[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794TQXVDP8SC9C6814X5684":3,"skill-same:01M794TQXVDP8SC9C6814X5684":67},{"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},"01M794TQXVDP8SC9C6814X5684","secretflow",null,"Guides SecretFlow workflows for runtime setup, federated data containers, the component CLI, preprocessing\u002Fstatistics\u002Fclassical ML, and privacy-oriented deployment tasks.","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\u002Fsecretflow\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: secretflow\ndescription: \"Guides SecretFlow workflows for runtime setup, federated data\n  containers, the component CLI, preprocessing\u002Fstatistics\u002Fclassical ML, and\n  privacy-oriented deployment tasks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# SecretFlow\n\nSecretFlow is a unified framework for privacy-preserving data intelligence and\nmachine learning. Use this skill when the task mentions the `secretflow`\npackage, `sf.init`, `PYU`, `SPU`, `HEU`, `TEEU`, `VDataFrame`, `HDataFrame`,\n`FedNdarray`, `component`, preprocessing, statistics, classical ML, PSI,\nKuscia, or TEE-style deployment.\n\n## Start here\n\n- Use Python 3.10 for the most reliable runtime coverage.\n- Install `secretflow` in the target environment and keep `python -m pip check`\n  clean.\n- Minimal import check: `python -c \"import secretflow as sf; print(sf.__version__)\"`\n- If you are validating an installed environment, run\n  `scripts\u002Fcheck_secretflow_install.py`.\n- Read `references\u002Frepo-provenance.md` when checking whether this skill still\n  matches the repository snapshot that produced it.\n- Read `references\u002Ftroubleshooting.md` when the install, import, CLI, backend,\n  or deployment path is failing.\n\n## Route map\n\n### `sub-skills\u002Fruntime-data\u002F`\nUse this route for local startup, device creation, reveal\u002Fto\u002Fwait behavior,\nFedNdarray, HDataFrame, VDataFrame, MixDataFrame, CSV\u002FORC IO, and small local\nsimulation flows.\n\nTypical triggers:\n- `sf.init` with `local` or a simple `cluster_config`\n- `PYU`, `SPU`, `HEU`, `TEEU`\n- `reveal`, `to`, `wait`\n- `read_csv`, `read_orc`, `partition`\n- device-mismatch or direct-to-SPU\u002FHEU errors\n\n### `sub-skills\u002Fcomponent-cli\u002F`\nUse this route for the component registry and the `secretflow component`\ncommand family, component evaluation payloads, model export, serving model\ninferencer, and plugin packaging.\n\nTypical triggers:\n- `secretflow component ls|inspect|translate|get_translation|run`\n- `comp_eval`, `Registry`, `NodeEvalParam`, `StorageConfig`, `DistData`\n- model export or serving package generation\n- plugin entry-point or component registration questions\n\n### `sub-skills\u002Fanalytics\u002F`\nUse this route for preprocessing, statistics, score-card helpers, and direct\nclassical ML APIs.\n\nTypical triggers:\n- `StandardScaler`\n- `psi_eval`, `table_statistics`, `categorical_statistics`, `ScoreCard`\n- `SSGLM`, `SSRegression`, `FlLogisticRegressionMix`,\n  `FlLogisticRegressionVertical`, `HESSLogisticRegression`\n- `KMeans`, `GNB`, `GPC`, `KNNClassifer`, and related model workflows\n\n### `sub-skills\u002Fprivacy-orchestration\u002F`\nUse this route for PSI, secure aggregation\u002Fcomparison, Kuscia, TEEU simulation,\nand deployment-mode questions.\n\nTypical triggers:\n- `psi_df`, `psi_eval`, `SPUAggregator`, `PlainComparator`\n- `KusciaTaskConfig`, `get_sf_cluster_config`, `convert_domain_data_to_individual_table`\n- `TEEU`, `auth_manager`, Ray\u002FKuscia setup, simulation\u002Fproduction mode choice\n- deployment and orchestration troubleshooting\n\n## Working style\n\n- Read the nearest sub-skill first, then cross-reference the shared root\n  troubleshooting guidance when something fails.\n- Keep runtime instructions inside this skill tree; do not rely on the original\n  repository checkout being present later.\n- For backend-specific work, prefer the smallest environment that can truthfully\n  cover the selected task. CPU coverage is enough for the core local runtime\n  and component CLI paths in this skill; advanced GPU, Kuscia, or TEE paths are\n  routed to their own guidance.\n\n## Companion files\n\n- `references\u002Frepo-provenance.md` — source snapshot and refresh baseline.\n- `references\u002Frepo-routing-metadata.json` — router metadata for repo-skills routing.\n- `references\u002Ftroubleshooting.md` — cross-cutting install\u002Fimport\u002Fbackend issues.\n- `scripts\u002Fcheck_secretflow_install.py` — quick environment and API smoke check.