[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794TZPE2ANKKF7HBW6FVH91":3,"skill-same:01M794TZPE2ANKKF7HBW6FVH91":59},{"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},"01M794TZPE2ANKKF7HBW6FVH91","privacy-orchestration",null,"Guides SecretFlow PSI, secure aggregation\u002Fcomparison, Kuscia, TEEU simulation, and deployment orchestration 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\u002Fsecretflow\u002Fsub-skills\u002Fprivacy-orchestration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: privacy-orchestration\ndescription: \"Guides SecretFlow PSI, secure aggregation\u002Fcomparison, Kuscia, TEEU\n  simulation, and deployment orchestration workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Privacy and orchestration\n\nUse this sub-skill when the task depends on privacy-preserving protocols,\ncluster wiring, or deployment mode selection rather than on direct model or\ncomponent APIs.\n\n## Owns\n\n- PSI helpers and PSI protocol choices\n- secure aggregation and comparison helpers\n- Kuscia request parsing and SecretFlow cluster conversion helpers\n- TEEU simulation guidance and deployment flow\n- debug\u002Fsimulation\u002Fproduction\u002FKuscia deployment-mode decisions\n- common party\u002Fdevice co-location and orchestration failures\n\n## Does not own\n\n- plain device setup and data containers — use `runtime-data`\n- direct preprocessing\u002Fstatistics\u002Fclassical ML APIs — use `analytics`\n- component CLI \u002F export workflows — use `component-cli`\n\n## Trigger phrases\n\nUse this route when a user asks things like:\n- how to run PSI in SecretFlow\n- how to compare or aggregate data securely\n- how to parse a Kuscia task config\n- how to choose debug, simulation, production, or Kuscia deployment modes\n- how to use TEEU in simulation mode\n- why a protocol or party layout is failing\n\n## Reading order\n\n1. Read `references\u002Fprivacy-orchestration.md` for the protocol and deployment\n   map.\n2. Read the root troubleshooting page when the problem is an install, backend,\n   or cluster issue that is not unique to this workflow.\n3. Use `scripts\u002Fkuscia_config_smoke.py` when you want a tiny config-parser check\n   that does not require any external cluster.\n\n## Workflow\n\n1. Pick the deployment mode before picking a protocol. The runtime shape changes\n   between debug, simulation, production, and Kuscia.\n2. For PSI or comparison tasks, decide which party owns the result and whether\n   the inputs must already be co-located.\n3. For Kuscia, parse the request shape first and only then derive the SecretFlow\n   cluster config.\n4. For TEEU, treat the auth-manager and memory prerequisites as part of the\n   workflow, not as an afterthought.\n\n## Common decisions\n\n- Use the simplest PSI protocol that matches the dataset size and privacy\n  needs.\n- Use simulation mode when the task is about code flow or basic validation and\n  not about a production deployment.\n- Use Kuscia when the task names task orchestration, port reuse, or production\n  scheduling.\n- Use TEEU simulation for educational or quick-start validation, not as a\n  production security proof.\n\n## Bundled files\n\n- `references\u002Fprivacy-orchestration.md` — PSI, deployment, Kuscia, and TEEU notes.\n- `scripts\u002Fkuscia_config_smoke.py` — tiny Kuscia config parsing helper.\n","# Privacy and orchestration\n\nUse this sub-skill when the task depends on privacy-preserving protocols,\ncluster wiring, or deployment mode selection rather than on direct model or\ncomponent APIs.\n\n## Owns\n\n- PSI helpers and PSI protocol choices\n- secure aggregation and comparison helpers\n- Kuscia request parsing and SecretFlow cluster conversion helpers\n- TEEU simulation guidance and deployment flow\n- debug\u002Fsimulation\u002Fproduction\u002FKuscia deployment-mode decisions\n- common party\u002Fdevice co-location and orchestration failures\n\n## Does not own\n\n- plain device setup and data containers — use `runtime-data`\n- direct preprocessing\u002Fstatistics\u002Fclassical ML APIs — use `analytics`\n- component CLI \u002F export workflows — use `component-cli`\n\n## Trigger phrases\n\nUse this route when a user asks things like:\n- how to run PSI in SecretFlow\n- how to compare or aggregate data securely\n- how to parse a Kuscia task config\n- how to choose debug, simulation, production, or Kuscia deployment modes\n- how to use TEEU in simulation mode\n- why a protocol or party layout is failing\n\n## Reading order\n\n1. Read `references\u002Fprivacy-orchestration.md` for the protocol and deployment\n   map.\n2. Read the root troubleshooting page when the problem is an install, backend,\n   or cluster issue that is not unique to this workflow.\n3. Use `scripts\u002Fkuscia_config_smoke.py` when you want a tiny config-parser check\n   that does not require any external cluster.\n\n## Workflow\n\n1. Pick the deployment mode before picking a protocol. The runtime shape changes\n   between debug, simulation, production, and Kuscia.\n2. For PSI or comparison tasks, decide which party owns the result and whether\n   the inputs must already be co-located.\n3. For Kuscia, parse the request shape first and only then derive the SecretFlow\n   cluster config.\n4. For TEEU, treat the auth-manager and memory prerequisites as part of the\n   workflow, not as an afterthought.\n\n## Common decisions\n\n- Use the simplest PSI protocol that matches the dataset size and privacy\n  needs.\n- Use simulation mode when the task is about code flow or basic validation and\n  not about a production deployment.\n- Use Kuscia when the task names task orchestration, port reuse, or production\n  scheduling.\n- Use TEEU simulation for educational or quick-start validation, not as a\n  production security proof.\n\n## Bundled files\n\n- `references\u002Fprivacy-orchestration.md` — PSI, deployment, Kuscia, and TEEU notes.\n- `scripts\u002Fkuscia_config_smoke.py` — tiny Kuscia config parsing helper.\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\u002Fsub-skills\u002Fprivacy-orchestration",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 privacy-orchestration",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill privacy-orchestration",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill privacy-orchestration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsecretflow\u002Fsub-skills\u002Fprivacy-orchestration\u002FSKILL.md",[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fprivacy-orchestration.md","REFERENCE","参考文档",4683,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsecretflow\u002Fsub-skills\u002Fprivacy-orchestration\u002Freferences\u002Fprivacy-orchestration.md",{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"scripts\u002Fkuscia_config_smoke.py","SCRIPT","脚本",819,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsecretflow\u002Fsub-skills\u002Fprivacy-orchestration\u002Fscripts\u002Fkuscia_config_smoke.py",[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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",[],[]]