[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795MG0KEMHDC3896NFDTYSA":3,"skill-same:01M795MG0KEMHDC3896NFDTYSA":71},{"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},"01M795MG0KEMHDC3896NFDTYSA","stellargraph",null,"Routes StellarGraph graph machine learning tasks across graph construction, samplers, TensorFlow Keras models, link prediction, embeddings, graph classification, time series, calibration, ensembles, interpretability, datasets, and Neo4j connector 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\u002Fstellargraph\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: stellargraph\ndescription: \"Routes StellarGraph graph machine learning tasks across graph\n  construction, samplers, TensorFlow Keras models, link prediction, embeddings,\n  graph classification, time series, calibration, ensembles, interpretability,\n  datasets, and Neo4j connector workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# StellarGraph Repo Skill\n\nUse this skill when a task involves the **StellarGraph** Python package or its\nTensorFlow\u002FKeras graph machine learning workflows. It is a router: read the\nsmallest sub-skill that matches the user's task, then use the bundled references\nand scripts from that sub-skill.\n\n## First checks\n\n- StellarGraph's package metadata targets Python `>=3.6,\u003C3.9`; prefer a Python\n  3.8 environment when installing or reproducing old examples.\n- Basic install for package use: `python -m pip install stellargraph`.\n- Use `python -m pip install \"stellargraph[demos]\"` only when notebook-style\n  demo dependencies such as `gensim`, `rdflib`, `numba`, Jupyter, or plotting\n  helpers are needed.\n- Use `python -m pip install \"stellargraph[neo4j]\"` only for Neo4j connector\n  workflows; it still requires a running Neo4j service.\n- Run [`scripts\u002Fcheck_stellargraph_environment.py`](scripts\u002Fcheck_stellargraph_environment.py)\n  when you need a safe import, TensorFlow\u002FKeras, graph-construction, and optional\n  backend diagnostic before following a workflow.\n- Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for\n  Python\u002FTensorFlow\u002Fimport, optional dependency, dataset-cache, GPU, and Neo4j\n  failures that affect multiple workflows.\n- Read [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) before\n  deciding whether this skill is stale for a newer checkout or package version.\n\n## Route by task\n\n### Data, graph objects, and datasets\n\nRead [`sub-skills\u002Fgraph-data-loading\u002FSKILL.md`](sub-skills\u002Fgraph-data-loading\u002FSKILL.md)\nwhen the task is about:\n\n- constructing `StellarGraph` or `StellarDiGraph` objects from Pandas, NumPy,\n  `IndexedArray`, or NetworkX;\n- choosing node\u002Fedge IDs, types, features, weights, or directedness;\n- converting\u002Fquerying graph structure or checking graph readiness for ML;\n- using built-in dataset loader classes such as `Cora`, `MovieLens`, `WN18`, or\n  `METR_LA` without confusing cache\u002Fdownload behavior with model logic.\n\n### Walkers, samplers, and Keras generators\n\nRead [`sub-skills\u002Fsampling-generators\u002FSKILL.md`](sub-skills\u002Fsampling-generators\u002FSKILL.md)\nwhen the task is about random walks, sampled breadth-first neighborhoods,\n`UnsupervisedSampler`, full-batch, sampled mini-batch, padded-graph,\nknowledge-graph, or sliding-window generators.\n\nUse this route before model routes when the failure mentions `flow`,\n`Sequence`, `num_samples`, `n_size`, node\u002Flink IDs, batch dimensions, sparse\nadjacency tensors, or generator\u002Fmodel incompatibility.\n\n### Node classification or node regression with GNNs\n\nRead [`sub-skills\u002Fnode-classification-gnns\u002FSKILL.md`](sub-skills\u002Fnode-classification-gnns\u002FSKILL.md)\nfor supervised or semi-supervised node workflows using `GCN`, `GAT`,\n`GraphSAGE`, `DirectedGraphSAGE`, `HinSAGE`, `ClusterNodeGenerator` + `GCN`,\n`RGCN`, `PPNP`, `APPNP`, or the SGC-style linear GCN pattern.\n\nUse sibling routes for upstream graph construction and generator details; this\nroute owns model selection, Keras tensor wiring, targets, and training\u002Fevaluation\nshape decisions for node tasks.\n\n### Link prediction, link regression, and knowledge graphs\n\nRead [`sub-skills\u002Flink-prediction-kg\u002FSKILL.md`](sub-skills\u002Flink-prediction-kg\u002FSKILL.md)\nfor edge-split workflows, `GraphSAGELinkGenerator`, `HinSAGELinkGenerator`,\n`FullBatchLinkGenerator`, link inference heads, temporal link prediction, and\nknowledge graph completion with `KGTripleGenerator`, `ComplEx`, `DistMult`,\n`RotatE`, `RotE`, or `RotH`.