[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792YFP207MTNP5PP0KX6XK0":3,"skill-same:01M792YFP207MTNP5PP0KX6XK0":66},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M792YFP207MTNP5PP0KX6XK0","gromov",null,"Use POT Gromov-Wasserstein and Fused GW solvers for graphs, structured data, heterogeneous spaces, GW barycenters, dictionary learning, quantized approximations, and validation.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpot\u002Fsub-skills\u002Fgromov\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gromov\ndescription: \"Use POT Gromov-Wasserstein and Fused GW solvers for graphs,\n  structured data, heterogeneous spaces, GW barycenters, dictionary learning,\n  quantized approximations, and validation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# POT Gromov-Wasserstein and Fused GW\n\nUse this sub-skill when the task involves comparing or aligning objects whose samples live in different metric spaces or have graph\u002Frelational structure: Gromov-Wasserstein (GW), Fused Gromov-Wasserstein (FGW), structured graph matching, node-feature-aware graph comparison, GW\u002FFGW barycenters, dictionary learning\u002Funmixing, semirelaxed\u002Fpartial\u002Funbalanced variants, quantized approximations, and GW validation.\n\nRead [references\u002Fapi-reference.md](references\u002Fapi-reference.md) when choosing a POT GW API, checking verified signatures\u002Fdefaults, understanding `ot.solve_gromov` versus `ot.gromov.*`, or validating expected plan\u002Flog\u002Fresult fields.\n\nRead [references\u002Fworkflows.md](references\u002Fworkflows.md) when building an end-to-end GW or FGW workflow for graphs, node features, heterogeneous spaces, barycenters, dictionary learning, or approximate\u002Fquantized GW.\n\nRead [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when cost matrices, weights, `loss_fun`\u002F`loss`, `alpha`, marginal constraints, `symmetric`, partial\u002Fsemirelaxed\u002Funbalanced semantics, convergence, quantized helpers, or optional GNN dependencies fail.\n\nRun [scripts\u002Fgromov_smoke.py](scripts\u002Fgromov_smoke.py) after installing POT to exercise deterministic NumPy GW and FGW fixtures with no plotting, downloads, original checkout, or optional graph dependencies.\n\n## Route quickly\n\n- Use **GW** when each object is represented only by an internal structure matrix (`C1`, `C2`), such as pairwise graph distances, adjacency-derived dissimilarities, shape geodesics, or relational similarities.\n- Use **FGW** when structures also have cross-space attributes or node features. Provide a feature cost matrix `M` of shape `(n_source, n_target)` and tune `alpha`: `0` emphasizes features\u002Flinear OT and `1` emphasizes pure GW structure.\n- Use **`ot.solve_gromov`** for a unified `OTResult` with `.plan`, `.value`, `.value_linear`, `.value_quad`, and marginal helpers. Use **`ot.gromov.*`** functions when you need a specific classical, entropic, semirelaxed, partial, quantized, barycenter, dictionary, or estimator API.\n- Use **entropic GW\u002FFGW** when exact conditional-gradient plans are too slow or too sparse and a smoother approximation is acceptable.\n- Use **semirelaxed GW\u002FFGW** when the source marginal is fixed but the target-side mass may be reweighted, for example matching a graph to a prototype or community structure.\n- Use **partial GW\u002FFGW** when only a known amount of mass should match, such as subgraph matching with outliers.\n- Use **fused unbalanced GW** when marginal masses should be penalized rather than enforced. Route general unbalanced\u002Fpartial OT fundamentals to `unbalanced-partial`.\n- Use **quantized, sampled, pointwise, or low-rank GW** when graph\u002Fsample sizes make full GW too expensive; validate the approximation on a reduced problem before trusting ranking or downstream decisions.\n- Use **GW\u002FFGW barycenters** when the output is itself a structure matrix or an attributed graph prototype. Route ordinary Wasserstein barycenters to `barycenters`.\n- Use **dictionary learning\u002Funmixing** when many structured samples should be represented as convex combinations of learned GW\u002FFGW atoms.\n- Treat **POT GNN layers** (`ot.gnn`) as optional reference-only functionality unless the user's environment has PyTorch and PyTorch Geometric installed and verified. Route backend installation and batch-array issues to `backend-and-batch`.\n\n## Stay in scope\n\nThis sub-skill owns structured GW\u002FFGW modeling, solver selection, validation, and workflow-specific recovery. It does not cover ordinary vector-space OT except as the `M` term inside FGW; route those tasks to `core-solvers`. It does not teach general mass-relaxation theory outside GW\u002FFGW; route that to `unbalanced-partial`. It does not install optional backend stacks, PyTorch Geometric, plotting, NetworkX, or scikit-learn; route setup questions to `backend-and-batch` or keep them explicitly optional.\n\n## Minimal operating checklist\n\n1. Build finite floating-point square structure matrices `C1` and `C2`; normalize scales when comparing multiple costs.\n2. If using FGW, build `M` with shape `(C1.shape[0], C2.shape[0])` from comparable node-feature distances.\n3. Set one-dimensional nonnegative weights `p` and `q` whose lengths match the structure matrices, or let POT use uniform weights.\n4. Choose the mass model: balanced GW\u002FFGW, semirelaxed target reweighting, partial transported mass, or unbalanced marginal penalty.\n5. Run the solver with explicit `loss_fun`\u002F`loss`, `alpha`, `reg`, `symmetric`, `max_iter`, and `tol` when reproducibility matters.\n6. Validate the returned plan: finite nonnegative values, expected shape, total mass, row\u002Fcolumn marginal behavior for the selected mass model, and a finite GW\u002FFGW value.\n7. For larger graphs, compare an approximate\u002Fquantized result against a tiny exact subset or the bundled smoke script before scaling up.