[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78TCTZGGNAM5BWWZG2V03C8":3,"skill-same:01M78TCTZGGNAM5BWWZG2V03C8":63},{"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},"01M78TCTZGGNAM5BWWZG2V03C8","identity-permissions-tenancy",null,"Operate on BiSheng JWT auth, RBAC\u002FReBAC\u002FOpenFGA permissions, tenant isolation, admin scope, approval center, commercial gateway integration, and cursor permission performance.","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\u002Fbisheng\u002Fsub-skills\u002Fidentity-permissions-tenancy\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: identity-permissions-tenancy\ndescription: \"Operate on BiSheng JWT auth, RBAC\u002FReBAC\u002FOpenFGA permissions,\n  tenant isolation, admin scope, approval center, commercial gateway\n  integration, and cursor permission performance.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# identity-permissions-tenancy\n\nUse this sub-skill when a task touches BiSheng authentication, authorization, resource ownership, OpenFGA\u002FReBAC, RBAC menu permissions, multi-tenant isolation, admin scope, approval workflows, SSO\u002Forg sync, commercial gateway behavior, or cursor-pagination permission performance.\n\n## Start here\n\nRun bundled helper commands from this sub-skill directory, or adjust the script path to this directory after import.\n\n\n1. Run the read-only pattern checker before or after a permission\u002Ftenant-sensitive edit:\n   ```bash\n   python scripts\u002Fcheck_arch_rules.py --repo-root \u003Cbisheng-checkout>\n   ```\n2. Read [references\u002Fworkflows.md](references\u002Fworkflows.md) for auth, PermissionService, tenant ContextVar, gateway, approval, and cursor workflows.\n3. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for missing permissions, invisible resources, tenant leaks, SSO\u002Fgateway, and cursor list failures.\n\n## Owned responsibilities\n\n- JWT\u002Fauth user loading, menu keys, and role\u002Fuser\u002Fgroup relationships.\n- PermissionService, OpenFGA\u002FReBAC model, failed tuple retry, owner grants, relation models, and resource authorization.\n- Tenant ContextVar, SQLAlchemy tenant filter, tenant storage prefixes, tenant tree\u002Fadmin scope, user-tenant membership, and quota hierarchy.\n- Approval center and menu-approval mode when they affect access decisions.\n- Commercial gateway integration, SSO\u002FOAuth\u002FLDAP\u002FWeCom org sync, sensitive-word gateway filters, and rate\u002Fonline limits.\n- Cursor pagination patterns where permission filtering and DM8 keyset compatibility determine list correctness.\n\n## Route sibling areas instead of duplicating them\n\n- Use `backend-core` for generic FastAPI routes, schemas, service layering, and non-permission models.\n- Use `frontend-apps` for React route guards and UI rendering after the backend permission contract is known.\n- Use `knowledge-rag` for parser\u002Fvector\u002Fretrieval internals after visibility is proven correct.\n- Use `workflow-engine` for graph execution after app visibility and permissions are proven correct.\n- Use `deployment-maintenance` for running operational backfill\u002Fmigration scripts.\n\n## Non-negotiables\n\n- New resource authorization must go through PermissionService\u002FOpenFGA-aware services; do not add direct role-access table shortcuts.\n- Resource creation must write owner\u002Fauthorization tuples or enqueue failed tuple compensation as designed.\n- ORM tenant filtering applies to SELECT; raw SQL and bulk update\u002Fdelete require explicit tenant-safe handling.\n- Use tenant bypass helpers only for intentional cross-tenant maintenance reads\u002Fwrites.\n- Cursor pagination under permission filtering must advance by the last DB row, not the last visible row.\n- Frontend 403 and menu visibility bugs should not be patched until backend\u002Fmenu\u002Fplugin permission data is understood.\n","# identity-permissions-tenancy\n\nUse this sub-skill when a task touches BiSheng authentication, authorization, resource ownership, OpenFGA\u002FReBAC, RBAC menu permissions, multi-tenant isolation, admin scope, approval workflows, SSO\u002Forg sync, commercial gateway behavior, or cursor-pagination permission performance.\n\n## Start here\n\nRun bundled helper commands from this sub-skill directory, or adjust the script path to this directory after import.\n\n\n1. Run the read-only pattern checker before or after a permission\u002Ftenant-sensitive edit:\n   ```bash\n   python scripts\u002Fcheck_arch_rules.py --repo-root \u003Cbisheng-checkout>\n   ```\n2. Read [references\u002Fworkflows.md](references\u002Fworkflows.md) for auth, PermissionService, tenant ContextVar, gateway, approval, and cursor workflows.\n3. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for missing permissions, invisible resources, tenant leaks, SSO\u002Fgateway, and cursor list failures.\n\n## Owned responsibilities\n\n- JWT\u002Fauth user loading, menu keys, and role\u002Fuser\u002Fgroup relationships.\n- PermissionService, OpenFGA\u002FReBAC model, failed tuple retry, owner grants, relation models, and resource authorization.\n- Tenant ContextVar, SQLAlchemy tenant filter, tenant storage prefixes, tenant tree\u002Fadmin scope, user-tenant membership, and quota hierarchy.\n- Approval center and menu-approval mode when they affect access decisions.\n- Commercial gateway integration, SSO\u002FOAuth\u002FLDAP\u002FWeCom org sync, sensitive-word gateway filters, and rate\u002Fonline limits.\n- Cursor pagination patterns where permission filtering and DM8 keyset compatibility determine list correctness.\n\n## Route sibling areas instead of duplicating them\n\n- Use `backend-core` for generic FastAPI routes, schemas, service layering, and non-permission models.\n- Use `frontend-apps` for React route guards and UI rendering after the backend permission contract is known.\n- Use `knowledge-rag` for parser\u002Fvector\u002Fretrieval internals after visibility is proven correct.\n- Use `workflow-engine` for graph execution after app visibility and permissions are proven correct.\n- Use `deployment-maintenance` for running operational backfill\u002Fmigration scripts.\n\n## Non-negotiables\n\n- New resource authorization must go through PermissionService\u002FOpenFGA-aware services; do not add direct role-access table shortcuts.\n- Resource creation must write owner\u002Fauthorization tuples or enqueue failed tuple compensation as designed.\n- ORM tenant filtering applies to SELECT; raw SQL and bulk update\u002Fdelete require explicit tenant-safe handling.\n- Use tenant bypass helpers only for intentional cross-tenant maintenance reads\u002Fwrites.\n- Cursor pagination under permission filtering must advance by the last DB row, not the last visible row.\n- Frontend 403 and menu visibility bugs should not be patched until backend\u002Fmenu\u002Fplugin permission data is understood.\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\u002Fbisheng\u002Fsub-skills\u002Fidentity-permissions-tenancy",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 identity-permissions-tenancy",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill identity-permissions-tenancy",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill identity-permissions-tenancy","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbisheng\u002Fsub-skills\u002Fidentity-permissions-tenancy\u002FSKILL.md",[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Ftroubleshooting.md","REFERENCE","参考文档",2860,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbisheng\u002Fsub-skills\u002Fidentity-permissions-tenancy\u002Freferences\u002Ftroubleshooting.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fworkflows.md",4595,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbisheng\u002Fsub-skills\u002Fidentity-permissions-tenancy\u002Freferences\u002Fworkflows.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fcheck_arch_rules.py","SCRIPT","脚本",2152,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbisheng\u002Fsub-skills\u002Fidentity-permissions-tenancy\u002Fscripts\u002Fcheck_arch_rules.py",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]