\n\n### Unsupervised embeddings and representation learning\n\nRead [`sub-skills\u002Fembedding-workflows\u002FSKILL.md`](sub-skills\u002Fembedding-workflows\u002FSKILL.md)\nfor Node2Vec\u002FDeepWalk, Metapath2Vec, Attri2Vec, unsupervised GraphSAGE,\nDeep Graph Infomax, GraphWave, Watch Your Step, or extracting embeddings for\nscikit-learn\u002FKeras downstream models.\n\n### Graph classification and graph time series\n\nRead [`sub-skills\u002Fgraph-time-series-workflows\u002FSKILL.md`](sub-skills\u002Fgraph-time-series-workflows\u002FSKILL.md)\nfor graph-level classification with `PaddedGraphGenerator`,\n`GCNSupervisedGraphClassification`, `DeepGraphCNN`, or `SortPooling`, and for\nspatio-temporal forecasting with `SlidingFeaturesNodeGenerator`, fixed\nadjacency, and `GCN_LSTM`.\n\n### Model operations, interpretability, and Neo4j\n\nRead [`sub-skills\u002Fmodel-ops-interpretability\u002FSKILL.md`](sub-skills\u002Fmodel-ops-interpretability\u002FSKILL.md)\nfor:\n\n- `custom_keras_layers` when saving\u002Floading Keras models that contain\n  StellarGraph layers;\n- calibration (`TemperatureCalibration`, `IsotonicCalibration`, expected\n  calibration error, reliability plots);\n- `Ensemble` and `BaggingEnsemble` wrappers;\n- GCN\u002FGAT saliency and integrated-gradient interpretability;\n- optional Neo4j connector objects and service-backed generators.\n\n## Package map\n\nRead [`references\u002Fpackage-overview.md`](references\u002Fpackage-overview.md) when a\nuser names an algorithm, dataset, module, notebook title, or capability and you\nneed to pick the correct route before acting.\n\n## Boundaries\n\n- This skill teaches package operation, not repository release maintenance or CI\n  pipeline editing.\n- Do not run long notebook demos, dataset downloads, Neo4j services, or GPU\n  checks unless the user explicitly wants that external dependency or runtime.\n- Prefer safe bundled scripts and tiny synthetic fixtures before attempting full\n  notebook-scale examples.\n","# StellarGraph Repo Skill\n\nUse this skill when a task involves the **StellarGraph** Python package or its\nTensorFlow\u002FKeras graph machine learning workflows. It is a router: read the\nsmallest sub-skill that matches the user's task, then use the bundled references\nand scripts from that sub-skill.\n\n## First checks\n\n- StellarGraph's package metadata targets Python `>=3.6,\u003C3.9`; prefer a Python\n  3.8 environment when installing or reproducing old examples.\n- Basic install for package use: `python -m pip install stellargraph`.\n- Use `python -m pip install \"stellargraph[demos]\"` only when notebook-style\n  demo dependencies such as `gensim`, `rdflib`, `numba`, Jupyter, or plotting\n  helpers are needed.\n- Use `python -m pip install \"stellargraph[neo4j]\"` only for Neo4j connector\n  workflows; it still requires a running Neo4j service.\n- Run [`scripts\u002Fcheck_stellargraph_environment.py`](scripts\u002Fcheck_stellargraph_environment.py)\n  when you need a safe import, TensorFlow\u002FKeras, graph-construction, and optional\n  backend diagnostic before following a workflow.\n- Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for\n  Python\u002FTensorFlow\u002Fimport, optional dependency, dataset-cache, GPU, and Neo4j\n  failures that affect multiple workflows.\n- Read [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md) before\n  deciding whether this skill is stale for a newer checkout or package version.\n\n## Route by task\n\n### Data, graph objects, and datasets\n\nRead [`sub-skills\u002Fgraph-data-loading\u002FSKILL.md`](sub-skills\u002Fgraph-data-loading\u002FSKILL.md)\nwhen the task is about:\n\n- constructing `StellarGraph` or `StellarDiGraph` objects from Pandas, NumPy,\n  `IndexedArray`, or NetworkX;\n- choosing node\u002Fedge IDs, types, features, weights, or directedness;\n- converting\u002Fquerying graph structure or checking graph readiness for ML;\n- using built-in dataset loader classes such as `Cora`, `MovieLens`, `WN18`, or\n  `METR_LA` without confusing cache\u002Fdownload behavior with model logic.\n\n### Walkers, samplers, and Keras generators\n\nRead [`sub-skills\u002Fsampling-generators\u002FSKILL.md`](sub-skills\u002Fsampling-generators\u002FSKILL.md)\nwhen the task is about random walks, sampled breadth-first neighborhoods,\n`UnsupervisedSampler`, full-batch, sampled mini-batch, padded-graph,\nknowledge-graph, or sliding-window generators.