\n","# POT Gromov-Wasserstein and Fused GW\n\nUse this sub-skill when the task involves comparing or aligning objects whose samples live in different metric spaces or have graph\u002Frelational structure: Gromov-Wasserstein (GW), Fused Gromov-Wasserstein (FGW), structured graph matching, node-feature-aware graph comparison, GW\u002FFGW barycenters, dictionary learning\u002Funmixing, semirelaxed\u002Fpartial\u002Funbalanced variants, quantized approximations, and GW validation.\n\nRead [references\u002Fapi-reference.md](references\u002Fapi-reference.md) when choosing a POT GW API, checking verified signatures\u002Fdefaults, understanding `ot.solve_gromov` versus `ot.gromov.*`, or validating expected plan\u002Flog\u002Fresult fields.\n\nRead [references\u002Fworkflows.md](references\u002Fworkflows.md) when building an end-to-end GW or FGW workflow for graphs, node features, heterogeneous spaces, barycenters, dictionary learning, or approximate\u002Fquantized GW.\n\nRead [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when cost matrices, weights, `loss_fun`\u002F`loss`, `alpha`, marginal constraints, `symmetric`, partial\u002Fsemirelaxed\u002Funbalanced semantics, convergence, quantized helpers, or optional GNN dependencies fail.\n\nRun [scripts\u002Fgromov_smoke.py](scripts\u002Fgromov_smoke.py) after installing POT to exercise deterministic NumPy GW and FGW fixtures with no plotting, downloads, original checkout, or optional graph dependencies.\n\n## Route quickly\n\n- Use **GW** when each object is represented only by an internal structure matrix (`C1`, `C2`), such as pairwise graph distances, adjacency-derived dissimilarities, shape geodesics, or relational similarities.\n- Use **FGW** when structures also have cross-space attributes or node features. Provide a feature cost matrix `M` of shape `(n_source, n_target)` and tune `alpha`: `0` emphasizes features\u002Flinear OT and `1` emphasizes pure GW structure.\n- Use **`ot.solve_gromov`** for a unified `OTResult` with `.plan`, `.value`, `.value_linear`, `.value_quad`, and marginal helpers. Use **`ot.gromov.*`** functions when you need a specific classical, entropic, semirelaxed, partial, quantized, barycenter, dictionary, or estimator API.\n- Use **entropic GW\u002FFGW** when exact conditional-gradient plans are too slow or too sparse and a smoother approximation is acceptable.\n- Use **semirelaxed GW\u002FFGW** when the source marginal is fixed but the target-side mass may be reweighted, for example matching a graph to a prototype or community structure.\n- Use **partial GW\u002FFGW** when only a known amount of mass should match, such as subgraph matching with outliers.\n- Use **fused unbalanced GW** when marginal masses should be penalized rather than enforced. Route general unbalanced\u002Fpartial OT fundamentals to `unbalanced-partial`.\n- Use **quantized, sampled, pointwise, or low-rank GW** when graph\u002Fsample sizes make full GW too expensive; validate the approximation on a reduced problem before trusting ranking or downstream decisions.\n- Use **GW\u002FFGW barycenters** when the output is itself a structure matrix or an attributed graph prototype. Route ordinary Wasserstein barycenters to `barycenters`.\n- Use **dictionary learning\u002Funmixing** when many structured samples should be represented as convex combinations of learned GW\u002FFGW atoms.\n- Treat **POT GNN layers** (`ot.gnn`) as optional reference-only functionality unless the user's environment has PyTorch and PyTorch Geometric installed and verified. Route backend installation and batch-array issues to `backend-and-batch`.\n\n## Stay in scope\n\nThis sub-skill owns structured GW\u002FFGW modeling, solver selection, validation, and workflow-specific recovery. It does not cover ordinary vector-space OT except as the `M` term inside FGW; route those tasks to `core-solvers`. It does not teach general mass-relaxation theory outside GW\u002FFGW; route that to `unbalanced-partial`. It does not install optional backend stacks, PyTorch Geometric, plotting, NetworkX, or scikit-learn; route setup questions to `backend-and-batch` or keep them explicitly optional.\n\n## Minimal operating checklist\n\n1. Build finite floating-point square structure matrices `C1` and `C2`; normalize scales when comparing multiple costs.\n2. If using FGW, build `M` with shape `(C1.shape[0], C2.shape[0])` from comparable node-feature distances.\n3. Set one-dimensional nonnegative weights `p` and `q` whose lengths match the structure matrices, or let POT use uniform weights.\n4. Choose the mass model: balanced GW\u002FFGW, semirelaxed target reweighting, partial transported mass, or unbalanced marginal penalty.\n5. Run the solver with explicit `loss_fun`\u002F`loss`, `alpha`, `reg`, `symmetric`, `max_iter`, and `tol` when reproducibility matters.\n6. Validate the returned plan: finite nonnegative values, expected shape, total mass, row\u002Fcolumn marginal behavior for the selected mass model, and a finite GW\u002FFGW value.\n7. For larger graphs, compare an approximate\u002Fquantized result against a tiny exact subset or the bundled smoke script before scaling up.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fpot\u002Fsub-skills\u002Fgromov",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill gromov",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill gromov",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill gromov","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpot\u002Fsub-skills\u002Fgromov\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",17240,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpot\u002Fsub-skills\u002Fgromov\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",10319,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpot\u002Fsub-skills\u002Fgromov\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",11458,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpot\u002Fsub-skills\u002Fgromov\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fgromov_smoke.py","SCRIPT","脚本",9188,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpot\u002Fsub-skills\u002Fgromov\u002Fscripts\u002Fgromov_smoke.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]