill when a task is about the original **DARTS: Differentiable Architecture Search** codebase: convolutional architecture search\u002Fevaluation, recurrent language-modeling search\u002Fevaluation, genotype schemas, visualization, dataset\u002Fcheckpoint layout, or legacy PyTorch\u002FCUDA failures.\n\nThis is a source-backed operating skill for a script-style research repository. It does not assume the original checkout is available, does not install a package, and does not claim that paper-scale native runs were executed during skill production.\n\n## Start here\n\n1. Read [legacy runtime](references\u002Flegacy-runtime.md) before promising native execution. The original code targets Python 3.5-era PyTorch 0.3.1\u002Ftorchvision 0.2.0 and CUDA.\n2. Read [data and checkpoints](references\u002Fdata-and-checkpoints.md) when a workflow needs CIFAR-10, ImageNet, PTB, WikiText-2, or pretrained model files.\n3. Read [troubleshooting](references\u002Ftroubleshooting.md) for cross-cutting failures such as `async=True` syntax errors, missing CUDA, dataset assertions, checkpoint-format mismatches, and Graphviz issues.\n4. Check [repo provenance](references\u002Frepo-provenance.md) before treating this skill as current for a different DARTS checkout.\n\n## Route by task\n\n| User task | Read |\n| --- | --- |\n| CIFAR-10 DARTS architecture search, CIFAR-10 training\u002Ftest, ImageNet training\u002Ftest, CNN model\u002Fcell\u002Foperation facts, or CNN CUDA\u002FOOM\u002Fnondeterminism failures | [cnn-architectures](sub-skills\u002Fcnn-architectures\u002FSKILL.md) |\n| Penn Treebank or WikiText-2 recurrent DARTS search\u002Ftraining\u002Ftest, corpus layout, checkpoint behavior, ASGD schedule, perplexity interpretation, or RNN CUDA\u002Fhidden-size\u002Fdata failures | [rnn-language-modeling](sub-skills\u002Frnn-language-modeling\u002FSKILL.md) |\n| CNN\u002FRNN genotype schemas, built-in DARTS\u002FNASNet\u002FAmoebaNet\u002FENAS genotypes, converting search outputs, validating custom genotypes, or DOT visualization | [genotypes-and-visualization](sub-skills\u002Fgenotypes-and-visualization\u002FSKILL.md) |\n| Construct a native command without launching a job | [darts_command_builder.py](scripts\u002Fdarts_command_builder.py) |\n| Inspect a local DARTS-style source tree before running or porting it | [darts_static_inspector.py](scripts\u002Fdarts_static_inspector.py) |\n\n## Safe helper scripts\n\n- Run `python scripts\u002Fdarts_command_builder.py list` to see workflow ids.\n- Run `python scripts\u002Fdarts_command_builder.py build cnn-search --smoke --gpu 0` to print a wiring-check command and prerequisites. The helper does **not** run training or download data.\n- Run `python scripts\u002Fdarts_static_inspector.py --repo-root \u003Cpath>` to statically check an external DARTS source tree. The helper does **not** import the repo.\n- Run `python sub-skills\u002Fgenotypes-and-visualization\u002Fscripts\u002Fdarts_genotype_tools.py list` to inspect bundled genotype catalogs and emit DOT without Graphviz.\n\n## Operating rules\n\n- Distinguish **architecture search** from **final evaluation**. Search validation accuracy\u002Fperplexity is not the paper result.\n- Treat full native workflows as legacy CUDA jobs. If the user is on modern Python\u002FPyTorch, route to porting guidance instead of implying direct compatibility.\n- Never report smoke-mode output as paper accuracy or perplexity.\n- Keep CNN and RNN genotype schemas separate; both define `DARTS`, but the tuple fields and valid edges differ.\n- Do not tell future agents to open original repo scripts or README pages for routine operation. Use the bundled references and scripts in this skill.\n- If a requested dataset, pretrained checkpoint, CUDA runtime, or legacy PyTorch build is missing, report the missing prerequisite clearly and stop before inventing a result.\n","# DARTS\n\nUse this repo skill when a task is about the original **DARTS: Differentiable Architecture Search** codebase: convolutional architecture search\u002Fevaluation, recurrent language-modeling search\u002Fevaluation, genotype schemas, visualization, dataset\u002Fcheckpoint layout, or legacy PyTorch\u002FCUDA failures.\n\nThis is a source-backed operating skill for a script-style research repository. It does not assume the original checkout is available, does not install a package, and does not claim that paper-scale native runs were executed during skill production.\n\n## Start here\n\n1. Read [legacy runtime](references\u002Flegacy-runtime.md) before promising native execution. The original code targets Python 3.5-era PyTorch 0.3.1\u002Ftorchvision 0.2.0 and CUDA.\n2. Read [data and checkpoints](references\u002Fdata-and-checkpoints.md) when a workflow needs CIFAR-10, ImageNet, PTB, WikiText-2, or pretrained model files.