\n\nUse this route before model routes when the failure mentions `flow`,\n`Sequence`, `num_samples`, `n_size`, node\u002Flink IDs, batch dimensions, sparse\nadjacency tensors, or generator\u002Fmodel incompatibility.\n\n### Node classification or node regression with GNNs\n\nRead [`sub-skills\u002Fnode-classification-gnns\u002FSKILL.md`](sub-skills\u002Fnode-classification-gnns\u002FSKILL.md)\nfor supervised or semi-supervised node workflows using `GCN`, `GAT`,\n`GraphSAGE`, `DirectedGraphSAGE`, `HinSAGE`, `ClusterNodeGenerator` + `GCN`,\n`RGCN`, `PPNP`, `APPNP`, or the SGC-style linear GCN pattern.\n\nUse sibling routes for upstream graph construction and generator details; this\nroute owns model selection, Keras tensor wiring, targets, and training\u002Fevaluation\nshape decisions for node tasks.\n\n### Link prediction, link regression, and knowledge graphs\n\nRead [`sub-skills\u002Flink-prediction-kg\u002FSKILL.md`](sub-skills\u002Flink-prediction-kg\u002FSKILL.md)\nfor edge-split workflows, `GraphSAGELinkGenerator`, `HinSAGELinkGenerator`,\n`FullBatchLinkGenerator`, link inference heads, temporal link prediction, and\nknowledge graph completion with `KGTripleGenerator`, `ComplEx`, `DistMult`,\n`RotatE`, `RotE`, or `RotH`.\n\n### Unsupervised embeddings and representation learning\n\nRead [`sub-skills\u002Fembedding-workflows\u002FSKILL.md`](sub-skills\u002Fembedding-workflows\u002FSKILL.md)\nfor Node2Vec\u002FDeepWalk, Metapath2Vec, Attri2Vec, unsupervised GraphSAGE,\nDeep Graph Infomax, GraphWave, Watch Your Step, or extracting embeddings for\nscikit-learn\u002FKeras downstream models.\n\n### Graph classification and graph time series\n\nRead [`sub-skills\u002Fgraph-time-series-workflows\u002FSKILL.md`](sub-skills\u002Fgraph-time-series-workflows\u002FSKILL.md)\nfor graph-level classification with `PaddedGraphGenerator`,\n`GCNSupervisedGraphClassification`, `DeepGraphCNN`, or `SortPooling`, and for\nspatio-temporal forecasting with `SlidingFeaturesNodeGenerator`, fixed\nadjacency, and `GCN_LSTM`.\n\n### Model operations, interpretability, and Neo4j\n\nRead [`sub-skills\u002Fmodel-ops-interpretability\u002FSKILL.md`](sub-skills\u002Fmodel-ops-interpretability\u002FSKILL.md)\nfor:\n\n- `custom_keras_layers` when saving\u002Floading Keras models that contain\n  StellarGraph layers;\n- calibration (`TemperatureCalibration`, `IsotonicCalibration`, expected\n  calibration error, reliability plots);\n- `Ensemble` and `BaggingEnsemble` wrappers;\n- GCN\u002FGAT saliency and integrated-gradient interpretability;\n- optional Neo4j connector objects and service-backed generators.\n\n## Package map\n\nRead [`references\u002Fpackage-overview.md`](references\u002Fpackage-overview.md) when a\nuser names an algorithm, dataset, module, notebook title, or capability and you\nneed to pick the correct route before acting.\n\n## Boundaries\n\n- This skill teaches package operation, not repository release maintenance or CI\n  pipeline editing.\n- Do not run long notebook demos, dataset downloads, Neo4j services, or GPU\n  checks unless the user explicitly wants that external dependency or runtime.\n- Prefer safe bundled scripts and tiny synthetic fixtures before attempting full\n  notebook-scale examples.\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\u002Fstellargraph",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 stellargraph",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill stellargraph",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill stellargraph","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fpackage-overview.md","REFERENCE","参考文档",4304,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Freferences\u002Fpackage-overview.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",3041,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",492,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",5955,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_stellargraph_environment.py","SCRIPT","脚本",5707,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstellargraph\u002Fscripts\u002Fcheck_stellargraph_environment.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":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},"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":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},"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":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},"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":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},"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",[],[]]