[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M798QTF1DFRSP25HASZKQZHM":3,"skill-same:01M798QTF1DFRSP25HASZKQZHM":54},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M798QTF1DFRSP25HASZKQZHM","nystrom_preconditioner",null,"Build and apply the inverse action of the Nyström preconditioner for regularized PSD linear systems.","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\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fpinn\u002Fskill\u002Frandomized_nystrom_preconditioning\u002Fnystrom_preconditioner\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nystrom_preconditioner\ndescription: Build and apply the inverse action of the Nyström preconditioner for regularized PSD linear systems.\n---\n\n# Nyström Preconditioner\n\nUse this skill after obtaining `U, lambda_hat` from a randomized Nyström factorization. It provides the inverse preconditioner action used by Nyström PCG and dense diagnostics for small recovery experiments.\n\n## Inputs\n\n- `U`: orthonormal Nyström basis.\n- `lambda_hat`: nonnegative approximate eigenvalues.\n- `mu > 0`: regularization parameter.\n- Residual vector or right-hand-side matrix.\n\n## Outputs\n\n- `apply_inverse_preconditioner(U, lambda_hat, mu, r)` result.\n- Preconditioner metadata, including rank and baseline scale.\n- Optional condition-number comparison for `A + mu I` versus the symmetrically preconditioned matrix.\n\n## Workflow\n\n1. Validate dimensions, `mu`, and approximate orthonormality.\n2. Sort eigenpairs by decreasing `lambda_hat` if necessary.\n3. Set `sigma = lambda_hat[-1] + mu`.\n4. Apply `P^{-1}` by scaling captured components with `sigma \u002F (lambda_hat_i + mu)` and leaving orthogonal components unchanged.\n5. For dense recovery checks, construct the SPD square-root action and estimate condition numbers.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fpreconditioner.py --self-test\npython tests\u002Ftest_preconditioner.py\n```\n\nThe tests verify inverse-action shape, dimension checks, and condition-number reduction on a diagonal PSD example.\n\n## Limitations\n\nDense condition-number diagnostics are intended for small experiments. Large systems should only use the vector action.\n","# Nyström Preconditioner\n\nUse this skill after obtaining `U, lambda_hat` from a randomized Nyström factorization. It provides the inverse preconditioner action used by Nyström PCG and dense diagnostics for small recovery experiments.\n\n## Inputs\n\n- `U`: orthonormal Nyström basis.\n- `lambda_hat`: nonnegative approximate eigenvalues.\n- `mu > 0`: regularization parameter.\n- Residual vector or right-hand-side matrix.\n\n## Outputs\n\n- `apply_inverse_preconditioner(U, lambda_hat, mu, r)` result.\n- Preconditioner metadata, including rank and baseline scale.\n- Optional condition-number comparison for `A + mu I` versus the symmetrically preconditioned matrix.\n\n## Workflow\n\n1. Validate dimensions, `mu`, and approximate orthonormality.\n2. Sort eigenpairs by decreasing `lambda_hat` if necessary.\n3. Set `sigma = lambda_hat[-1] + mu`.\n4. Apply `P^{-1}` by scaling captured components with `sigma \u002F (lambda_hat_i + mu)` and leaving orthogonal components unchanged.\n5. For dense recovery checks, construct the SPD square-root action and estimate condition numbers.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fpreconditioner.py --self-test\npython tests\u002Ftest_preconditioner.py\n```\n\nThe tests verify inverse-action shape, dimension checks, and condition-number reduction on a diagonal PSD example.\n\n## Limitations\n\nDense condition-number diagnostics are intended for small experiments. Large systems should only use the vector action.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fpinn\u002Fskill\u002Frandomized_nystrom_preconditioning\u002Fnystrom_preconditioner",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill nystrom_preconditioner",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill nystrom_preconditioner",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill nystrom_preconditioner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fpinn\u002Fskill\u002Frandomized_nystrom_preconditioning\u002Fnystrom_preconditioner\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fpreconditioner.py","SCRIPT","脚本",3044,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fpinn\u002Fskill\u002Frandomized_nystrom_preconditioning\u002Fnystrom_preconditioner\u002Fscripts\u002Fpreconditioner.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_preconditioner.py",784,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fpinn\u002Fskill\u002Frandomized_nystrom_preconditioning\u002Fnystrom_preconditioner\u002Ftests\u002Ftest_preconditioner.py",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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",[],[]]