\n","# SecretFlow\n\nSecretFlow is a unified framework for privacy-preserving data intelligence and\nmachine learning. Use this skill when the task mentions the `secretflow`\npackage, `sf.init`, `PYU`, `SPU`, `HEU`, `TEEU`, `VDataFrame`, `HDataFrame`,\n`FedNdarray`, `component`, preprocessing, statistics, classical ML, PSI,\nKuscia, or TEE-style deployment.\n\n## Start here\n\n- Use Python 3.10 for the most reliable runtime coverage.\n- Install `secretflow` in the target environment and keep `python -m pip check`\n  clean.\n- Minimal import check: `python -c \"import secretflow as sf; print(sf.__version__)\"`\n- If you are validating an installed environment, run\n  `scripts\u002Fcheck_secretflow_install.py`.\n- Read `references\u002Frepo-provenance.md` when checking whether this skill still\n  matches the repository snapshot that produced it.\n- Read `references\u002Ftroubleshooting.md` when the install, import, CLI, backend,\n  or deployment path is failing.\n\n## Route map\n\n### `sub-skills\u002Fruntime-data\u002F`\nUse this route for local startup, device creation, reveal\u002Fto\u002Fwait behavior,\nFedNdarray, HDataFrame, VDataFrame, MixDataFrame, CSV\u002FORC IO, and small local\nsimulation flows.\n\nTypical triggers:\n- `sf.init` with `local` or a simple `cluster_config`\n- `PYU`, `SPU`, `HEU`, `TEEU`\n- `reveal`, `to`, `wait`\n- `read_csv`, `read_orc`, `partition`\n- device-mismatch or direct-to-SPU\u002FHEU errors\n\n### `sub-skills\u002Fcomponent-cli\u002F`\nUse this route for the component registry and the `secretflow component`\ncommand family, component evaluation payloads, model export, serving model\ninferencer, and plugin packaging.\n\nTypical triggers:\n- `secretflow component ls|inspect|translate|get_translation|run`\n- `comp_eval`, `Registry`, `NodeEvalParam`, `StorageConfig`, `DistData`\n- model export or serving package generation\n- plugin entry-point or component registration questions\n\n### `sub-skills\u002Fanalytics\u002F`\nUse this route for preprocessing, statistics, score-card helpers, and direct\nclassical ML APIs.\n\nTypical triggers:\n- `StandardScaler`\n- `psi_eval`, `table_statistics`, `categorical_statistics`, `ScoreCard`\n- `SSGLM`, `SSRegression`, `FlLogisticRegressionMix`,\n  `FlLogisticRegressionVertical`, `HESSLogisticRegression`\n- `KMeans`, `GNB`, `GPC`, `KNNClassifer`, and related model workflows\n\n### `sub-skills\u002Fprivacy-orchestration\u002F`\nUse this route for PSI, secure aggregation\u002Fcomparison, Kuscia, TEEU simulation,\nand deployment-mode questions.\n\nTypical triggers:\n- `psi_df`, `psi_eval`, `SPUAggregator`, `PlainComparator`\n- `KusciaTaskConfig`, `get_sf_cluster_config`, `convert_domain_data_to_individual_table`\n- `TEEU`, `auth_manager`, Ray\u002FKuscia setup, simulation\u002Fproduction mode choice\n- deployment and orchestration troubleshooting\n\n## Working style\n\n- Read the nearest sub-skill first, then cross-reference the shared root\n  troubleshooting guidance when something fails.\n- Keep runtime instructions inside this skill tree; do not rely on the original\n  repository checkout being present later.\n- For backend-specific work, prefer the smallest environment that can truthfully\n  cover the selected task. CPU coverage is enough for the core local runtime\n  and component CLI paths in this skill; advanced GPU, Kuscia, or TEE paths are\n  routed to their own guidance.\n\n## Companion files\n\n- `references\u002Frepo-provenance.md` — source snapshot and refresh baseline.\n- `references\u002Frepo-routing-metadata.json` — router metadata for repo-skills routing.\n- `references\u002Ftroubleshooting.md` — cross-cutting install\u002Fimport\u002Fbackend issues.\n- `scripts\u002Fcheck_secretflow_install.py` — quick environment and API smoke check.\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\u002Fsecretflow",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 secretflow",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill secretflow",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill secretflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsecretflow\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Frepo-provenance.md","REFERENCE","参考文档",1183,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsecretflow\u002Freferences\u002Frepo-provenance.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-routing-metadata.json",505,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsecretflow\u002Freferences\u002Frepo-routing-metadata.json",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",4502,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsecretflow\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_secretflow_install.py","SCRIPT","脚本",1083,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsecretflow\u002Fscripts\u002Fcheck_secretflow_install.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]