[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SS5FPRFE7CJ3JCNFDSXM9":3,"skill-same:01M78SS5FPRFE7CJ3JCNFDSXM9":60},{"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},"01M78SS5FPRFE7CJ3JCNFDSXM9","review-and-provider-backends",null,"Configure and troubleshoot ARIS cross-model reviewers, MCP bridges, OpenAI-compatible providers, MiniMax, Claude\u002FGemini overlays, manual review, and optional Feishu\u002FLark integrations.","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\u002Faris\u002Fsub-skills\u002Freview-and-provider-backends\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: review-and-provider-backends\ndescription: \"Configure and troubleshoot ARIS cross-model reviewers, MCP\n  bridges, OpenAI-compatible providers, MiniMax, Claude\u002FGemini overlays, manual\n  review, and optional Feishu\u002FLark integrations.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Review and Provider Backends\n\nUse this sub-skill when ARIS needs an external reviewer, MCP server registration, an alternative LLM endpoint, a manual human review handoff, a Claude\u002FGemini\u002FCodex combination, MiniMax or ModelScope configuration, Feishu\u002FLark notification, or a Codex image bridge.\n\n## Route Here\n\n- Configure the default Claude executor + Codex MCP reviewer path.\n- Configure Codex executor + Claude\u002FGemini reviewer overlays.\n- Use a generic OpenAI-compatible `llm-chat` backend or MiniMax instead of Codex MCP.\n- Run manual review in browser or headless file mode.\n- Diagnose provider credentials, model names, retries, timeouts, MCP registration, protocol negotiation, and restart requirements.\n- Preserve cross-model independence and provenance evidence.\n\n## Reroute\n\n- Host skill directory, manifest, or selective install: `..\u002Finstall-and-distribution\u002FSKILL.md`.\n- Workflow selection and assurance levels: `..\u002Fworkflow-routing-and-skill-catalog\u002FSKILL.md`.\n- Research state, trace files, or watchdog: `..\u002Fstate-recovery-and-experiment-ops\u002FSKILL.md`.\n- Source edits or mocked server tests: `..\u002Frepository-maintenance\u002FSKILL.md`.\n\n## Safe Backend Pattern\n\n1. Identify executor family and reviewer family.\n2. Pick one reviewer route and record its model, server name, endpoint, and credential source.\n3. Register MCP before invoking a workflow, then restart the host agent.\n4. Validate with a trivial tool call before spending a full review request.\n5. Keep raw review artifacts and traces; never let the executor summarize away a failure.\n6. If a provider is unavailable, switch to an explicitly configured alternative or mark the review blocked.\n\n## Reference Map\n\n- `references\u002Fprovider-matrix.md` compares reviewer\u002Fprovider routes, required environment variables, and independence implications.\n- `references\u002Fmcp-servers.md` summarizes the optional server contracts and testable failure modes.\n- `references\u002Ftroubleshooting.md` covers keys, endpoints, protocol, model, timeout, and local handoff failures.\n- Root `..\u002F..\u002Freferences\u002Frepo-provenance.md` and `..\u002F..\u002Freferences\u002Ftroubleshooting.md` provide provenance and cross-cutting diagnosis.\n\n## Avoid\n\n- Never publish API keys, bearer tokens, raw provider error bodies, or local debug paths in artifacts.\n- Do not call a same-family reviewer and label it independent.\n- Do not treat mocked MCP unit tests as proof of live provider connectivity.\n- Do not install every provider dependency when one selected reviewer path is enough.\n","# Review and Provider Backends\n\nUse this sub-skill when ARIS needs an external reviewer, MCP server registration, an alternative LLM endpoint, a manual human review handoff, a Claude\u002FGemini\u002FCodex combination, MiniMax or ModelScope configuration, Feishu\u002FLark notification, or a Codex image bridge.\n\n## Route Here\n\n- Configure the default Claude executor + Codex MCP reviewer path.\n- Configure Codex executor + Claude\u002FGemini reviewer overlays.\n- Use a generic OpenAI-compatible `llm-chat` backend or MiniMax instead of Codex MCP.\n- Run manual review in browser or headless file mode.\n- Diagnose provider credentials, model names, retries, timeouts, MCP registration, protocol negotiation, and restart requirements.\n- Preserve cross-model independence and provenance evidence.\n\n## Reroute\n\n- Host skill directory, manifest, or selective install: `..\u002Finstall-and-distribution\u002FSKILL.md`.\n- Workflow selection and assurance levels: `..\u002Fworkflow-routing-and-skill-catalog\u002FSKILL.md`.\n- Research state, trace files, or watchdog: `..\u002Fstate-recovery-and-experiment-ops\u002FSKILL.md`.\n- Source edits or mocked server tests: `..\u002Frepository-maintenance\u002FSKILL.md`.\n\n## Safe Backend Pattern\n\n1. Identify executor family and reviewer family.\n2. Pick one reviewer route and record its model, server name, endpoint, and credential source.\n3. Register MCP before invoking a workflow, then restart the host agent.\n4. Validate with a trivial tool call before spending a full review request.\n5. Keep raw review artifacts and traces; never let the executor summarize away a failure.\n6. If a provider is unavailable, switch to an explicitly configured alternative or mark the review blocked.\n\n## Reference Map\n\n- `references\u002Fprovider-matrix.md` compares reviewer\u002Fprovider routes, required environment variables, and independence implications.\n- `references\u002Fmcp-servers.md` summarizes the optional server contracts and testable failure modes.\n- `references\u002Ftroubleshooting.md` covers keys, endpoints, protocol, model, timeout, and local handoff failures.\n- Root `..\u002F..\u002Freferences\u002Frepo-provenance.md` and `..\u002F..\u002Freferences\u002Ftroubleshooting.md` provide provenance and cross-cutting diagnosis.\n\n## Avoid\n\n- Never publish API keys, bearer tokens, raw provider error bodies, or local debug paths in artifacts.\n- Do not call a same-family reviewer and label it independent.\n- Do not treat mocked MCP unit tests as proof of live provider connectivity.\n- Do not install every provider dependency when one selected reviewer path is enough.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Faris\u002Fsub-skills\u002Freview-and-provider-backends",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 review-and-provider-backends",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill review-and-provider-backends",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill review-and-provider-backends","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faris\u002Fsub-skills\u002Freview-and-provider-backends\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fmcp-servers.md","REFERENCE","参考文档",2189,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faris\u002Fsub-skills\u002Freview-and-provider-backends\u002Freferences\u002Fmcp-servers.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fprovider-matrix.md",2465,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faris\u002Fsub-skills\u002Freview-and-provider-backends\u002Freferences\u002Fprovider-matrix.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",1768,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Faris\u002Fsub-skills\u002Freview-and-provider-backends\u002Freferences\u002Ftroubleshooting.md",[61,69,76,83,90,97],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[]]