\n3. Read [troubleshooting](references\u002Ftroubleshooting.md) for cross-cutting failures such as `async=True` syntax errors, missing CUDA, dataset assertions, checkpoint-format mismatches, and Graphviz issues.\n4. Check [repo provenance](references\u002Frepo-provenance.md) before treating this skill as current for a different DARTS checkout.\n\n## Route by task\n\n| User task | Read |\n| --- | --- |\n| CIFAR-10 DARTS architecture search, CIFAR-10 training\u002Ftest, ImageNet training\u002Ftest, CNN model\u002Fcell\u002Foperation facts, or CNN CUDA\u002FOOM\u002Fnondeterminism failures | [cnn-architectures](sub-skills\u002Fcnn-architectures\u002FSKILL.md) |\n| Penn Treebank or WikiText-2 recurrent DARTS search\u002Ftraining\u002Ftest, corpus layout, checkpoint behavior, ASGD schedule, perplexity interpretation, or RNN CUDA\u002Fhidden-size\u002Fdata failures | [rnn-language-modeling](sub-skills\u002Frnn-language-modeling\u002FSKILL.md) |\n| CNN\u002FRNN genotype schemas, built-in DARTS\u002FNASNet\u002FAmoebaNet\u002FENAS genotypes, converting search outputs, validating custom genotypes, or DOT visualization | [genotypes-and-visualization](sub-skills\u002Fgenotypes-and-visualization\u002FSKILL.md) |\n| Construct a native command without launching a job | [darts_command_builder.py](scripts\u002Fdarts_command_builder.py) |\n| Inspect a local DARTS-style source tree before running or porting it | [darts_static_inspector.py](scripts\u002Fdarts_static_inspector.py) |\n\n## Safe helper scripts\n\n- Run `python scripts\u002Fdarts_command_builder.py list` to see workflow ids.\n- Run `python scripts\u002Fdarts_command_builder.py build cnn-search --smoke --gpu 0` to print a wiring-check command and prerequisites. The helper does **not** run training or download data.\n- Run `python scripts\u002Fdarts_static_inspector.py --repo-root \u003Cpath>` to statically check an external DARTS source tree. The helper does **not** import the repo.\n- Run `python sub-skills\u002Fgenotypes-and-visualization\u002Fscripts\u002Fdarts_genotype_tools.py list` to inspect bundled genotype catalogs and emit DOT without Graphviz.\n\n## Operating rules\n\n- Distinguish **architecture search** from **final evaluation**. Search validation accuracy\u002Fperplexity is not the paper result.\n- Treat full native workflows as legacy CUDA jobs. If the user is on modern Python\u002FPyTorch, route to porting guidance instead of implying direct compatibility.\n- Never report smoke-mode output as paper accuracy or perplexity.\n- Keep CNN and RNN genotype schemas separate; both define `DARTS`, but the tuple fields and valid edges differ.\n- Do not tell future agents to open original repo scripts or README pages for routine operation. Use the bundled references and scripts in this skill.\n- If a requested dataset, pretrained checkpoint, CUDA runtime, or legacy PyTorch build is missing, report the missing prerequisite clearly and stop before inventing a result.\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\u002Fquark0-darts",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 quark0-darts",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill quark0-darts",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill quark0-darts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fquark0-darts\u002FSKILL.md",[47,53,57,61,65,69,75],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdata-and-checkpoints.md","REFERENCE","参考文档",4064,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fquark0-darts\u002Freferences\u002Fdata-and-checkpoints.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Flegacy-runtime.md",3138,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fquark0-darts\u002Freferences\u002Flegacy-runtime.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-provenance.md",1842,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fquark0-darts\u002Freferences\u002Frepo-provenance.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-routing-metadata.json",473,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fquark0-darts\u002Freferences\u002Frepo-routing-metadata.json",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",3506,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fquark0-darts\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fdarts_command_builder.py","SCRIPT","脚本",12093,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fquark0-darts\u002Fscripts\u002Fdarts_command_builder.py",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fdarts_static_inspector.py",6061,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fquark0-darts\u002Fscripts\u002Fdarts_static_inspector.py",[80,87,94,101,108,115],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"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":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"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",[],[]]