[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797XTQ7APZ8Q1MP7Z6D8KCN":3,"skill-same:01M797XTQ7APZ8Q1MP7Z6D8KCN":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},"01M797XTQ7APZ8Q1MP7Z6D8KCN","nami_graph_inversion",null,"Generate natural minimally faithful inverse graph structures from Bayesian-network DAGs using the paper's NaMI variable-elimination procedure.","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\u002Fall-in-one\u002Fskill\u002Ffaithful_inversion_graphical_models\u002Fnami_graph_inversion\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nami_graph_inversion\ndescription: Generate natural minimally faithful inverse graph structures from Bayesian-network DAGs using the paper's NaMI variable-elimination procedure.\n---\n\n# NaMI Graph Inversion\n\nUse this skill when a task needs the structural inversion method from \"Faithful Inversion of Generative Models for Effective Amortized Inference\": converting a generative Bayesian-network DAG into inverse parent sets for an amortized inference network. Do not use it for numeric posterior inference by itself; it produces graph structure and an elimination trace, not trained neural parameters.\n\n## Inputs\n\n- A JSON object or Python mapping `parents` from node id to a list of directed parents in the generative BN.\n- A list of `latents` that the inverse network must sample.\n- A list of `observed` variables that condition the inverse network.\n- `mode`, either `topological` for forward-NaMI or `reverse_topological` for reverse-NaMI.\n\n## Outputs\n\n- `inverse_parents`: mapping from latent variable to parent variables in the inverse graph.\n- `elimination_order`: latent variables in the order simulated by variable elimination.\n- `trace`: per-step frontier, fill edges, unmarked neighbors, and selected variable.\n- `edge_count`: number of inverse parent edges.\n\n## Workflow\n\n1. Validate that the generative graph is acyclic and that all latent\u002Fobserved variables exist.\n2. Moralize the graph by dropping directions and connecting all co-parents.\n3. Initialize the frontier with latent variables that have no upstream latent variables for the selected mode.\n4. Repeatedly choose the frontier variable with the smallest min-fill score, using lexical order for ties.\n5. Add fill edges among unmarked neighbors, assign those neighbors as inverse parents, mark the variable, and update the frontier.\n6. Return the inverse structure and trace. Run both modes when compactness matters.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fnami.py --example binary_tree --mode topological\npython tests\u002Ftest_nami.py\n```\n\nThe test file uses only the Python standard library and can also be run by the Distiller skill-tree validator.\n\n## Limitations\n\nThis skill intentionally implements the graph algorithm only. It does not train inference networks, compute analytic Gaussian posteriors, or prove global optimality among all possible minimal I-maps.\n","# NaMI Graph Inversion\n\nUse this skill when a task needs the structural inversion method from \"Faithful Inversion of Generative Models for Effective Amortized Inference\": converting a generative Bayesian-network DAG into inverse parent sets for an amortized inference network. Do not use it for numeric posterior inference by itself; it produces graph structure and an elimination trace, not trained neural parameters.\n\n## Inputs\n\n- A JSON object or Python mapping `parents` from node id to a list of directed parents in the generative BN.\n- A list of `latents` that the inverse network must sample.\n- A list of `observed` variables that condition the inverse network.\n- `mode`, either `topological` for forward-NaMI or `reverse_topological` for reverse-NaMI.\n\n## Outputs\n\n- `inverse_parents`: mapping from latent variable to parent variables in the inverse graph.\n- `elimination_order`: latent variables in the order simulated by variable elimination.\n- `trace`: per-step frontier, fill edges, unmarked neighbors, and selected variable.\n- `edge_count`: number of inverse parent edges.\n\n## Workflow\n\n1. Validate that the generative graph is acyclic and that all latent\u002Fobserved variables exist.\n2. Moralize the graph by dropping directions and connecting all co-parents.\n3. Initialize the frontier with latent variables that have no upstream latent variables for the selected mode.\n4. Repeatedly choose the frontier variable with the smallest min-fill score, using lexical order for ties.\n5. Add fill edges among unmarked neighbors, assign those neighbors as inverse parents, mark the variable, and update the frontier.\n6. Return the inverse structure and trace. Run both modes when compactness matters.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fnami.py --example binary_tree --mode topological\npython tests\u002Ftest_nami.py\n```\n\nThe test file uses only the Python standard library and can also be run by the Distiller skill-tree validator.\n\n## Limitations\n\nThis skill intentionally implements the graph algorithm only. It does not train inference networks, compute analytic Gaussian posteriors, or prove global optimality among all possible minimal I-maps.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fall-in-one\u002Fskill\u002Ffaithful_inversion_graphical_models\u002Fnami_graph_inversion",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 nami_graph_inversion",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill nami_graph_inversion",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill nami_graph_inversion","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fall-in-one\u002Fskill\u002Ffaithful_inversion_graphical_models\u002Fnami_graph_inversion\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fnami.py","SCRIPT","脚本",7391,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fall-in-one\u002Fskill\u002Ffaithful_inversion_graphical_models\u002Fnami_graph_inversion\u002Fscripts\u002Fnami.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_nami.py",1840,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fall-in-one\u002Fskill\u002Ffaithful_inversion_graphical_models\u002Fnami_graph_inversion\u002Ftests\u002Ftest_nami.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",[],[]]